The Hidden Cost of Running Multiple AI Coding Agents
My terminal has several AI coding agents running. One is adding a feature in a side project, another is writing tests in a second repository, a third is reviewing a branch. Every pane is moving, and it looks like a lot of work is getting done.
Then the panes stop, one after the other, with the same kind of message: usage limit reached. The work doesn't fail. It just waits, until the window resets or until I decide to pay for more.
I use Claude Code on a Claude Pro plan and OpenAI Codex on ChatGPT Plus, two subscriptions of $20 a month each in the US (billed monthly), plus tmux, Git worktrees, subagents, Agent Teams and Orca. That combination raised a question I couldn't answer from the feeling of speed: are parallel AI agents making me more productive, or am I just reaching my subscription usage limits faster?
This post is my answer, built from the official docs of both tools and the research on AI coding productivity:
1. What a Claude Pro and a ChatGPT Plus plan actually give you, and what they don't promise.
2. Single agent, tmux sessions, subagents and Agent Teams compared, with diagrams.
3. A tested tmux + Git worktree workflow, and where Orca fits.
4. A way to measure it on your own plans, with the metrics that matter.
5. A decision framework and a list of habits that make a $20 plan last.
One idea runs through all of it: more generated code is not more delivered software.
---
The illusion of infinite productivity
Running four agents feels four times faster. It isn't, and the reason is in three words people use as synonyms.
| Term | What it measures | What parallel agents change |
| --- | --- | --- |
| Throughput | Work items completed per hour (here: code generated, not yet reviewed) | Can increase for independent tasks, but coordination and resource limits may reduce the gains |
| Latency | Time from "start this task" to "this task is done" | Can go down for independent tasks, up for dependent ones |
| Productivity | Verified, merged, working features per unit of your time and budget | Unknown until you count review, rework and waiting |
At best, parallel agents raise throughput of generated code. Productivity only counts code that passed tests, survived review and merged. Everything between those two numbers is work that lands on you: reading diffs, resolving conflicts, re-explaining context, and waiting for a reset.
There is research on how unreliable the feeling of speed is. In METR's 2025 randomized controlled trial, 16 experienced open-source developers worked on 246 real issues from their own repositories. With AI tools allowed, they took 19% longer. Before the study they expected a 24% speedup, and afterwards they still believed AI had made them about 20% faster.
That result has limits that matter. It used early-2025 tools (mostly Cursor with Claude 3.5 and 3.7 Sonnet), large mature codebases and a small sample. In a February 2026 update, METR said developers are probably more sped up now, but its new data is "only very weak evidence" of how much, partly because many developers refused to work without AI. So the study is not evidence that AI makes you slower. Its useful lesson here is simpler: your sense of speed is not a measurement.
Google's DORA team points in the same direction from a different angle. The 2024 report associated higher AI adoption with better documentation and code review speed, but also with an estimated 1.5% drop in delivery throughput and 7.2% drop in delivery stability. The 2025 report sums it up as AI being an amplifier of what a team already does well or badly.
---
What Claude Pro and ChatGPT Plus usage limits actually give you
Before comparing workflows, get the budget right. Neither vendor sells you a fixed number of tokens, and several different limits get mixed up in discussions online.
| Limit | What it is | Claude Pro | ChatGPT Plus (Codex) |
| --- | --- | --- | --- |
| Session window | Usage allowed inside a five-hour period | Five hours, starting with your first message (source) | Five hours, published as ranges of local messages per model (source) |
| Weekly limit | A second cap over the week | Yes, across all models, reset at a fixed time per account | "Weekly limits may also apply" |
| Shared pool | What draws from the same budget | claude.ai, Claude Code and Claude Desktop | Local messages and cloud tasks |
| Published allowance | A guaranteed token count | None; "the number of messages you can send will vary" (source) | Ranges, explicitly "not fixed message limits" |
| Paying for more | When the plan runs out | Optional usage credits, prepaid, billed at standard API rates (source) | Optional credits, or an API key billed at API rates |
| Context window | How much one conversation can hold | A model property and a separate limit, though a fuller context costs more quota per turn | Same: a separate limit, but more context means more usage |
| How to check | Remaining usage | /usage in Claude Code, Settings > Usage | /status in the CLI, the Codex usage dashboard |
Prices and ranges are as of November 2026. Three details change how you should work.
The pool is shared. Every Claude Code session in every tmux pane, every subagent and every chat on claude.ai draws from the same Pro budget. Ten terminals are not ten budgets. On the OpenAI side, local messages and cloud tasks share one allowance too, and the docs warn that cloud tasks "may use more of your allowance than local messages".
Usage is not message count. Anthropic says usage depends on the length and complexity of the conversation, the features you use, the model and the effort level. Its Claude Code guide adds the part most people miss: every turn resends the conversation so far, plus CLAUDE.md and the files Claude has read, before your new prompt. A long session gets more expensive per message as it grows.
Model choice is the biggest lever you control. OpenAI publishes it plainly. On Plus, the heaviest model in the Codex table allows 5 to 45 local messages per five hours, and the lightest allows 350 to 3,000. The published ranges for the two ends of the table differ by about two orders of magnitude, and OpenAI says they vary by task, so read them as a direction, not a conversion rate. Anthropic doesn't publish numbers, but says Opus "uses meaningfully more of your quota" and that Sonnet is the right choice for most coding work.
Two traps to avoid. API prices are not the price of subscription usage; they only apply when you turn on usage credits or use an API key. And if ANTHROPIC_API_KEY is set in your shell, Claude Code uses that key instead of your subscription, which can turn an evening of "free" agents into an API bill.
---
One agent vs multiple agents
There are four architectures in my day-to-day, and they behave very differently on tokens, context and review.
flowchart LR
subgraph A["A. Single agent"]
D1([You]) --> S1[One session]
end
subgraph B["B. tmux sessions"]
D2([You]) --> P1[Claude Code: project 1]
D2 --> P2[Codex: project 2]
D2 --> P3[Claude Code: project 3]
end
subgraph C["C. Subagents"]
D3([You]) --> M[Main session]
M --> SA1[Explore]
M --> SA2[Test runner]
SA1 -. summary .-> M
SA2 -. summary .-> M
end
subgraph D["D. Agent Team"]
D4([You]) --> L[Lead]
L --> T1[Teammate 1]
L --> T2[Teammate 2]
T1 <-. messages .-> T2
end
A. A single agent
One Claude Code or Codex session working through tasks in order. It has the best context continuity: the agent remembers why a decision was made, and you review one stream of changes. Debugging is simple because there is one author.
It isn't automatically the most token-efficient option, though. Because every turn resends the whole conversation, a session that carries three unrelated tasks pays for the history of the first two while working on the third. Anthropic's own best practices say /clear between unrelated tasks "costs nothing" and stops the next task from paying for the previous one. A single agent is efficient when its context is relevant, not when it is long.
B. Multiple tmux sessions across projects
Independent agents on independent projects. This is the cleanest form of parallelism: no shared files, no merge conflicts, and each agent has a small, relevant context.
Two limits still apply. All the Claude Code sessions share one quota, so parallelism spends your five-hour window faster; it doesn't create more of it. And the scarce resource moves to you: each pane eventually asks a question, needs a decision or produces a diff to review. tmux keeps the sessions alive and organized. It does nothing for token consumption.
This is also where mixing providers is a real advantage. Claude Pro and ChatGPT Plus are two separate pools. Putting one project on Claude Code and another on Codex is the only way in this post to get more included allowance without upgrading a plan or paying API rates for credits.
C. Subagents inside one project
A parent session delegates a bounded job to a subagent. In Claude Code, each subagent runs in its own context window, and only its result returns to the main conversation. The built-in Explore subagent, for example, is read-only and made for searching a codebase.
The common misunderstanding is that subagents save tokens. They save context, which is different. The docs say each subagent sends its own requests, which "count toward the same usage limits as your main conversation". What you gain is a main session that stays short and focused, because 40 files of search results never enter it. Codex says the same about its own subagents: they "consume more tokens than comparable single-agent runs" (source).
A real example from this post. To research it, I delegated the documentation reading to Claude Code subagents (Claude Code 2.1.308): five of them read the Anthropic help center, the Claude Code docs, the Codex docs, Orca's docs and the productivity studies in parallel, and all came back in under two minutes. Claude Code reported about 430,000 tokens across those five. That's a token total, not a share of my quota, which neither tool exposes as a number. That's the ideal case for subagents: read-only, independent, verbose work. It still needed checking: one later verification pass found that an earlier subagent summary had marked a sentence as missing from a doc page when it was there.
Subagents pay off for narrow, verbose, read-heavy tasks: exploring a codebase, running a test suite and summarizing failures, reviewing a diff. They pay off more with a cheaper model; Claude Code lets you set model: haiku on a simple subagent.
D. Agent Teams
Agent Teams in Claude Code are experimental and off by default (you enable them with CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1). A lead session coordinates separate Claude Code instances that share a task list and message each other directly. Subagents return their result to the caller. One catch if you use both: while Agent Teams are enabled, a subagent that Claude names launches as a teammate, so a team, with team-level token costs, can form when you only asked for delegation.
The docs are direct about the cost. Agent Teams "use significantly more tokens than a single session", usage scales with the number of active teammates, and the costs page estimates about 7x the tokens of a standard session when teammates run in plan mode. The same docs say that for sequential tasks, same-file edits or work with many dependencies, a single session or subagents are more effective.
Anthropic's engineering team found the same pattern outside Claude Code. Its multi-agent research system used about 15 times the tokens of a chat, worked best on breadth-first research, and the post notes that "most coding tasks involve fewer truly parallelizable tasks than research".
| | Single agent | tmux sessions | Subagents | Agent Team |
| --- | --- | --- | --- | --- |
| Context | One, continuous | One per project | Isolated per task, summary returns | One per teammate |
| Tokens vs one session | Baseline | Sum of sessions, same pool | Higher, but the main context stays small | Highest, scales with teammates |
| Coordination | None | You | The main agent | Lead, task list, messages |
| Merge conflicts | None | None across projects | Low if subagents only read | Possible on shared files |
| Best for | Dependent, sequential work | Unrelated projects | Search, tests, review | Research, competing hypotheses, cross-layer work with clear ownership |
---
tmux, Git worktrees and multi-agent IDEs
When you want two agents on the same repository, they need separate checkouts, or they'll edit the same files under each other. Anthropic's docs put it simply: give each piece of work "its own checkout so the edits can't collide". Git worktrees are the standard way to do that: each worktree is a separate directory, on its own branch, sharing one repository.
Here is the workflow I'd use. I ran the git and tmux commands in a scratch repository with git 2.54 and tmux 3.8, with the agent commands replaced by echo so no usage was spent (the git pull and npm ci lines need a real remote and project, so they didn't run there):
# From the main checkout, with an up-to-date main
git switch main && git pull --ff-only
# 1. One worktree and one branch per independent task
git worktree add -b feat/rbac ../app-rbac main
git worktree add -b feat/audit-log ../app-audit main
# 2. Worktrees are fresh checkouts: no .env, no node_modules.
# Start from the committed template, never your real .env, then give
# each worktree its own dev-only database and no production secrets.
cp .env.example ../app-rbac/.env && cp .env.example ../app-audit/.env
createdb app_rbac && createdb app_audit
perl -pi -e 's|^DATABASE_URL=.*|DATABASE_URL=postgres://localhost:5432/app_rbac|' ../app-rbac/.env
perl -pi -e 's|^DATABASE_URL=.*|DATABASE_URL=postgres://localhost:5432/app_audit|' ../app-audit/.env
(cd ../app-rbac && npm ci) && (cd ../app-audit && npm ci)
# 3. One tmux session, one window per agent
tmux new-session -d -s agents -n rbac -c "$PWD/../app-rbac"
tmux new-window -t agents -n audit -c "$PWD/../app-audit"
tmux send-keys -t agents:rbac 'claude "Implement docs/tasks/rbac.md. Run npm test before you stop."' Enter
tmux send-keys -t agents:audit 'codex "Implement docs/tasks/audit-log.md. Run npm test before you stop."' Enter
tmux attach -t agents
Each task description lives in a file in the repository, so both agents start from the same written requirements instead of a prompt you typed differently twice. The second window runs Codex on purpose. One practical detail: the first time you run claude in a new directory it asks you to trust the folder, so attach to the session and accept it before the prompt runs.
Then review and merge like you would a colleague's branch:
git log --oneline main..feat/rbac # what the agent committed
git diff --stat main...feat/rbac # how big the change is
(cd ../app-rbac && npm test) # run the checks yourself
git switch main && git merge --no-ff feat/rbac
# Cleanup, only after the merge and once nothing in the worktree still matters
git -C ../app-rbac status --short --ignored # lists what removal would touch
git worktree remove ../app-rbac # fails on modified or untracked files
git branch -d feat/rbac # fails if the branch isn't merged
dropdb app_rbac # the worktree's own dev database
# Repeat for feat/audit-log, ../app-audit and app_audit, then:
tmux kill-session -t agents
In my test, git worktree remove refused to delete a worktree with an untracked file until I passed --force, and git branch -d refused to delete a branch still checked out in a worktree. Keep those guards, and know their gap: gitignored files don't count, so node_modules and a .env you edited inside a worktree are deleted without a warning. That's why the status --ignored line comes first: if it lists anything you still need, copy it out before you remove the worktree.
Both tools also do this for you. claude --worktree feature-auth starts a Claude Code session in a new worktree, and a .worktreeinclude file lists the gitignored files to copy into it; keep that list to dev-only files, for the same reason as above. OpenAI's desktop app has a Worktree mode for running Codex chats in parallel (docs); its docs don't describe the same for the CLI.
A worktree isolates files, not processes. Both agents run as your user, on the same machine, with the same network access, the same credentials in ~/.aws or ~/.ssh, and often the same local database and ports. If two worktrees run migrations against one Postgres database, they will collide, which is why each one got its own above. If you need security isolation, that comes from the agents' sandbox settings, containers or separate machines, not from a second directory.
Where Orca fits
Orca is an open-source (MIT) desktop app for running coding agents side by side, each in its own Git worktree. It supports Claude Code, Codex and many other CLI agents, and you use your own subscriptions; it doesn't sell model usage. According to its docs, it creates a real git worktree per task, shows diffs you can annotate and send back to the agent, notifies you when an agent finishes or needs attention, and tracks the usage and reset times of providers like Claude Code and Codex in its status bar.
What it doesn't do: raise your limits. Orca runs the same CLIs against the same plans, so four agents in Orca spend the same pool as four agents in tmux. Its own docs say to prefer the provider console for authoritative spend. Its value is visibility (which agent is waiting on you, how much quota is left) and less manual worktree work. Its cost is another app in your toolchain that releases very often (v1.4.245 on October 30, 2026), with plugins that, per its release notes, run with full access to your computer once approved.
My rule: if you run one or two agents, tmux and three git commands are enough. When you regularly lose track of which agent is blocked, a tool like Orca starts paying for itself in attention, not in tokens.
---
The hidden cost of parallelism
Parallel agents move work to places you don't see in the moment.
Duplicated context. Every agent learns your codebase from scratch: it reads CLAUDE.md or AGENTS.md, explores the folders, opens the same core files. Four agents pay that onboarding four times, from one quota.
Coordination tokens. In an Agent Team, messages between teammates and task-list updates are model calls too. Every teammate is also a separate Claude instance with its own context window, which is the reason Anthropic gives for teams in plan mode using about seven times the tokens of a standard session.
Merge conflicts and semantic conflicts. Worktrees prevent agents from overwriting each other's files. They don't prevent two branches from making incompatible decisions, like two different error formats or two ways of checking a role. Git merges those cleanly, and your tests or your users find them later.
Review is serial. You can run five agents in parallel, but you read diffs one at a time. If an agent produces a 600-line change in 20 minutes and you need 40 minutes to review it properly, adding a second agent mostly doubles your review queue.
Interruptions. A limit that hits halfway through a task stalls it. Recent Claude Code versions (2.1.234 and later) wait and continue on their own after the reset, but the first request after a long break misses the prompt cache and reprocesses your whole context. Meanwhile, the half-finished branch blocks whatever depended on it.
flowchart LR
G[Agents generate code<br/>parallel] --> R[You review<br/>serial] --> T[Tests and fixes] --> M[Merged and verified]
R -. rework .-> G
The bottleneck in AI-assisted development is usually the review step, not the generation step. Add agents until your review queue is full, and stop there.
---
How to measure this on your own plans
No article can tell you which workflow wins on your codebase, your plans and your review speed. A small, controlled comparison can, and it's the only way to stop trusting the feeling of speed that METR measured. This is the setup I'd use.
The project. A TypeScript REST API with PostgreSQL, authentication, role-based access control (RBAC), automated tests and one small frontend screen. Every run starts from the same commit, the same written task files and the same acceptance tests.
The tasks. A mix of independent and dependent work:
| # | Task | Depends on |
| --- | --- | --- |
| T1 | Add a roles table, migration and seed | none |
| T2 | RBAC middleware: deny by default, check role and resource owner | T1 |
| T3 | Audit log of security events (login, failed login, role change) | none |
| T4 | Rate limiting on login with progressive lockout | none |
| T5 | Admin screen listing users and their roles | T2 |
| T6 | Tests that try IDOR and privilege escalation against T2 | T2 |
The workflows. Single agent, tmux sessions (one task per session, same checkout, to expose conflicts), subagents, an Agent Team, tmux with worktrees, and worktrees split across Claude Code and Codex. If you use Orca, run the last one from it as a seventh. Change one thing at a time: same models, same task files, same tests, and at least two runs per workflow, because one run of an agent is an anecdote.
The metrics. Wall-clock time to the last merged task, active human time (time you spend typing, reviewing or deciding), input, output and cache tokens, quota consumed, sessions interrupted by a limit, acceptance test pass rate, security issues found in review, merge conflicts, rework rounds, and verified tasks per hour: tasks that passed the acceptance tests and your review, divided by wall-clock hours.
Both tools expose token data. Claude Code exports claude_code.token.usage through OpenTelemetry when CLAUDE_CODE_ENABLE_TELEMETRY=1 is set and an exporter is configured (for example OTEL_METRICS_EXPORTER=console), with input, output and cache tokens as separate types, and codex exec --json emits a turn.completed event with input_tokens, cached_input_tokens and output_tokens (docs). Quota is harder: neither plan shows a raw number, so record the percentage from /usage or /status before and after each run.
Put one row per workflow and one column per metric in a spreadsheet, and read verified tasks per hour first. A workflow that finishes faster but needs more rework or more of your review time hasn't won anything.
What I'd expect, as a hypothesis and not a result: worktrees across two providers will win on verified tasks per hour for T1, T3 and T4, and a single agent will win on T2, T5 and T6, because those three share one design decision (how a role is checked) that is cheaper to make once than to explain to three agents.
---
How to get more from your AI subscription
These are the habits I'd apply before upgrading any plan. Each one comes from the vendors' own guidance or follows from how usage is counted.
1. Clear between tasks. /clear when switching to unrelated work, /compact with a focus when continuing a long task. Every turn resends the history, so stale history is the most expensive thing in your session.
2. Pick the model per task. Sonnet for most Claude Code work, Opus only when it's stuck or for wide changes (/model opusplan plans with Opus and executes with Sonnet). On Codex, a lighter model for routine edits buys you a much larger allowance.
3. Keep the always-loaded files small. Anthropic suggests keeping CLAUDE.md under 200 lines; OpenAI suggests reducing the size of AGENTS.md. Both get read on every session.
4. Turn off what you don't use. Every MCP server adds to the context: in Claude Code its tool names and instructions (full definitions load only when a tool is used), in Codex context on every message. Both vendors say to disable the servers you don't need, and Anthropic suggests CLI tools like gh when they exist.
5. Delegate verbose work, not judgement. Send searches, test runs and log reading to a subagent with a cheap model, and keep design decisions in the main session.
6. Split by provider, not only by pane. Put independent projects or tasks on the plan that has quota left.
7. Write the task down. A task file with acceptance criteria and the test command saves the back-and-forth that burns tokens, and it lets you hand the same task to a different agent after a reset.
8. Watch the meter before you start, not when it stops you. Check /usage or /status before launching parallel work. If the window is 80% spent, start one task, not four.
9. Turn on paid overflow deliberately. Usage credits are opt-in and billed at API rates. Set a monthly cap if you enable them, so a forgotten agent can't run up a bill.
10. Check that ANTHROPIC_API_KEY is unset in shells where you mean to use your subscription.
---
A decision framework
| Workload | Best fit | Why |
| --- | --- | --- |
| One feature, steps depend on each other | Single agent, /clear between features | Shared decisions stay in one context |
| Unrelated projects | tmux sessions, mixed providers | Clean parallelism, two quotas |
| Independent tasks in one repository | Worktrees, one agent each | File isolation, simple merges |
| Search, test runs, log analysis, review | Subagents with a cheaper model | Keeps the main context small |
| Debugging with competing hypotheses, broad research | Agent Team, few teammates | Teammates challenge each other; worth the tokens |
| Same files, shared schema, tight dependencies | Single agent | Parallel agents create semantic conflicts |
| Three or more agents, or you lose track of which is blocked | Orca or a similar tool | Pays back in attention, not quota |
| Window almost spent | One small task, or switch provider | Interrupted work stalls, and resuming re-reads the whole context |
---
Final verdict
So, are parallel AI agents making developers more productive, or just reaching the limit faster?
Both, depending on the work. Parallel agents are worth it when tasks are truly independent, when each one has written acceptance criteria and tests, when the work is spread across two providers' quotas, and when your review capacity keeps up with what they produce. A single agent is the better choice when the tasks share decisions, touch the same files or depend on each other, which, according to Anthropic's own engineering team, describes more coding work than research work.
What doesn't hold up is the idea that more agents means more software. Every architecture in this post spends from a limited pool, and every one of them ends at the same place: a person reading a diff and deciding whether it's right.
The best AI coding workflow is not the one running the most agents. It's the one producing the most verified engineering value within its constraints.
Takeaway
- Your quota is shared. Every Claude Code pane, subagent and chat draws from one Pro pool; Codex local and cloud work share one Plus pool.
- Subagents save context, not tokens. Use them for verbose, read-heavy work, with a cheaper model.
- Agent Teams cost about 7x in plan mode. Use them for work that benefits from discussion, not for routine edits.
- Worktrees isolate files, not processes. Separate databases, ports and credentials need their own isolation.
- Two $20 plans are two pools. Splitting work by provider is the cleanest way to get more allowance without upgrading.
- Count verified tasks per hour, not agents running or lines generated.
How many agents can you run before your review becomes the bottleneck, and what did you change when you hit that point? Tell me in the comments.
---
I'm Diogo Soares, a Staff AI Engineer working on AI agents and legacy modernization. If this was useful, follow me here on DEV.to and on Instagram at @diogosoares.dev, where the habits from this post become a carousel you can save for your next planning session. This article also has a video walkthrough on my YouTube channel, Diogo Soares Dev, so subscribe there for the next ones. Let's also connect on LinkedIn, or check out diogosoares.dev.
Top 10 GitHub Repos This Week | Oct 18 – Oct 24 | The Harness Beats the Model
This week the biggest gains went to the harness around the agent, not the model: Cloudflare's security audit skill took #1 with 12,680 new stars, and three of the ten are instructions rather than apps.
⏱️ TIMESTAMPS
0:00 — Intro
0:46 — #10 andrej-karpathy-skills — One rules file for coding agents (223.6K⭐️)
2:37 — #9 claude-plugins-official — Anthropic's official plugin directory (44.5K⭐️)
4:36 — #8 ruflo — An agent meta-harness (79.2K⭐️)
6:38 — #7 ai-memory — Shared memory across coding agents (13.4K⭐️)
8:46 — #6 ComfyUI — Node-graph engine for AI images and video (142.8K⭐️)
10:50 — #5 hyperframes — Write HTML, render video (71.9K⭐️)
13:13 — #4 opencode — The open source coding agent (221.4K⭐️)
15:21 — #3 graphify — Your codebase as a knowledge graph (134.8K⭐️)
18:01 — #2 orca — A command center for a fleet of agents (105.4K⭐️)
20:18 — #1 security-audit-skill — Turn your agent into a security auditor (46K⭐️)
23:17 — Recap & Trends
🔗 REPOS
• #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills
• #9 claude-plugins-official → anthropics/claude-plugins-official
• #8 ruflo → ruvnet/ruflo
• #7 ai-memory → akitaonrails/ai-memory
• #6 ComfyUI → Comfy-Org/ComfyUI
• #5 hyperframes → heygen-com/hyperframes
• #4 opencode → anomalyco/opencode
• #3 graphify → Graphify-Labs/graphify
• #2 orca → stablyai/orca
• #1 security-audit-skill → cloudflare/security-audit-skill
👍 Like, 💬 Comment, 🔔 Subscribe, ⭐️ Star the repos!
#github #opensource #ai #coding #programming #trending #devtools #developer
[ar] أفضل 10 مستودعات على GitHub لهذا الأسبوع | 18 أكتوبر – 24 أكتوبر | "إطار العمل" يتفوق على النموذج
هذا الأسبوع، كانت أكبر المكاسب من نصيب البنية التحتية المحيطة بالوكيل، وليس النموذج نفسه: فقد تصدّرت مهارة التدقيق الأمني من كلاود فلير القائمة بحصولها على 12,680 نجمة جديدة، وثلاث من هذه النجوم العشر عبارة عن تعليمات وليست تطبيقات.
⏱️ الطوابع الزمنية
0:00 — مقدمة
0:46 — #10 مهارات أندريه كارباثي — ملف قواعد واحد لوكلاء البرمجة (223.6 ألف نجمة)
2:37 — #9 دليل إضافات كلود الرسمي — دليل إضافات أنثروبيك الرسمي (44.5 ألف نجمة)
4:36 — #8 روفلو — أداة شاملة لوكلاء البرمجة (79.2 ألف نجمة)
6:38 — #7 ذاكرة الذكاء الاصطناعي — ذاكرة مشتركة بين وكلاء البرمجة (13.4 ألف نجمة)
8:46 — #6 كومفي يو آي — محرك رسم بياني للعقد لصور وفيديوهات الذكاء الاصطناعي (142.8 ألف نجمة)
10:50 — #5 هايبر فريمز — كتابة HTML، عرض الفيديو (71.9 ألف نجمة)
13:13 — #4 أوبن كود — وكيل البرمجة مفتوح المصدر (221.4 ألف نجمة)
15:21 — #3 graphify — قاعدة بياناتك البرمجية كرسم بياني معرفي (134.8 ألف نجمة)
18:01 — #2 orca — مركز قيادة لأسطول من العملاء (105.4 ألف نجمة)
20:18 — #1 security-audit-skill — حوّل عميلك إلى مدقق أمني (46 ألف نجمة)
23:17 — ملخص واتجاهات
🔗 المستودعات
• #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills
• #9 claude-plugins-official → anthropics/claude-plugins-official
• #8 ruflo → ruvnet/ruflo
• #7 ai-memory → akitaonrails/ai-memory
• #6 ComfyUI → Comfy-Org/ComfyUI
• #5 hyperframes → heygen-com/hyperframes
• #4 opencode → anomalyco/opencode
• #3 graphify → Graphify-Labs/graphify
• #2 orca → staablyai/orca
• #1 security-audit-skill → cloudflare/security-audit-skill
👍 إعجاب، 💬 تعليق، 🔔 اشتراك، ⭐️ ضع نجمة على المستودعات!
#github #opensource #ai #coding #programming #trending #devtools #developer
[bn] এই সপ্তাহের শীর্ষ ১০ গিটহাব রিপো | ১৮ অক্টোবর – ২৪ অক্টোবর | মডেলকে হার মানালো হারনেস
এই সপ্তাহে সবচেয়ে বেশি অগ্রগতি হয়েছে এজেন্টের চারপাশের হারনেসের, মডেলের নয়: ক্লাউডফ্লেয়ারের সিকিউরিটি অডিট স্কিল ১২,৬৮০টি নতুন স্টার পেয়ে প্রথম স্থান অধিকার করেছে, এবং এই দশটির মধ্যে তিনটিই অ্যাপ না হয়ে নির্দেশনা।
⏱️ টাইমস্ট্যাম্প
০:০০ — ভূমিকা
০:৪৬ — #১০ andrej-karpathy-skills — কোডিং এজেন্টদের জন্য একটি রুলস ফাইল (২২৩.৬ হাজার⭐️)
২:৩৭ — #৯ claude-plugins-official — অ্যানথ্রোপিকের অফিসিয়াল প্লাগইন ডিরেক্টরি (৪৪.৫ হাজার⭐️)
৪:৩৬ — #৮ ruflo — একটি এজেন্ট মেটা-হারনেস (৭৯.২ হাজার⭐️)
৬:৩৮ — #৭ ai-memory — কোডিং এজেন্টদের মধ্যে শেয়ার্ড মেমরি (১৩.৪ হাজার⭐️)
৮:৪৬ — #৬ ComfyUI — AI ইমেজ এবং ভিডিওর জন্য নোড-গ্রাফ ইঞ্জিন (১৪২.৮ হাজার⭐️)
১০:৫০ — #৫ hyperframes — HTML লেখা, ভিডিও রেন্ডার করা (৭১.৯ হাজার⭐️)
১৩:১৩ — #৪ opencode — ওপেন সোর্স কোডিং এজেন্ট (২২১.৪ হাজার ⭐️)
১৫:২১ — #৩ গ্রাফিফাই — আপনার কোডবেসকে একটি নলেজ গ্রাফ হিসেবে ব্যবহার করুন (১৩৪.৮ হাজার ⭐️)
১৮:০১ — #২ ওরকা — একদল এজেন্টের জন্য একটি কমান্ড সেন্টার (১০৫.৪ হাজার ⭐️)
২০:১৮ — #১ সিকিউরিটি-অডিট-স্কিল — আপনার এজেন্টকে একজন সিকিউরিটি অডিটরে পরিণত করুন (৪৬ হাজার ⭐️)
২৩:১৭ — সারসংক্ষেপ ও ট্রেন্ডস
🔗 রিপো
• #১০ আন্দ্রেজ-কারপ্যাথি-স্কিলস → multica-ai/andrej-karpathy-skills
• #৯ ক্লড-প্লাগইনস-অফিশিয়াল → anthropics/claude-plugins-official
• #৮ রুফলো → ruvnet/ruflo
• #৭ ai-memory → akitaonrails/ai-memory
• #৬ ComfyUI → Comfy-Org/ComfyUI
• #৫ hyperframes → heygen-com/hyperframes
• #৪ opencode → anomalyco/opencode
• #৩ graphify → Graphify-Labs/graphify
• #২ orca → stablyai/orca
• #১ security-audit-skill → cloudflare/security-audit-skill
👍 লাইক, 💬 কমেন্ট, 🔔 সাবস্ক্রাইব, ⭐️ রিপোজিটরিগুলোতে স্টার দিন!
#github #opensource #ai #coding #programming #trending #devtools #developer
[de-DE] Die 10 besten GitHub-Repos der Woche | 18. Okt. – 24. Okt. | Das Framework schlägt das Modell
Diese Woche erzielten die Anwender die größten Zuwächse, nicht das Modell selbst: Cloudflares Sicherheitsaudit-Funktion belegte mit 12.680 neuen Sternen den ersten Platz, und drei der zehn besten Funktionen sind Anleitungen und keine Apps.
⏱️ ZEITSTEMPEL
0:00 — Intro
0:46 — #10 andrej-karpathy-skills — Eine Regeldatei für Coding-Agenten (223,6K⭐️)
2:37 — #9 claude-plugins-official — Das offizielle Plugin-Verzeichnis von Anthropic (44,5K⭐️)
4:36 — #8 ruflo — Ein Agenten-Meta-Harness (79,2K⭐️)
6:38 — #7 ai-memory — Gemeinsamer Speicher für Coding-Agenten (13,4K⭐️)
8:46 — #6 ComfyUI — Node-Graph-Engine für KI-Bilder und -Videos (142,8K⭐️)
10:50 — #5 hyperframes — HTML schreiben, Video rendern (71,9K⭐️)
13:13 — #4 Opencode – Der Open-Source-Codierungsagent (221,4K⭐️)
15:21 – #3 Graphify – Ihre Codebasis als Wissensgraph (134,8K⭐️)
18:01 – #2 Orca – Eine Kommandozentrale für eine Flotte von Agenten (105,4K⭐️)
20:18 – #1 Security-Audit-Skill – Machen Sie Ihren Agenten zum Sicherheitsauditor (46K⭐️)
23:17 – Zusammenfassung & Trends
🔗 REPOS
• #10 Andrej-Karpathy-Skills → multica-ai/andrej-karpathy-skills
• #9 Claude-Plugins-Official → anthropics/claude-plugins-official
• #8 Ruflo → ruvnet/ruflo
• #7 ai-memory → akitaonrails/ai-memory
• #6 ComfyUI → Comfy-Org/ComfyUI
• #5 hyperframes → heygen-com/hyperframes
• #4 opencode → anomalyco/opencode
• #3 graphify → Graphify-Labs/graphify
• #2 orca → stablyai/orca
• #1 security-audit-skill → cloudflare/security-audit-skill
👍 Gefällt mir, 💬 Kommentar, 🔔 Abonnieren, ⭐️ Repos mit Stern markieren!
#github #opensource #ai #coding #programming #trending #devtools #developer
[es-US] Los 10 mejores repositorios de GitHub esta semana | 18 al 24 de octubre | The Harness Beats the M...
Esta semana, las mayores ganancias se concentraron en la plataforma que rodea al agente, no en el modelo: la habilidad de auditoría de seguridad de Cloudflare alcanzó el primer puesto con 12.680 nuevas estrellas, y tres de las diez mejores son instrucciones, no aplicaciones.
Esta semana, el mayor avance se centró en la plataforma que rodea al agente, no en el modelo: la habilidad de auditoría de seguridad de Cloudflare se posicionó en el primer lugar con 12.680 nuevas estrellas, y tres de las diez mejores son instrucciones, no aplicaciones. ⏱️ MARCAS DE TIEMPO
0:00 — Introducción
0:46 — #10 andrej-karpathy-skills — Un archivo de reglas para agentes de codificación (223.6K⭐️)
2:37 — #9 claude-plugins-official — Directorio oficial de plugins de Anthropic (44.5K⭐️)
4:36 — #8 ruflo — Un meta-arnés para agentes (79.2K⭐️)
6:38 — #7 ai-memory — Memoria compartida entre agentes de codificación (13.4K⭐️)
8:46 — #6 ComfyUI — Motor de grafo de nodos para imágenes y vídeo con IA (142.8K⭐️)
10:50 — #5 hyperframes — Escribe HTML, renderiza vídeo (71.9K⭐️)
13:13 — #4 opencode — OpenCode Agente de codificación fuente (221.4K⭐️)
15:21 — #3 graphify — Tu base de código como un grafo de conocimiento (134.8K⭐️)
18:01 — #2 orca — Un centro de mando para una flota de agentes (105.4K⭐️)
20:18 — #1 security-audit-skill — Convierte a tu agente en un auditor de seguridad (46K⭐️)
23:17 — Resumen y tendencias
🔗 REPOSICIONES
• #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills
• #9 claude-plugins-official → anthropics/claude-plugins-official
• #8 ruflo → ruvnet/ruflo
• #7 ai-memory → akitaonrails/ai-memory
• #6 ComfyUI → Comfy-Org/ComfyUI
• #5 hyperframes → heygen-com/hyperframes
• #4 opencode → anomalyco/opencode
• #3 graphify → Graphify-Labs/graphify
• #2 orca → stablyai/orca
• #1 security-audit-skill → cloudflare/security-audit-skill
👍 Dale Me gusta, 💬 Comenta, 🔔 Suscríbete, ⭐️ ¡Marca los repositorios como favoritos!
#github #opensource #ai #codificación #programación #tendencias #devtools #desarrollador
[fr-FR] Top 10 des dépôts GitHub de la semaine | 18-24 oct. | Le harnais surpasse le modèle
Cette semaine, ce sont les outils autour de l'agent, et non le modèle, qui ont enregistré les plus fortes progressions : la fonctionnalité d'audit de sécurité de Cloudflare s'est hissée à la première place avec 12 680 nouvelles étoiles, et trois des dix meilleures sont des instructions plutôt que des applications.
⏱️ HORODATAGE
0:00 — Introduction
0:46 — #10 andrej-karpathy-skills — Un fichier de règles pour la programmation d'agents (223,6K⭐️)
2:37 — #9 claude-plugins-official — Répertoire officiel des plugins d'Anthropic (44,5K⭐️)
4:36 — #8 ruflo — Un méta-harnais pour agents (79,2K⭐️)
6:38 — #7 ai-memory — Mémoire partagée entre agents de programmation (13,4K⭐️)
8:46 — #6 ComfyUI — Moteur de graphes de nœuds pour les images et vidéos IA (142,8K⭐️)
10:50 — #5 hyperframes — Écrire du HTML, générer de la vidéo (71,9K⭐️)
13:13 — #4 opencode — L'agent de codage open source (221,4K⭐️)
15:21 — #3 Graphify — Votre code source sous forme de graphe de connaissances (134,8K⭐️)
18:01 — #2 Orca — Un centre de commandement pour une flotte d'agents (105,4K⭐️)
20:18 — #1 Security-audit-skill — Transformez votre agent en auditeur de sécurité (46K⭐️)
23:17 — Récapitulatif et tendances
🔗 DÉPÔTS
• #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills
• #9 claude-plugins-official → anthropics/claude-plugins-official
• #8 ruflo → ruvnet/ruflo
• #7 ai-memory → akitaonrails/ai-memory
• #6 ComfyUI → Comfy-Org/ComfyUI
• #5 hyperframes → heygen-com/hyperframes
• #4 opencode → anomalyco/opencode
• #3 graphify → Graphify-Labs/graphify
• #2 orca → stablyai/orca
• #1 security-audit-skill → cloudflare/security-audit-skill
👍 Aimez, 💬 Commentez, 🔔 Abonnez-vous, ⭐️ Mettez les dépôts en favoris !
#github #opensource #ai #coding #programming #trending #devtools #developer
[hi] इस सप्ताह के शीर्ष 10 GitHub रिपोज़ | 18 अक्टूबर - 24 अक्टूबर | हार्नेस मॉडल से बेहतर
इस सप्ताह सबसे अधिक लाभ एजेंट के आसपास के हार्नेस को मिला, न कि मॉडल को: क्लाउडफ्लेयर के सुरक्षा ऑडिट कौशल ने 12,680 नए स्टार्स के साथ पहला स्थान प्राप्त किया, और इनमें से दस में से तीन निर्देश हैं, न कि ऐप्स।
⏱️ समय-सारणी
0:00 — परिचय
0:46 — #10 andrej-karpathy-skills — कोडिंग एजेंटों के लिए एक नियम फ़ाइल (223.6K⭐️)
2:37 — #9 claude-plugins-official — Anthropic की आधिकारिक प्लगइन निर्देशिका (44.5K⭐️)
4:36 — #8 ruflo — एक एजेंट मेटा-हार्नेस (79.2K⭐️)
6:38 — #7 ai-memory — कोडिंग एजेंटों के बीच साझा मेमोरी (13.4K⭐️)
8:46 — #6 ComfyUI — AI छवियों और वीडियो के लिए नोड-ग्राफ़ इंजन (142.8K⭐️)
10:50 — #5 hyperframes — HTML लिखें, वीडियो रेंडर करें (71.9K⭐️)
13:13 — #4 opencode — ओपन सोर्स कोडिंग एजेंट (221.4K⭐️)
15:21 — #3 ग्राफीफाई — आपका कोडबेस एक नॉलेज ग्राफ के रूप में (134.8K⭐️)
18:01 — #2 ओर्का — एजेंटों के बेड़े के लिए एक कमांड सेंटर (105.4K⭐️)
20:18 — #1 सिक्योरिटी ऑडिट स्किल — अपने एजेंट को सिक्योरिटी ऑडिटर में बदलें (46K⭐️)
23:17 — सारांश और रुझान
🔗 रिपॉजिटरी
• #10 आंद्रेज कार्पेथी स्किल्स → multica-ai/andrej-karpathy-skills
• #9 क्लाउड प्लगइन्स ऑफिशियल → anthropics/claude-plugins-official
• #8 रुफ्लो → ruvnet/ruflo
• #7 ai-memory → akitaonrails/ai-memory
• #6 ComfyUI → Comfy-Org/ComfyUI
• #5 hyperframes → heygen-com/hyperframes
• #4 opencode → anomalyco/opencode
• #3 graphify → Graphify-Labs/graphify
• #2 orca → stablyai/orca
• #1 security-audit-skill → cloudflare/security-audit-skill
👍 लाइक करें, 💬 टिप्पणी करें, 🔔 सब्सक्राइब करें, ⭐️ रिपॉजिटरी को स्टार दें!
#github #opensource #ai #coding #programming #trending #devtools #developer
[id] 10 Repositori GitHub Teratas Minggu Ini | 18 Okt – 24 Okt | The Harness Beats the Model
Minggu ini, peningkatan terbesar terjadi pada sistem pendukung agen, bukan pada modelnya: keterampilan audit keamanan Cloudflare menduduki peringkat #1 dengan 12.680 bintang baru, dan tiga dari sepuluh bintang tersebut berupa instruksi, bukan aplikasi.
⏱️ CAP WAKTU
0:00 — Pendahuluan
0:46 — #10 andrej-karpathy-skills — Satu file aturan untuk agen pengkodean (223,6K⭐️)
2:37 — #9 claude-plugins-official — Direktori plugin resmi Anthropic (44,5K⭐️)
4:36 — #8 ruflo — Meta-harness agen (79,2K⭐️)
6:38 — #7 ai-memory — Memori bersama di seluruh agen pengkodean (13,4K⭐️)
8:46 — #6 ComfyUI — Mesin node-graph untuk gambar dan video AI (142,8K⭐️)
10:50 — #5 hyperframes — Tulis HTML, render video (71,9K⭐️)
13:13 — #4 opencode — Agen pengkodean sumber terbuka (221,4 ribu ⭐️)
15:21 — #3 graphify — Basis kode Anda sebagai grafik pengetahuan (134,8 ribu ⭐️)
18:01 — #2 orca — Pusat komando untuk armada agen (105,4 ribu ⭐️)
20:18 — #1 security-audit-skill — Ubah agen Anda menjadi auditor keamanan (46 ribu ⭐️)
23:17 — Rekap & Tren
🔗 REPOS
• #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills
• #9 claude-plugins-official → anthropics/claude-plugins-official
• #8 ruflo → ruvnet/ruflo
• #7 ai-memory → akitaonrails/ai-memory
• #6 ComfyUI → Comfy-Org/ComfyUI
• #5 hyperframes → heygen-com/hyperframes
• #4 opencode → anomalyco/opencode
• #3 graphify → Graphify-Labs/graphify
• #2 orca → stablyai/orca
• #1 security-audit-skill → cloudflare/security-audit-skill
👍 Suka, 💬 Komentar, 🔔 Berlangganan, ⭐️ Beri bintang pada repositori!
#github #opensource #ai #coding #programming #trending #devtools #developer
[it] I 10 migliori repository GitHub di questa settimana | 18 ott – 24 ott | L'infrastruttura batte il...
Questa settimana i maggiori progressi sono andati all'infrastruttura che circonda l'agente, non al modello: la skill di audit di sicurezza di Cloudflare si è aggiudicata il primo posto con 12.680 nuove stelle, e tre delle prime dieci sono istruzioni anziché applicazioni.
⏱️ INDICE DEI CONTENUTI
0:00 — Introduzione
0:46 — #10 andrej-karpathy-skills — Un file di regole per agenti di codifica (223.600⭐️)
2:37 — #9 claude-plugins-official — La directory ufficiale dei plugin di Anthropic (44.500⭐️)
4:36 — #8 ruflo — Un meta-sistema di controllo per agenti (79.200⭐️)
6:38 — #7 ai-memory — Memoria condivisa tra agenti di codifica (13.400⭐️)
8:46 — #6 ComfyUI — Motore a grafo di nodi per immagini e video AI (142.800⭐️)
10:50 — #5 hyperframes — Scrivi HTML, renderizza video (71.900⭐️)
13:13 — #4 opencode — Il progetto open source agente di codifica (221.400⭐️)
15:21 — #3 graphify — Il tuo codice sorgente come grafo della conoscenza (134.800⭐️)
18:01 — #2 orca — Un centro di comando per una flotta di agenti (105.400⭐️)
20:18 — #1 security-audit-skill — Trasforma il tuo agente in un revisore della sicurezza (46.000⭐️)
23:17 — Riepilogo e tendenze
🔗 REPOS
• #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills
• #9 claude-plugins-official → anthropics/claude-plugins-official
• #8 ruflo → ruvnet/ruflo
• #7 ai-memory → akitaonrails/ai-memory
• #6 ComfyUI → Comfy-Org/ComfyUI
• #5 hyperframes → heygen-com/hyperframes
• #4 opencode → anomalyco/opencode
• #3 graphify → Graphify-Labs/graphify
• #2 orca → stablyai/orca
• #1 security-audit-skill → cloudflare/security-audit-skill
👍 Metti Mi piace, 💬 Commenta, 🔔 Iscriviti, ⭐️ Aggiungi i repository ai preferiti!
#github #opensource #ai #coding #programming #trending #devtools #developer
[iw] 10 מאגרי ה-GitHub המובילים השבוע | 18 באוקטובר – 24 באוקטובר | המעטפת מנצחת את המודל
השבוע, הרווחים הגדולים ביותר הלכו לרתמה סביב הסוכן, לא למודל: מיומנות ביקורת האבטחה של Cloudflare תפסה את המקום הראשון עם 12,680 כוכבים חדשים, ושלושה מתוך עשרתם הם הוראות ולא אפליקציות.
⏱️ חותמות זמן
0:00 — מבוא
0:46 — #10 andrej-karpathy-skills — קובץ כללים אחד עבור סוכני קידוד (223.6K⭐️)
2:37 — #9 claude-plugins-official — ספריית התוספים הרשמית של Anthropic (44.5K⭐️)
4:36 — #8 ruflo — רתמת מטא של סוכן (79.2K⭐️)
6:38 — #7 ai-memory — זיכרון משותף בין סוכני קידוד (13.4K⭐️)
8:46 — #6 ComfyUI — מנוע Node-graph עבור תמונות ווידאו של בינה מלאכותית (142.8K⭐️)
10:50 — #5 hyperframes — כתיבת HTML, עיבוד וידאו (71.9K⭐️)
13:13 — #4 opencode — סוכן קידוד בקוד פתוח (221.4K⭐️)
15:21 — #3 graphify — בסיס הקוד שלך כגרף ידע (134.8K⭐️)
18:01 — #2 orca — מרכז פיקוד עבור צי סוכנים (105.4K⭐️)
20:18 — #1 security-audit-skill — הפוך את הסוכן שלך למבקר אבטחה (46K⭐️)
23:17 — סיכום ומגמות
🔗 REPOS
• #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills
• #9 claude-plugins-official → anthropics/claude-plugins-official
• #8 ruflo → ruvnet/ruflo
• #7 ai-memory → akitaonrails/ai-memory
• #6 ComfyUI → Comfy-Org/ComfyUI
• #5 היפר-פריימים → heygen-com/hyperframes
• #4 קוד פתוח → anomalyco/opencode
• #3 גרפיפי → Graphify-Labs/graphify
• #2 אורקה → stablyai/orca
• #1 סקיל ביקורת-על-ביטחון → cloudflare/security-audit-skill
👍 לייק, 💬 הגיבו, 🔔 הירשמו, ⭐️ סמנו בכוכב את המאגרים!
#github #קודפתוח #בינה מלאכותית #קידוד #תכנות #טרנדי #כליפיתוח #מפתח
[ja] 今週のGitHub注目リポジトリTOP10 | 10月18日～10月24日 | モデルを凌駕するハーネス
今週、最も大きな伸びを見せたのはエージェントのモデルではなく、その周辺技術でした。Cloudflareのセキュリティ監査スキルが12,680個の新たなスターを獲得し、1位に輝きました。上位10件のうち3件はアプリではなく、手順書でした。
⏱️ タイムスタンプ
0:00 — はじめに
0:46 — #10 andrej-karpathy-skills — コーディングエージェントのためのルールファイル (223.6K⭐️)
2:37 — #9 claude-plugins-official — Anthropic の公式プラグインディレクトリ (44.5K⭐️)
4:36 — #8 ruflo — エージェントメタハーネス (79.2K⭐️)
6:38 — #7 ai-memory — コーディングエージェント間で共有されるメモリ (13.4K⭐️)
8:46 — #6 ComfyUI — AI 画像と動画のためのノードグラフエンジン (142.8K⭐️)
10:50 — #5 hyperframes — HTML の書き込み、動画のレンダリング (71.9K⭐️)
13:13 — #4 opencode — オープンソースのコーディングエージェント (221.4K⭐️)
15:21 — #3 graphify — コードベースをナレッジグラフとして活用 (134.8K⭐️)
18:01 — #2 orca — エージェント群のためのコマンドセンター (105.4K⭐️)
20:18 — #1 security-audit-skill — エージェントをセキュリティ監査ツールに変える (46K⭐️)
23:17 — まとめとトレンド
🔗 リポジトリ
• #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills
• #9 claude-plugins-official → anthropics/claude-plugins-official
• #8 ruflo → ruvnet/ruflo
• #7 ai-memory → akitaonrails/ai-memory
• #6 ComfyUI → Comfy-Org/ComfyUI
• #5 ハイパーフレーム → heygen-com/hyperframes
• #4 オープンコード → anomalyco/opencode
• #3 グラフィファイ → Graphify-Labs/graphify
• #2 オルカ → stablyai/orca
• #1 セキュリティ監査スキル → cloudflare/security-audit-skill
👍 いいね、💬 コメント、🔔 チャンネル登録、⭐️ スターをリポジトリに追加！
#github #opensource #ai #coding #programming #trending #devtools #developer
[ko] 이번 주 GitHub Top 10 저장소 | 10월 18일 – 10월 24일 | 모델을 능가하는 활용 도구
이번 주 가장 큰 성과는 모델이 아닌 에이전트 관련 도구에서 나타났습니다. 클라우드플레어의 보안 감사 스킬이 12,680개의 새로운 별점을 얻으며 1위를 차지했고, 상위 10개 중 3개는 앱이 아닌 사용법 안내였습니다.
⏱️ 타임스탬프
0:00 — 소개
0:46 — #10 andrej-karpathy-skills — 코딩 에이전트를 위한 하나의 규칙 파일 (223.6K⭐️)
2:37 — #9 claude-plugins-official — Anthropic의 공식 플러그인 디렉토리 (44.5K⭐️)
4:36 — #8 ruflo — 에이전트 메타 하네스 (79.2K⭐️)
6:38 — #7 ai-memory — 코딩 에이전트 간 공유 메모리 (13.4K⭐️)
8:46 — #6 ComfyUI — AI 이미지 및 비디오용 노드 그래프 엔진 (142.8K⭐️)
10:50 — #5 hyperframes — HTML 작성 및 비디오 렌더링 (71.9K⭐️)
13:13 — #4 opencode — 오픈 소스 코딩 에이전트 (221.4K⭐️)
15:21 — #3 Graphify — 코드베이스를 지식 그래프로 (134.8K⭐️)
18:01 — #2 Orca — 에이전트 함대를 위한 명령 센터 (105.4K⭐️)
20:18 — #1 Security-Audit-Skill — 에이전트를 보안 감사자로 전환 (46K⭐️)
23:17 — 요약 및 트렌드
🔗 저장소
• #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills
• #9 claude-plugins-official → anthropics/claude-plugins-official
• #8 ruflo → ruvnet/ruflo
• #7 ai-memory → akitaonrails/ai-memory
• #6 ComfyUI → Comfy-Org/ComfyUI
• #5 hyperframes → heygen-com/hyperframes
• #4 opencode → anomalyco/opencode
• #3 graphify → Graphify-Labs/graphify
• #2 orca → stablyai/orca
• #1 security-audit-skill → cloudflare/security-audit-skill
👍 좋아요, 💬 댓글, 🔔 구독, ⭐️ 저장소에 별표 표시!
#github #opensource #ai #coding #programming #trending #devtools #developer
[ml] ഈ ആഴ്ചയിലെ മികച്ച 10 GitHub റിപ്പോസിറ്ററികൾ | ഒക്ടോബർ 18 – ഒക്ടോബർ 24 | മോഡലിനേക്കാൾ കേമൻ ഹാർനെസ്
ഈ ആഴ്ച ഏറ്റവും വലിയ നേട്ടം മോഡലിനെയല്ല, ഏജന്റിനെ ചുറ്റിപ്പറ്റിയുള്ളതാണ്: 12,680 പുതിയ നക്ഷത്രങ്ങളുമായി ക്ലൗഡ്ഫ്ലെയറിന്റെ സുരക്ഷാ ഓഡിറ്റ് വൈദഗ്ദ്ധ്യം ഒന്നാം സ്ഥാനത്തെത്തി, പത്തിൽ മൂന്നെണ്ണം ആപ്പുകളേക്കാൾ നിർദ്ദേശങ്ങളാണ്.
⏱️ TIMESTAMPS
0:00 — ആമുഖം
0:46 — #10 andrej-karpathy-skills — കോഡിംഗ് ഏജന്റുകൾക്കുള്ള ഒരു റൂൾ ഫയൽ (223.6K⭐️)
2:37 — #9 claude-plugins-official — ആന്ത്രോപിക്കിന്റെ ഔദ്യോഗിക പ്ലഗിൻ ഡയറക്ടറി (44.5K⭐️)
4:36 — #8 ruflo — ഒരു ഏജന്റ് മെറ്റാ-ഹാർനെസ് (79.2K⭐️)
6:38 — #7 ai-memory — കോഡിംഗ് ഏജന്റുകളിലുടനീളം പങ്കിട്ട മെമ്മറി (13.4K⭐️)
8:46 — #6 ComfyUI — AI ഇമേജുകൾക്കും വീഡിയോയ്ക്കുമുള്ള നോഡ്-ഗ്രാഫ് എഞ്ചിൻ (142.8K⭐️)
10:50 — #5 ഹൈപ്പർഫ്രെയിമുകൾ — HTML എഴുതുക, വീഡിയോ റെൻഡർ ചെയ്യുക (71.9K⭐️)
13:13 — #4 ഓപ്പൺകോഡ് — ഓപ്പൺ സോഴ്സ് കോഡിംഗ് ഏജന്റ് (221.4K⭐️)
15:21 — #3 ഗ്രാഫിഫൈ — നിങ്ങളുടെ കോഡ്ബേസ് ഒരു നോളജ് ഗ്രാഫ് ആയി (134.8K⭐️)
18:01 — #2 ഓർക്ക — ഏജന്റുമാരുടെ ഒരു കൂട്ടത്തിനായുള്ള ഒരു കമാൻഡ് സെന്റർ (105.4K⭐️)
20:18 — #1 സുരക്ഷാ-ഓഡിറ്റ്-സ്കിൽ — നിങ്ങളുടെ ഏജന്റിനെ ഒരു സുരക്ഷാ ഓഡിറ്ററാക്കി മാറ്റുക (46K⭐️)
23:17 — റീക്യാപ്പ് & ട്രെൻഡുകൾ
🔗 REPOS
• #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills
• #9 claude-plugins-official → anthropics/claude-plugins-official
• #8 ruflo → ruvnet/ruflo
• #7 ai-memory → akitaonrails/ai-memory
• #6 ComfyUI → Comfy-Org/ComfyUI
• #5 ഹൈപ്പർഫ്രെയിമുകൾ → heygen-com/hyperframes
• #4 ഓപ്പൺകോഡ് → anomalyco/opencode
• #3 ഗ്രാഫിഫൈ → Graphify-Labs/graphify
• #2 ഓർക്ക → stablyai/orca
• #1 സെക്യൂരിറ്റി-ഓഡിറ്റ്-സ്കിൽ → cloudflare/security-audit-%E0%B4%B8%E0%B5%8D%E0%B4%95%E0%B4%BF%E0%B5%BD
👍 ലൈക്ക് ചെയ്യുക, 💬 കമന്റ് ചെയ്യുക, 🔔 സബ്സ്ക്രൈബ് ചെയ്യുക, ⭐️ റിപ്പോകളിൽ സ്റ്റാർ ചെയ്യുക!
#github #opensource #ai #coding #programming #trending #devtools #developer
[nl-NL] Top 10 GitHub-repo's van deze week | 18 okt – 24 okt | Het harnas verslaat het model
Deze week ging de grootste winst naar de hardware rondom de agent, niet naar het model zelf: Cloudflare's beveiligingsauditvaardigheid behaalde de eerste plaats met 12.680 nieuwe sterren, waarvan drie van de tien instructies zijn in plaats van apps.
⏱️ TIJDSTEMPELS
0:00 — Intro
0:46 — #10 andrej-karpathy-skills — Eén regelsbestand voor codeeragenten (223,6K⭐️)
2:37 — #9 claude-plugins-official — De officiële plugin-directory van Anthropic (44,5K⭐️)
4:36 — #8 ruflo — Een agent-meta-harness (79,2K⭐️)
6:38 — #7 ai-memory — Gedeeld geheugen voor codeeragenten (13,4K⭐️)
8:46 — #6 ComfyUI — Node-graph engine voor AI-afbeeldingen en -video (142,8K⭐️)
10:50 — #5 hyperframes — Schrijf HTML, render video (71,9K⭐️)
13:13 — #4 opencode — De open broncodeagent (221,4K⭐️)
15:21 — #3 graphify — Je codebase als kennisgrafiek (134,8K⭐️)
18:01 — #2 orca — Een commandocentrum voor een vloot agenten (105,4K⭐️)
20:18 — #1 security-audit-skill — Verander je agent in een beveiligingsauditor (46K⭐️)
23:17 — Samenvatting & Trends
🔗 REPOS
• #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills
• #9 claude-plugins-official → anthropics/claude-plugins-official
• #8 ruflo → ruvnet/ruflo
• #7 ai-memory → akitaonrails/ai-memory
• #6 ComfyUI → Comfy-Org/ComfyUI
• #5 hyperframes → heygen-com/hyperframes
• #4 opencode → anomalyco/opencode
• #3 graphify → Graphify-Labs/graphify
• #2 orca → stablyai/orca
• #1 security-audit-skill → cloudflare/security-audit-skill
👍 Vind ik leuk, 💬 Reageer, 🔔 Abonneer, ⭐️ Geef de repositories een ster!
#github #opensource #ai #coding #programming #trending #devtools #developer
[pa] ਇਸ ਹਫ਼ਤੇ ਦੀਆਂ ਚੋਟੀ ਦੀਆਂ 10 GitHub ਰਿਪੋਜ਼ | 18 ਅਕਤੂਬਰ – 24 ਅਕਤੂਬਰ | ਮਾਡਲ ਨਾਲੋਂ ਹਾਰਨੇਸ ਬਿਹਤਰ
ਇਸ ਹਫ਼ਤੇ ਸਭ ਤੋਂ ਵੱਧ ਲਾਭ ਏਜੰਟ ਦੇ ਆਲੇ-ਦੁਆਲੇ ਦੇ ਹਾਰਨੈੱਸ ਨੂੰ ਹੋਇਆ, ਮਾਡਲ ਨੂੰ ਨਹੀਂ: ਕਲਾਉਡਫਲੇਅਰ ਦੇ ਸੁਰੱਖਿਆ ਆਡਿਟ ਹੁਨਰ ਨੇ 12,680 ਨਵੇਂ ਸਿਤਾਰਿਆਂ ਨਾਲ #1 ਸਥਾਨ ਪ੍ਰਾਪਤ ਕੀਤਾ, ਅਤੇ ਦਸ ਵਿੱਚੋਂ ਤਿੰਨ ਐਪਸ ਦੀ ਬਜਾਏ ਨਿਰਦੇਸ਼ ਹਨ।
⏱️ ਟਾਈਮਸਟੈਂਪਸ
0:00 — ਜਾਣ-ਪਛਾਣ
0:46 — #10 andrej-karpathy-skills — ਕੋਡਿੰਗ ਏਜੰਟਾਂ ਲਈ ਇੱਕ ਨਿਯਮ ਫਾਈਲ (223.6K⭐️)
2:37 — #9 claude-plugins-official — Anthropic ਦੀ ਅਧਿਕਾਰਤ ਪਲੱਗਇਨ ਡਾਇਰੈਕਟਰੀ (44.5K⭐️)
4:36 — #8 ruflo — ਇੱਕ ਏਜੰਟ ਮੈਟਾ-ਹਾਰਨੈੱਸ (79.2K⭐️)
6:38 — #7 ai-ਮੈਮੋਰੀ — ਕੋਡਿੰਗ ਏਜੰਟਾਂ ਵਿੱਚ ਸਾਂਝੀ ਮੈਮੋਰੀ (13.4K⭐️)
8:46 — #6 ComfyUI — AI ਚਿੱਤਰਾਂ ਅਤੇ ਵੀਡੀਓ ਲਈ ਨੋਡ-ਗ੍ਰਾਫ ਇੰਜਣ (142.8K⭐️)
10:50 — #5 ਹਾਈਪਰਫ੍ਰੇਮ — HTML ਲਿਖੋ, ਵੀਡੀਓ ਰੈਂਡਰ ਕਰੋ (71.9K⭐️)
13:13 — #4 ਓਪਨਕੋਡ — ਓਪਨ ਸੋਰਸ ਕੋਡਿੰਗ ਏਜੰਟ (221.4K⭐️)
15:21 — #3 ਗ੍ਰਾਫੀਫਾਈ — ਤੁਹਾਡਾ ਕੋਡਬੇਸ ਇੱਕ ਗਿਆਨ ਗ੍ਰਾਫ਼ ਵਜੋਂ (134.8K⭐️)
18:01 — #2 ਓਰਕਾ — ਏਜੰਟਾਂ ਦੇ ਫਲੀਟ ਲਈ ਇੱਕ ਕਮਾਂਡ ਸੈਂਟਰ (105.4K⭐️)
20:18 — #1 ਸੁਰੱਖਿਆ-ਆਡਿਟ-ਹੁਨਰ — ਆਪਣੇ ਏਜੰਟ ਨੂੰ ਸੁਰੱਖਿਆ ਆਡੀਟਰ ਵਿੱਚ ਬਦਲੋ (46K⭐️)
23:17 — ਸੰਖੇਪ ਅਤੇ ਰੁਝਾਨ
🔗 REPOS
• #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills
• #9 claude-plugins-official → anthropics/claude-plugins-official
• #8 ruflo → ruvnet/ruflo
• #7 ai-memory → akitaonrails/ai-memory
• #6 ComfyUI → Comfy-Org/ComfyUI
• #5 ਹਾਈਪਰਫ੍ਰੇਮ → heygen-com/hyperframes
• #4 ਓਪਨਕੋਡ → anomalyco/opencode
• #3 graphify → Graphify-Labs/graphify
• #2 orca → stablyai/orca
• #1 security-audit-skill → cloudflare/security-audit-skill
👍 ਪਸੰਦ ਕਰੋ, 💬 ਟਿੱਪਣੀ ਕਰੋ, 🔔 ਗਾਹਕ ਬਣੋ, ⭐️ ਰਿਪੋਜ਼ ਨੂੰ ਸਟਾਰ ਕਰੋ!
#github #opensource #ai #ਕੋਡਿੰਗ #ਪ੍ਰੋਗਰਾਮਿੰਗ #ਟ੍ਰੇਂਡਿੰਗ #devtools #developer
[pl] 10 najlepszych repozytoriów GitHub w tym tygodniu | 18–24 października | Oprzyrządowanie lepsze n...
W tym tygodniu największe zyski odnotowały uprząż wokół agenta, a nie sam model: umiejętność audytu bezpieczeństwa Cloudflare zajęła pierwsze miejsce z 12 680 nowymi gwiazdkami, a trzy z dziesięciu to instrukcje, a nie aplikacje.
⏱️ ZNACZNIKI CZASU
0:00 — Wprowadzenie
0:46 — #10 andrej-karpathy-skills — Jeden plik reguł dla agentów kodujących (223,6 tys.⭐️)
2:37 — #9 claude-plugins-official — Oficjalny katalog wtyczek Anthropic (44,5 tys.⭐️)
4:36 — #8 ruflo — Meta-uprząż dla agentów kodujących (79,2 tys.⭐️)
6:38 — #7 ai-memory — Pamięć współdzielona przez agentów kodujących (13,4 tys.⭐️)
8:46 — #6 ComfyUI — Silnik Node-graph dla obrazów i wideo AI (142,8 tys.⭐️)
10:50 — #5 hyperframes — Pisanie HTML, renderowanie wideo (71,9 tys.⭐️)
13:13 — #4 opencode — Agent kodujący open source (221,4 tys.⭐️)
15:21 — #3 graphify — Twoja baza kodu jako graf wiedzy (134,8 tys.⭐️)
18:01 — #2 orca — Centrum dowodzenia dla floty agentów (105,4 tys.⭐️)
20:18 — #1 security-audit-skill — Zmień swojego agenta w audytora bezpieczeństwa (46 tys.⭐️)
23:17 — Podsumowanie i trendy
🔗 REPOZYTORIA
• #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills
• #9 claude-plugins-official → anthropics/claude-plugins-official
• #8 ruflo → ruvnet/ruflo
• #7 ai-memory → akitaonrails/ai-memory
• #6 ComfyUI → Comfy-Org/ComfyUI
• #5 hyperframes → heygen-com/hyperframes
• #4 opencode → anomalyco/opencode
• #3 graphify → Graphify-Labs/graphify
• #2 orca → stablyai/orca
• #1 security-audit-skill → cloudflare/security-audit-skill
👍 Polub, 💬 Skomentuj, 🔔 Subskrybuj, ⭐️ Oznacz repozytoria gwiazdką!
#github #opensource #ai #kodowanie #programowanie #trendy #devtools #deweloper
[pt-BR] Top 10 Repos do GitHub Esta Semana | 18 de out – 24 de out | A Estrutura Supera o Modelo
Nesta semana, os maiores ganhos foram para a estrutura em torno do agente, não para o modelo: a skill de auditoria de segurança da Cloudflare conquistou o primeiro lugar com 12.680 novas estrelas, e três dessas dez estrelas são para instruções, não para aplicativos.
⏱️ MARCAÇÕES DE TEMPO
0:00 — Introdução
0:46 — #10 andrej-karpathy-skills — Um arquivo de regras para agentes de codificação (223,6 mil ⭐️)
2:37 — #9 claude-plugins-official — Diretório oficial de plugins do Anthropic (44,5 mil ⭐️)
4:36 — #8 ruflo — Um meta-arnês para agentes (79,2 mil ⭐️)
6:38 — #7 ai-memory — Memória compartilhada entre agentes de codificação (13,4 mil ⭐️)
8:46 — #6 ComfyUI — Mecanismo de grafo de nós para imagens e vídeos com IA (142,8 mil ⭐️)
10:50 — #5 hyperframes — Escreva HTML, renderize vídeo (71,9 mil ⭐️)
13:13 — #4 opencode — O código aberto Agente de codificação (221,4 mil estrelas)
15:21 — #3 graphify — Sua base de código como um grafo de conhecimento (134,8 mil estrelas)
18:01 — #2 orca — Um centro de comando para uma frota de agentes (105,4 mil estrelas)
20:18 — #1 security-audit-skill — Transforme seu agente em um auditor de segurança (46 mil estrelas)
23:17 — Resumo e Tendências
🔗 REPOS
• #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills
• #9 claude-plugins-official → anthropics/claude-plugins-official
• #8 ruflo → ruvnet/ruflo
• #7 ai-memory → akitaonrails/ai-memory
• #6 ComfyUI → Comfy-Org/ComfyUI
• #5 hyperframes → heygen-com/hyperframes
• #4 opencode → anomalyco/opencode
• #3 graphify → Graphify-Labs/graphify
• #2 orca → stablyai/orca
• #1 security-audit-skill → cloudflare/security-audit-skill
👍 Curtir, 💬 Comentar, 🔔 Inscrever-se, ⭐️ Favoritar os repositórios!
#github #opensource #ai #codificação #programação #tendências #devtools #developer
[ru] Топ-10 репозиториев GitHub за неделю | 18 окт – 24 окт | Оболочка важнее модели
На этой неделе наибольший прирост достался инструменту, используемому в агенте, а не модели: навык аудита безопасности Cloudflare занял первое место с 12 680 новыми звездами, и три из десяти из них — это инструкции, а не приложения.
⏱️ ВРЕМЕННЫЕ МЕТКИ
0:00 — Вступление
0:46 — #10 andrej-karpathy-skills — Один файл правил для агентов кодирования (223,6 тыс.⭐️)
2:37 — #9 claude-plugins-official — Официальный каталог плагинов Anthropic (44,5 тыс.⭐️)
4:36 — #8 ruflo — Мета-инструмент для агентов (79,2 тыс.⭐️)
6:38 — #7 ai-memory — Общая память для агентов кодирования (13,4 тыс.⭐️)
8:46 — #6 ComfyUI — Графовый движок для изображений и видео ИИ (142,8 тыс.⭐️)
10:50 — #5 hyperframes — Написание HTML, рендеринг видео (71,9 тыс.⭐️)
13:13 — #4 opencode — Агент для разработки кода с открытым исходным кодом (221,4 тыс. ⭐️)
15:21 — #3 graphify — Ваша кодовая база как граф знаний (134,8 тыс. ⭐️)
18:01 — #2 orca — Командный центр для флота агентов (105,4 тыс. ⭐️)
20:18 — #1 security-audit-skill — Превратите своего агента в аудитора безопасности (46 тыс. ⭐️)
23:17 — Краткий обзор и тренды
🔗 РЕПОЗИЦИИ
• #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills
• #9 claude-plugins-official → anthropics/claude-plugins-official
• #8 ruflo → ruvnet/ruflo
• #7 ai-memory → akitaonrails/ai-memory
• #6 ComfyUI → Comfy-Org/ComfyUI
• #5 hyperframes → heygen-com/hyperframes
• #4 opencode → anomalyco/opencode
• #3 graphify → Graphify-Labs/graphify
• #2 orca → stablyai/orca
• #1 security-audit-skill → cloudflare/security-audit-skill
👍 Лайк, 💬 Комментарий, 🔔 Подписка, ⭐️ Отметьте репозитории звездочкой!
#github #opensource #ai #coding #programming #trending #devtools #developer
[ta] இந்த வாரத்தின் டாப் 10 GitHub களஞ்சியங்கள் | அக் 18 – அக் 24 | மாடலை விட ஹார்னஸ் சிறந்தது
இந்த வாரம், மாடலை விட ஏஜென்ட்டைச் சுற்றியுள்ள கட்டமைப்புக்கே மிகப்பெரிய ஆதாயங்கள் கிடைத்தன: கிளவுட்ஃபிளேரின் பாதுகாப்புத் தணிக்கைத் திறன் 12,680 புதிய நட்சத்திரங்களுடன் முதலிடத்தைப் பிடித்தது, மேலும் பத்தில் மூன்று செயலிகள் அல்ல, மாறாக அறிவுறுத்தல்களாகும்.
⏱️ நேரக்குறிப்புகள்
0:00 — அறிமுகம்
0:46 — #10 andrej-karpathy-skills — கோடிங் ஏஜென்ட்களுக்கான ஒரே விதிக் கோப்பு (223.6K⭐️)
2:37 — #9 claude-plugins-official — ஆந்த்ரோபிக்கின் அதிகாரப்பூர்வ பிளகின் கோப்பகம் (44.5K⭐️)
4:36 — #8 ruflo — ஒரு ஏஜென்ட் மெட்டா-ஹார்னஸ் (79.2K⭐️)
6:38 — #7 ai-memory — கோடிங் ஏஜென்ட்கள் முழுவதும் பகிரப்பட்ட நினைவகம் (13.4K⭐️)
8:46 — #6 ComfyUI — AI படங்கள் மற்றும் வீடியோவிற்கான நோட்-கிராஃப் எஞ்சின் (142.8K⭐️)
10:50 — #5 hyperframes — HTML எழுது, வீடியோவை ரெண்டர் செய் (71.9K⭐️)
13:13 — #4 opencode — திறந்த மூல குறியீட்டு முகவர் (221.4K⭐️)
15:21 — #3 கிராஃபிஃபை — உங்கள் குறியீட்டுத் தொகுப்பை ஒரு அறிவு வரைபடமாக மாற்றுதல் (134.8K⭐️)
18:01 — #2 ஓர்கா — முகவர்களின் குழுவிற்கான ஒரு கட்டளை மையம் (105.4K⭐️)
20:18 — #1 செக்யூரிட்டி-ஆடிட்-ஸ்கில் — உங்கள் முகவரை ஒரு பாதுகாப்பு தணிக்கையாளராக மாற்றுங்கள் (46K⭐️)
23:17 — மீள்பார்வை & போக்குகள்
🔗 ரெப்போக்கள்
• #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills
• #9 claude-plugins-official → anthropics/claude-plugins-official
• #8 ரூஃப்லோ → ruvnet/ruflo
• #7 ai-memory → akitaonrails/ai-memory
• #6 ComfyUI → Comfy-Org/ComfyUI
• #5 hyperframes → heygen-com/hyperframes
• #4 opencode → anomalyco/opencode
• #3 graphify → Graphify-Labs/graphify
• #2 orca → stablyai/orca
• #1 security-audit-skill → cloudflare/security-audit-skill
👍 லைக், 💬 கமெண்ட், 🔔 சப்ஸ்கிரைப், ⭐️ ரெப்போக்களுக்கு ஸ்டார் கொடுங்கள்!
#github #opensource #ai #coding #programming #trending #devtools #developer
[te] ఈ వారం టాప్ 10 GitHub రిపోలు | అక్టోబర్ 18 – అక్టోబర్ 24 | మోడల్ కంటే హార్నెస్దే పైచేయి
ఈ వారం అత్యధిక ప్రయోజనాలు మోడల్కు కాకుండా, ఏజెంట్ చుట్టూ ఉన్న హార్నెస్కు దక్కాయి: క్లౌడ్ఫ్లేర్ సెక్యూరిటీ ఆడిట్ స్కిల్ 12,680 కొత్త స్టార్లతో మొదటి స్థానాన్ని దక్కించుకుంది, మరియు ఆ పదింటిలో మూడు యాప్లకు బదులుగా సూచనలే ఉన్నాయి.
⏱️ టైమ్స్టాంప్లు
0:00 — పరిచయం
0:46 — #10 andrej-karpathy-skills — కోడింగ్ ఏజెంట్ల కోసం ఒక రూల్స్ ఫైల్ (223.6K⭐️)
2:37 — #9 claude-plugins-official — ఆంత్రోపిక్ యొక్క అధికారిక ప్లగిన్ డైరెక్టరీ (44.5K⭐️)
4:36 — #8 ruflo — ఒక ఏజెంట్ మెటా-హార్నెస్ (79.2K⭐️)
6:38 — #7 ai-memory — కోడింగ్ ఏజెంట్ల అంతటా షేర్డ్ మెమరీ (13.4K⭐️)
8:46 — #6 ComfyUI — AI చిత్రాలు మరియు వీడియో కోసం నోడ్-గ్రాఫ్ ఇంజిన్ (142.8K⭐️)
10:50 — #5 hyperframes — HTML రాయండి, వీడియోను రెండర్ చేయండి (71.9K⭐️)
13:13 — #4 ఓపెన్కోడ్ — ఓపెన్ సోర్స్ కోడింగ్ ఏజెంట్ (221.4K⭐️)
15:21 — #3 గ్రాఫిఫై — మీ కోడ్బేస్ను ఒక నాలెడ్జ్ గ్రాఫ్గా మార్చడం (134.8K⭐️)
18:01 — #2 ఓర్కా — ఏజెంట్ల సముదాయానికి ఒక కమాండ్ సెంటర్ (105.4K⭐️)
20:18 — #1 సెక్యూరిటీ-ఆడిట్-స్కిల్ — మీ ఏజెంట్ను ఒక సెక్యూరిటీ ఆడిటర్గా మార్చడం (46K⭐️)
23:17 — రీక్యాప్ & ట్రెండ్స్
🔗 REPOS
• #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills
• #9 claude-plugins-official → anthropics/claude-plugins-official
• #8 ruflo → ruvnet/ruflo
• #7 ai-memory → akitaonrails/ai-memory
• #6 ComfyUI → Comfy-Org/ComfyUI
• #5 hyperframes → heygen-com/hyperframes
• #4 opencode → anomalyco/opencode
• #3 graphify → Graphify-Labs/graphify
• #2 orca → stablyai/orca
• #1 security-audit-skill → cloudflare/security-audit-skill
👍 లైక్ చేయండి, 💬 కామెంట్ చేయండి, 🔔 సబ్స్క్రైబ్ చేయండి, ⭐️ రిపోలకు స్టార్ ఇవ్వండి!
#github #opensource #ai #coding #programming #trending #devtools #developer
[uk] Топ-10 репозиторіїв GitHub цього тижня | 18 жовтня – 24 жовтня | Обв'язка перемагає модель
Цього тижня найбільших успіхів досягла система, що працює навколо агента, а не модель: навичка аудиту безпеки Cloudflare посіла перше місце з 12 680 новими зірками, і три з десяти – це інструкції, а не програми.
⏱️ ЧАСОВІ ПОМІТКИ
0:00 — Вступ
0:46 — #10 andrej-karpathy-skills — Один файл правил для агентів кодування (223.6 тис.⭐️)
2:37 — #9 claude-plugins-official — Офіційний каталог плагінів Anthropic (44.5 тис.⭐️)
4:36 — #8 ruflo — Мета-обладнання агента (79.2 тис.⭐️)
6:38 — #7 ai-memory — Спільна пам'ять між агентами кодування (13.4 тис.⭐️)
8:46 — #6 ComfyUI — Двигун графів вузлів для зображень та відео на основі штучного інтелекту (142.8 тис.⭐️)
10:50 — #5 гіперфрейми — Написання HTML, рендеринг відео (71.9 тис.⭐️)
13:13 — #4 opencode — Агент кодування з відкритим вихідним кодом (221.4 тис.⭐️)
15:21 — #3 graphify — Ваша кодова база як граф знань (134.8 тис.⭐️)
18:01 — #2 orca — Командний центр для флоту агентів (105.4 тис.⭐️)
20:18 — #1 security-audit-skill — Перетворіть свого агента на аудитора безпеки (46 тис.⭐️)
23:17 — Підсумки та тенденції
🔗 РЕПОРТАЖІЇ
• #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills
• #9 claude-plugins-official → anthropics/claude-plugins-official
• #8 ruflo → ruvnet/ruflo
• #7 ai-memory → akitaonrails/ai-memory
• #6 ComfyUI → Comfy-Org/ComfyUI
• #5 гіперфрейми → heygen-com/hyperframes
• #4 відкритий код → anomalyco/opencode
• #3 графіка → Graphify-Labs/graphify
• #2 орка → stablyai/orca
• #1 навичка аудиту безпеки → cloudflare/security-audit-skill
👍 Вподобайкайте, 💬 Коментуйте, 🔔 Підпишіться, ⭐️ Поставте зірочку на репозиторії!
#github #відкритийвихіднийкод #штучнийінтелект #кодування #програмування #тренди #інструментирозробки #розробник
168 likes · 4 comments · 18,724 views
Mentions
Run Claude Code and Codex in parallel git worktrees and track usage with Orca Running one Claude Code or Codex session is easy. Running five at once on the same repo is where it falls apart: agents overwrite each other's files, you lose track of which terminal finished, and your usage limit vanishes without warning. stablyai/orca is a desktop app that treats each agent as a first-class worktree. Per its README, you run Codex, Claude Code, OpenCode or Pi side by side, each in its own git worktree, tracked in one place. This post covers the parts that help most with Claude Code and Codex, especially watching usage and swapping accounts. What it gives you From the README feature list: - Parallel worktrees. Fan one prompt across five agents, each in an isolated git worktree, compare the results and merge the winner. Because each agent has its own checkout, they cannot clobber each other. - Account switcher and usage tracking. See Claude and Codex usage and rate-limit resets, and hot-swap accounts without logging in again. - Notifications and unread state. Know when an agent finishes or needs attention, and mark threads unread to come back later. - Annotate AI diffs. Drop comments on any diff line and send them back to the agent. - Terminal splits. Ghostty-class terminals with WebGL rendering, and scrollback that survives restarts. - Design mode. Click any element in a real Chromium window to send its HTML, CSS and a cropped screenshot into the agent's prompt. - GitHub and Linear. Browse PRs, issues and boards in the app, and open a worktree from any task. - SSH worktrees. Run agents on a remote machine with file editing, git, terminals and port forwarding. - Mobile companion. Get notified from your phone when an agent finishes and send follow-ups. The README lists iOS and Android apps. - Orca CLI. Agents can drive Orca too, with commands such as orca worktree create, snapshot, click and fill. It works with any CLI agent, so if it runs in a terminal, it runs in Orca. Get started Download the app from the project's site or the GitHub releases page; the README points to a Download Orca button and says the team ships daily, so the changelog is the real feature list. Then: 1. Open a git repository in Orca. 2. Create a worktree for the task. Each worktree is its own branch and folder. 3. Launch Claude Code or Codex in that worktree's terminal. 4. Repeat for as many parallel attempts as you want, for example one worktree per approach to the same bug. 5. Compare the diffs, comment on lines you want changed, and merge the one you like. Watching usage across accounts If you hit rate limits on Claude Code or Codex, the usage tracking view is the feature to try first. The README says it shows usage and reset times for both, and lets you hot-swap accounts without a new login. Use only accounts you own and stay inside each provider's terms. Caveats - Several agents in parallel multiply token use. Watch the usage view. - Worktrees share your git history, so disk use is small, but dependency installs (node_modules and the like) happen per worktree. - This walkthrough follows the README and we have not run it end to end. The step-by-step version is on our use-case page: watch Claude and Codex usage and swap accounts with Orca. If you want one app for several agents without worktrees, see control Claude Code and Codex from one app with T3 Code. Want the setup commands for 50 AI repos people actually ship with? Get the free AI Repos That Actually Ship pack: dedupedai.com
@theo I think your best competitor which is also open source is Orca: stablyai/orca
Orcaを使ってみたら、開発のテンポがガラッと変わった話 こんにちは！ 最近、複数のAIコーディングエージェントを同時に動かせるADEの「Orca」が話題になっていますね。 普段はVSCodeでClaude Codeを使って開発しているのですが、「複数のタスクを同時に進められたら楽だな〜」と思い、実際にOrcaを試してみました！ 今回は、Orcaの「並列実行」と「スマホからの操作」を中心に、使ってみて分かったメリット・デメリットをお届けします。 🔗 公式サイト（無料）: onorca.dev 🐈⬛ GitHubリポジトリ: stablyai/orca ! ※ 本記事は Orca v1.4.243 時点の情報・検証をもとに記載しています。今後のアップデートで仕様や機能が変わる可能性がありますのでご注意ください。 そもそも「Orca」ってなに？ Orcaを一言でいうと、複数のAIエージェントを1つの画面で管理・並列実行できるデスクトップアプリです。 公式サイトではIDEではなく、「ADE（Agent Development Environment）」と表現されています。 IDE（VS Code / Cursor など）： 人間が直接コードを書くための統合開発環境 ADE（Orca など）： AIエージェントがコードを書き、人間がそれを指揮・レビューするためのエージェント開発環境 Orca自体が新しいAIモデルを提供しているわけではなく、手持ちのClaude CodeやCodexなどのAIを持ち込んで、1つの「管制塔」から一括操縦するイメージです。 実際に使ってみて感動した機能 1. Git worktreeを使った「超快適な並列実行」 一番感動したのが、Git worktreeを利用したタスク分離と並列実行です。 これまでは、1つのタスクをAIに依頼したら完了を待つか、別ウィンドウを開いて手動でブランチを切る必要がありました。 Orcaなら、画面左側の「＋」ボタンでタスク（作業スペース）を作るだけ。裏側で独立した作業フォルダ（worktree）とブランチを自動生成してくれます。 （並列でAIエージェントを実行している様子です↑） たとえば、こんな使い方ができます。 マルチタスク： タスクAとタスクBを、別々のAIエージェントで同時に進める モデル比較： 1つの同じタスクを別々のAIモデルに渡し、出来が良い方のコードを採用する 作業場所が完全に隔離されているため、コードが混ざって崩れる心配もありません。 実際、普段の感覚なら半日くらいかかると思うような「複数の機能改修」が、Orcaで並列実行させることで午前中の2時間足らずで片付いてしまったのは感動の体験でした！ 並列で動かしていると「どのエージェントが終わったか」を見逃しがちですが、作業が終わったときや操作が必要なときには通知音が「ピコン🎵」と鳴ってくれますし 画面上のタスク一覧のタイトル横にもアイコンで現在の進行状況や待機状態がパッと表示されるので、音だけでなく目視でもステータスがひと目で把握できます。 別タスクのレビュー中でもすぐにステータスがわかるので、地味に嬉しい機能でした🥰 2. GitHub感覚でサクサク直せる「インラインレビュー機能」 修正されたコードの確認画面が、GitHubのPR上でコードレビューをする感覚で操作できます！ 変更差分を見ながら、気になる行に直接「ここを共通化して」「ここを変数化して」と注釈を残すだけで、その指示が該当エージェントにそのままフィードバックされます。 チャット欄に「〇〇ファイルの〇行目を〜」と説明する手間がなくなり、チーム開発でのレビュー感覚で指示を出せるのが最高でした。 3. 家事の隙間時間で開発できる！「スマホからのリモート操作」📱 PCでOrcaを起動しておけばスマホから進捗確認や追加指示ができるので、家事育児に追われる私にとってはとっても嬉しい機能です！🙌 接続はスマホアプリをブラウザからダウンロードし、PCに表示されるQRコードをスマホで読み取ってペアリングで行います。 ペアリングした端末からしか操作できないので、他人に操作される心配もありません。 こんな感じで、ワークスペースを作成します。 これが想像以上に快適で、 重いタスクをAIに頼んでおき、洗濯しながらスマホで進捗チェック ベッドの中から「〇〇のバグ修正やっておいて」と依頼しておく といった「AIエージェントの進捗を監視するマネージャー」のような働き方ができるようになります。 差分もスマホからチェックできます！（ちょっと見にくいですが、、） さすがにGithubのようなインラインでのレビュー指示はスマホからはできないみたいでした。 あとはコミット履歴や、作成したPRも確認できるようです。 スマホでここまで確認できるのは便利ですね！ ! PCがスリープになると接続できないので、スリープ設定は 「なし（または十分長い時間）」 にしておく必要があります⚠️ 使って分かったメリット・デメリットまとめ ⭕️ メリット 機能単位で任せられるため、コード把握と効率化が両立できる GitHubライクなUIで生成コードのレビューが快適 スマホからいつでもどこでも進捗確認・指示ができる 面倒なコンフリクト解消までAIにお任せできる 複数タスクの並列実行でコンフリクトが発生しても、メイン側のエージェントにお願いすればコードの文脈を汲み取って解消・マージしてくれます。 （※もちろん最終的な差分確認やテスト実行は自分で行うのが安全な運用です） Token消費量がパッとひと目で確認できて安心 画面左下に「いまどれくらいAPIトークンを使ったか」がリアルタイムに可視化できるので、知らない間に利用上限に達してしまう心配もなし！ 急な差し込みタスクがあってもスタッシュする必要がない 「＋」ボタンで新しいタスクを作るだけで裏側に独立した環境が用意されるので、今の作業をわざわざ退避（stash）したりブランチを切り替えたりする手間がゼロになります！ ❌ デメリット・注意点 Token消費量上限に早く達する 並列で2〜3個のエージェントを同時に動かすため、Claude Codeなどの定額プラン利用時は利用上限（レートリミット）に達するスピードが早くなります。 Git worktree特有のセットアップの手間 新しいworktreeを作るたびに、node_modules などの依存パッケージのインストール（またはビルド）が必要です。また、.env などの .gitignore 対象のファイルは、新しいworktreeに自動ではコピーされません。 Orcaにはworktree作成時に指定したコマンドを実行する設定があるので、npm install や .env のコピーを登録しておけば自動化できます。ただし、この設定はプロジェクトごとに最初に用意しておく必要があります。 ファイルを他のワークスペースや、他のエディタにコピペできない 「ワークツリーAのAI生成の結果を、ワークツリーBに持ってきたい」と思った時や、他のエディタに移したいなーという時に、コピペコマンドが効かずコピーできませんでした。 Orca上で「ワークツリーBに〇〇をコピーして」と指示すれば代行してくれますが、あくまでエージェント経由を前提とした設計のため、手動での自由な操作感には欠けるようです。 どんな人におすすめ？ Orcaを使うことで、1人の開発者がチームのリーダー（指揮官）となって開発を進める感覚を体験できました。 特に以下のような人におすすめです！ 普段から複数タスクを並行して抱えている人 1つのAIの応答待ち時間にストレスを感じている人 GitHubのコードレビューのように直感的に指示を出したい人 PCの前で張り付けない or スマホからサクッと開発したい人 コードの変更内容をしっかり把握・レビューしながら効率化したい人 単発のコード修正なら今までのCursorやVS Codeで十分ですが、「AIにどんどん作業を任せて自分はレビューと指揮に専念したい」という方には間違いなく刺さるツールです。 気になった方は、ぜひ一度触ってみてください！
Kudos to @davidfano for making such a high-quality PR for Orca that it’s the only one to pass the elegance review in one go 👏 orca#37557 t.co
AIツールを自己管理できるOSSにするために、認証・接続・日常操作の責務を分ける !AIは借りる。自分の道具は、自分で。 先に、結論を3行で書きます。 - 外部AIを使うことと、自作ツールの運営者へ認証や接続管理を預けることを分けて考えました。 - PC・サーバー・ネットワークは利用者が選び、ソフトは依頼・監視・承認・引き継ぎを使いやすくする方針です。 - many-ai-cliとMany Irisの構想整理であり、統合の完成やゼロトラストの実装を報告する記事ではありません。 時間に合わせて、読み方を選べます。 - 少し忙しい人向け：5分で読める要約版（個人サイト） - もっと深掘りしたい人は、このまま本文へどうぞ。 まず、誰が何を管理するかを分けました 複数のAIコーディングCLIを操作・監視するmany-ai-cliと、案件や計画の現在地を扱いたいMany Irisについて、提供範囲を整理しています。 many-ai-cliのコードと概要はこちらです。 GitHub：ishizakahiroshi/many-ai-cli 紹介ページ：ishizakahiroshi.com 前回は、スマホのChatGPTとローカルAIをつなぐ実験を書きました。接続できても、仕事の受領・実行・結果照合まで自動でつながるとは限らない、という内容です。 前回の記事：qiita.com その後、認証や中継の設定をどこまでツール側が吸収するかを考えました。利用者がログインするだけでPCにつながる体験を提供するなら、提供側にはアカウント、接続先の登録、中継、資格の失効、障害対応が必要になります。 今回は、そのサービス運営を初版の必須条件にせず、自分で管理する環境で使う道具として整理することにしました。 | 管理するもの | 基本の担当 | ソフト側で使いやすくすること | |---|---|---| | PC・VPS・ネットワーク | 利用者 | 接続先の登録、到達状態の表示、設定不足の診断 | | AIサービスとその認証 | 利用者が選んだサービスと利用者 | 利用者の環境にある認証を扱い、認証切れを説明する | | 依頼・実行・監視 | ソフト | 同じ仕事と実行状態を対応付ける | | 計画・承認・引き継ぎ | ソフトで扱う構想 | 許可範囲、判断待ち、結果不明を区別する | | 環境の更新・復旧 | 利用者 | 状態の保存、更新の説明、復元しやすい構造 | 表の後半は、今後具体化・検証する設計を含みます。運営者が管理しないことと、ソフトに認証や認可が要らないことは別です。 「自分で管理する」と「全部手作業」は分けたい 初回の環境構築は、自分でできる人に使ってもらえればよいと思っています。その代わり、日常の操作は楽にしたいです。 案件を選ぶ。指定した計画を任せる。途中で判断が必要なら返事をする。担当AIが替わっても、何を許可して、どこまで終わったかを追える。最後に成果物と根拠まで確かめる。 many-ai-cliの実行側と、Many Irisの計画・状況・根拠を、一式の体験としてつなげたいと考えています。毎回チャットやターミナルを読み直して、利用者が全体を再構成する負担を減らすためです。 !外部AIの能力、利用者が管理する環境、ソフトが支援する日常操作の分担 図は、AIから借りる能力と、利用者が管理する環境、ソフトが支援する操作を分けたものです。外部AIへ送った指示や資料は、そのベンダーが処理する前提です。 「データを一切外へ出さない」という意味ではありません。自作ツールの運営者へ、新たに認証情報や接続権限を預けることを必須にしない、という提供方針です。 接続経路と、処理を動かす場所も別でした PCで処理することと、Cloudflareなどを到達経路に使うことは両立します。指揮者や認証をCloudflare側に置く案も、個人のVPSに置く案も考えられます。 ただし、それらを最初から全て実装する必要はありません。まず自分が使う構成で、登録から依頼、承認、結果確認までの一周を作るつもりです。 MCPという接続方式を選んでも、ネットワーク上で届くかどうかは別に確認します。スマホアプリ自身が呼ぶ場合と、ChatGPTのようなサービス側が呼ぶ場合では、通信の出発点が違います。 T3 Codeの公式文書も、クラウド上の外部AIにはインターネットから届く環境アドレスが必要で、Tailscaleのアドレスは自分のtailnet内から使うものと区別しています。 github.com/pingdotgg/t3code/blob/47f2c8d29e981c77… 自主管理というだけでは、独自の機能にはならない 参考にしたT3 Codeには、LAN・Tailscale・SSHの接続方法があります。Orcaにも、Tailscaleなどを使うremote serverの説明があります。両者を「認証を必ず提供者へ預ける製品」として扱うのは正確ではありません。 T3 Code：github.com/pingdotgg/t3code/blob/47f2c8d29e981c77… Orca：github.com/stablyai/orca/blob/10a623b910d82c80b0c… | 比べる軸 | 接続をサービス側に任せる形 | 利用者が自分で管理する形 | |---|---|---| | 初期設定 | 提供側が吸収する部分が増える | 利用者が環境や経路を用意する | | 接続基盤の運用 | サービス提供側が担う | 利用者が選んだ環境で担う | | 日常の使いやすさ | ソフトの設計で変わる | こちらもソフトの設計で改善できる | これは製品を二分する表ではなく、提供形態の比較です。同じ製品が両方を用意することもあります。 自分の道具では、案件の現在地、許可した計画、担当交代、成果の根拠までつなぐ体験を確かめたいです。上流にも関連する機能はあるので、優れているかどうかは同じ仕事で使ってみないと分かりません。 ゼロトラストという言葉は、少し慎重に使います Nextcloudの、自分のサーバーや選んだホスティング先で動かせる考え方は参考になります。 <!-- doxguard: allow Nextcloud --> nextcloud.com 今回の整理の中心は、自己管理と、データや認証の主導権です。ゼロトラストは、ネットワーク上の場所や所有者だけを根拠に暗黙の信頼を与えず、認証・認可を行う考え方です。 nist.gov ローカルで動かしたり、OSSとして公開したりするだけで、その設計が実現するわけではありません。AIの指示をどの権限で実行するか、事前許可の範囲をどう照合するかは、別に実装して確かめる必要があります。 まず、自分が使うところを仕上げます 自己管理できる分、AI CLIやOSの変更への追従、認証の更新、設定やデータの復旧は残ります。保守コストが自動的に最小になるわけではありません。 だからこそ、自分に必要な範囲から作ります。CloudflareとVPSを両対応にすることより、毎日使う一周が分かりやすく、困ったときに戻せることを先に確かめたいです。 使い方や環境が合う人がいれば使ってもらい、違う使い方がしたければ改造してもらう。まず自分は使い続ける。今は、そのくらいの温度感で育てていこうと思っています。 many-ai-cliのコードと概要です。Many Irisとの統合は未完成で、この記事はその提供範囲を整理した記録です。 GitHub：ishizakahiroshi/many-ai-cli 紹介ページ：ishizakahiroshi.com --- ※ ヘッダー画像は AI（画像生成）で作成しています。本文図はHTMLで組版しています。 書いた人: ishizakahiroshi 群馬の北部で、保護猫2匹と暮らす、在宅エンジニア（何でも屋） ishizakahiroshi.com github.com/ishizakahiroshi X（業務委託・各種相談はこちら）： x.com バックエンド・インフラ・AI連携まわりで、業務委託のご相談を受け付けています。フルリモートです。スポットや週2〜3時間からでも歓迎で、いろんな案件に携われたらうれしいです。こんな相談、歓迎です。
The Hidden Cost of Running Multiple AI Coding Agents My terminal has several AI coding agents running. One is adding a feature in a side project, another is writing tests in a second repository, a third is reviewing a branch. Every pane is moving, and it looks like a lot of work is getting done. Then the panes stop, one after the other, with the same kind of message: usage limit reached. The work doesn't fail. It just waits, until the window resets or until I decide to pay for more. I use Claude Code on a Claude Pro plan and OpenAI Codex on ChatGPT Plus, two subscriptions of $20 a month each in the US (billed monthly), plus tmux, Git worktrees, subagents, Agent Teams and Orca. That combination raised a question I couldn't answer from the feeling of speed: are parallel AI agents making me more productive, or am I just reaching my subscription usage limits faster? This post is my answer, built from the official docs of both tools and the research on AI coding productivity: 1. What a Claude Pro and a ChatGPT Plus plan actually give you, and what they don't promise. 2. Single agent, tmux sessions, subagents and Agent Teams compared, with diagrams. 3. A tested tmux + Git worktree workflow, and where Orca fits. 4. A way to measure it on your own plans, with the metrics that matter. 5. A decision framework and a list of habits that make a $20 plan last. One idea runs through all of it: more generated code is not more delivered software. --- The illusion of infinite productivity Running four agents feels four times faster. It isn't, and the reason is in three words people use as synonyms. | Term | What it measures | What parallel agents change | | --- | --- | --- | | Throughput | Work items completed per hour (here: code generated, not yet reviewed) | Can increase for independent tasks, but coordination and resource limits may reduce the gains | | Latency | Time from "start this task" to "this task is done" | Can go down for independent tasks, up for dependent ones | | Productivity | Verified, merged, working features per unit of your time and budget | Unknown until you count review, rework and waiting | At best, parallel agents raise throughput of generated code. Productivity only counts code that passed tests, survived review and merged. Everything between those two numbers is work that lands on you: reading diffs, resolving conflicts, re-explaining context, and waiting for a reset. There is research on how unreliable the feeling of speed is. In METR's 2025 randomized controlled trial, 16 experienced open-source developers worked on 246 real issues from their own repositories. With AI tools allowed, they took 19% longer. Before the study they expected a 24% speedup, and afterwards they still believed AI had made them about 20% faster. That result has limits that matter. It used early-2025 tools (mostly Cursor with Claude 3.5 and 3.7 Sonnet), large mature codebases and a small sample. In a February 2026 update, METR said developers are probably more sped up now, but its new data is "only very weak evidence" of how much, partly because many developers refused to work without AI. So the study is not evidence that AI makes you slower. Its useful lesson here is simpler: your sense of speed is not a measurement. Google's DORA team points in the same direction from a different angle. The 2024 report associated higher AI adoption with better documentation and code review speed, but also with an estimated 1.5% drop in delivery throughput and 7.2% drop in delivery stability. The 2025 report sums it up as AI being an amplifier of what a team already does well or badly. --- What Claude Pro and ChatGPT Plus usage limits actually give you Before comparing workflows, get the budget right. Neither vendor sells you a fixed number of tokens, and several different limits get mixed up in discussions online. | Limit | What it is | Claude Pro | ChatGPT Plus (Codex) | | --- | --- | --- | --- | | Session window | Usage allowed inside a five-hour period | Five hours, starting with your first message (source) | Five hours, published as ranges of local messages per model (source) | | Weekly limit | A second cap over the week | Yes, across all models, reset at a fixed time per account | "Weekly limits may also apply" | | Shared pool | What draws from the same budget | claude.ai, Claude Code and Claude Desktop | Local messages and cloud tasks | | Published allowance | A guaranteed token count | None; "the number of messages you can send will vary" (source) | Ranges, explicitly "not fixed message limits" | | Paying for more | When the plan runs out | Optional usage credits, prepaid, billed at standard API rates (source) | Optional credits, or an API key billed at API rates | | Context window | How much one conversation can hold | A model property and a separate limit, though a fuller context costs more quota per turn | Same: a separate limit, but more context means more usage | | How to check | Remaining usage | /usage in Claude Code, Settings > Usage | /status in the CLI, the Codex usage dashboard | Prices and ranges are as of November 2026. Three details change how you should work. The pool is shared. Every Claude Code session in every tmux pane, every subagent and every chat on claude.ai draws from the same Pro budget. Ten terminals are not ten budgets. On the OpenAI side, local messages and cloud tasks share one allowance too, and the docs warn that cloud tasks "may use more of your allowance than local messages". Usage is not message count. Anthropic says usage depends on the length and complexity of the conversation, the features you use, the model and the effort level. Its Claude Code guide adds the part most people miss: every turn resends the conversation so far, plus CLAUDE.md and the files Claude has read, before your new prompt. A long session gets more expensive per message as it grows. Model choice is the biggest lever you control. OpenAI publishes it plainly. On Plus, the heaviest model in the Codex table allows 5 to 45 local messages per five hours, and the lightest allows 350 to 3,000. The published ranges for the two ends of the table differ by about two orders of magnitude, and OpenAI says they vary by task, so read them as a direction, not a conversion rate. Anthropic doesn't publish numbers, but says Opus "uses meaningfully more of your quota" and that Sonnet is the right choice for most coding work. Two traps to avoid. API prices are not the price of subscription usage; they only apply when you turn on usage credits or use an API key. And if ANTHROPIC_API_KEY is set in your shell, Claude Code uses that key instead of your subscription, which can turn an evening of "free" agents into an API bill. --- One agent vs multiple agents There are four architectures in my day-to-day, and they behave very differently on tokens, context and review. flowchart LR subgraph A["A. Single agent"] D1([You]) --> S1[One session] end subgraph B["B. tmux sessions"] D2([You]) --> P1[Claude Code: project 1] D2 --> P2[Codex: project 2] D2 --> P3[Claude Code: project 3] end subgraph C["C. Subagents"] D3([You]) --> M[Main session] M --> SA1[Explore] M --> SA2[Test runner] SA1 -. summary .-> M SA2 -. summary .-> M end subgraph D["D. Agent Team"] D4([You]) --> L[Lead] L --> T1[Teammate 1] L --> T2[Teammate 2] T1 <-. messages .-> T2 end A. A single agent One Claude Code or Codex session working through tasks in order. It has the best context continuity: the agent remembers why a decision was made, and you review one stream of changes. Debugging is simple because there is one author. It isn't automatically the most token-efficient option, though. Because every turn resends the whole conversation, a session that carries three unrelated tasks pays for the history of the first two while working on the third. Anthropic's own best practices say /clear between unrelated tasks "costs nothing" and stops the next task from paying for the previous one. A single agent is efficient when its context is relevant, not when it is long. B. Multiple tmux sessions across projects Independent agents on independent projects. This is the cleanest form of parallelism: no shared files, no merge conflicts, and each agent has a small, relevant context. Two limits still apply. All the Claude Code sessions share one quota, so parallelism spends your five-hour window faster; it doesn't create more of it. And the scarce resource moves to you: each pane eventually asks a question, needs a decision or produces a diff to review. tmux keeps the sessions alive and organized. It does nothing for token consumption. This is also where mixing providers is a real advantage. Claude Pro and ChatGPT Plus are two separate pools. Putting one project on Claude Code and another on Codex is the only way in this post to get more included allowance without upgrading a plan or paying API rates for credits. C. Subagents inside one project A parent session delegates a bounded job to a subagent. In Claude Code, each subagent runs in its own context window, and only its result returns to the main conversation. The built-in Explore subagent, for example, is read-only and made for searching a codebase. The common misunderstanding is that subagents save tokens. They save context, which is different. The docs say each subagent sends its own requests, which "count toward the same usage limits as your main conversation". What you gain is a main session that stays short and focused, because 40 files of search results never enter it. Codex says the same about its own subagents: they "consume more tokens than comparable single-agent runs" (source). A real example from this post. To research it, I delegated the documentation reading to Claude Code subagents (Claude Code 2.1.308): five of them read the Anthropic help center, the Claude Code docs, the Codex docs, Orca's docs and the productivity studies in parallel, and all came back in under two minutes. Claude Code reported about 430,000 tokens across those five. That's a token total, not a share of my quota, which neither tool exposes as a number. That's the ideal case for subagents: read-only, independent, verbose work. It still needed checking: one later verification pass found that an earlier subagent summary had marked a sentence as missing from a doc page when it was there. Subagents pay off for narrow, verbose, read-heavy tasks: exploring a codebase, running a test suite and summarizing failures, reviewing a diff. They pay off more with a cheaper model; Claude Code lets you set model: haiku on a simple subagent. D. Agent Teams Agent Teams in Claude Code are experimental and off by default (you enable them with CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1). A lead session coordinates separate Claude Code instances that share a task list and message each other directly. Subagents return their result to the caller. One catch if you use both: while Agent Teams are enabled, a subagent that Claude names launches as a teammate, so a team, with team-level token costs, can form when you only asked for delegation. The docs are direct about the cost. Agent Teams "use significantly more tokens than a single session", usage scales with the number of active teammates, and the costs page estimates about 7x the tokens of a standard session when teammates run in plan mode. The same docs say that for sequential tasks, same-file edits or work with many dependencies, a single session or subagents are more effective. Anthropic's engineering team found the same pattern outside Claude Code. Its multi-agent research system used about 15 times the tokens of a chat, worked best on breadth-first research, and the post notes that "most coding tasks involve fewer truly parallelizable tasks than research". | | Single agent | tmux sessions | Subagents | Agent Team | | --- | --- | --- | --- | --- | | Context | One, continuous | One per project | Isolated per task, summary returns | One per teammate | | Tokens vs one session | Baseline | Sum of sessions, same pool | Higher, but the main context stays small | Highest, scales with teammates | | Coordination | None | You | The main agent | Lead, task list, messages | | Merge conflicts | None | None across projects | Low if subagents only read | Possible on shared files | | Best for | Dependent, sequential work | Unrelated projects | Search, tests, review | Research, competing hypotheses, cross-layer work with clear ownership | --- tmux, Git worktrees and multi-agent IDEs When you want two agents on the same repository, they need separate checkouts, or they'll edit the same files under each other. Anthropic's docs put it simply: give each piece of work "its own checkout so the edits can't collide". Git worktrees are the standard way to do that: each worktree is a separate directory, on its own branch, sharing one repository. Here is the workflow I'd use. I ran the git and tmux commands in a scratch repository with git 2.54 and tmux 3.8, with the agent commands replaced by echo so no usage was spent (the git pull and npm ci lines need a real remote and project, so they didn't run there): # From the main checkout, with an up-to-date main git switch main && git pull --ff-only # 1. One worktree and one branch per independent task git worktree add -b feat/rbac ../app-rbac main git worktree add -b feat/audit-log ../app-audit main # 2. Worktrees are fresh checkouts: no .env, no node_modules. # Start from the committed template, never your real .env, then give # each worktree its own dev-only database and no production secrets. cp .env.example ../app-rbac/.env && cp .env.example ../app-audit/.env createdb app_rbac && createdb app_audit perl -pi -e 's|^DATABASE_URL=.*|DATABASE_URL=postgres://localhost:5432/app_rbac|' ../app-rbac/.env perl -pi -e 's|^DATABASE_URL=.*|DATABASE_URL=postgres://localhost:5432/app_audit|' ../app-audit/.env (cd ../app-rbac && npm ci) && (cd ../app-audit && npm ci) # 3. One tmux session, one window per agent tmux new-session -d -s agents -n rbac -c "$PWD/../app-rbac" tmux new-window -t agents -n audit -c "$PWD/../app-audit" tmux send-keys -t agents:rbac 'claude "Implement docs/tasks/rbac.md. Run npm test before you stop."' Enter tmux send-keys -t agents:audit 'codex "Implement docs/tasks/audit-log.md. Run npm test before you stop."' Enter tmux attach -t agents Each task description lives in a file in the repository, so both agents start from the same written requirements instead of a prompt you typed differently twice. The second window runs Codex on purpose. One practical detail: the first time you run claude in a new directory it asks you to trust the folder, so attach to the session and accept it before the prompt runs. Then review and merge like you would a colleague's branch: git log --oneline main..feat/rbac # what the agent committed git diff --stat main...feat/rbac # how big the change is (cd ../app-rbac && npm test) # run the checks yourself git switch main && git merge --no-ff feat/rbac # Cleanup, only after the merge and once nothing in the worktree still matters git -C ../app-rbac status --short --ignored # lists what removal would touch git worktree remove ../app-rbac # fails on modified or untracked files git branch -d feat/rbac # fails if the branch isn't merged dropdb app_rbac # the worktree's own dev database # Repeat for feat/audit-log, ../app-audit and app_audit, then: tmux kill-session -t agents In my test, git worktree remove refused to delete a worktree with an untracked file until I passed --force, and git branch -d refused to delete a branch still checked out in a worktree. Keep those guards, and know their gap: gitignored files don't count, so node_modules and a .env you edited inside a worktree are deleted without a warning. That's why the status --ignored line comes first: if it lists anything you still need, copy it out before you remove the worktree. Both tools also do this for you. claude --worktree feature-auth starts a Claude Code session in a new worktree, and a .worktreeinclude file lists the gitignored files to copy into it; keep that list to dev-only files, for the same reason as above. OpenAI's desktop app has a Worktree mode for running Codex chats in parallel (docs); its docs don't describe the same for the CLI. A worktree isolates files, not processes. Both agents run as your user, on the same machine, with the same network access, the same credentials in ~/.aws or ~/.ssh, and often the same local database and ports. If two worktrees run migrations against one Postgres database, they will collide, which is why each one got its own above. If you need security isolation, that comes from the agents' sandbox settings, containers or separate machines, not from a second directory. Where Orca fits Orca is an open-source (MIT) desktop app for running coding agents side by side, each in its own Git worktree. It supports Claude Code, Codex and many other CLI agents, and you use your own subscriptions; it doesn't sell model usage. According to its docs, it creates a real git worktree per task, shows diffs you can annotate and send back to the agent, notifies you when an agent finishes or needs attention, and tracks the usage and reset times of providers like Claude Code and Codex in its status bar. What it doesn't do: raise your limits. Orca runs the same CLIs against the same plans, so four agents in Orca spend the same pool as four agents in tmux. Its own docs say to prefer the provider console for authoritative spend. Its value is visibility (which agent is waiting on you, how much quota is left) and less manual worktree work. Its cost is another app in your toolchain that releases very often (v1.4.245 on October 30, 2026), with plugins that, per its release notes, run with full access to your computer once approved. My rule: if you run one or two agents, tmux and three git commands are enough. When you regularly lose track of which agent is blocked, a tool like Orca starts paying for itself in attention, not in tokens. --- The hidden cost of parallelism Parallel agents move work to places you don't see in the moment. Duplicated context. Every agent learns your codebase from scratch: it reads CLAUDE.md or AGENTS.md, explores the folders, opens the same core files. Four agents pay that onboarding four times, from one quota. Coordination tokens. In an Agent Team, messages between teammates and task-list updates are model calls too. Every teammate is also a separate Claude instance with its own context window, which is the reason Anthropic gives for teams in plan mode using about seven times the tokens of a standard session. Merge conflicts and semantic conflicts. Worktrees prevent agents from overwriting each other's files. They don't prevent two branches from making incompatible decisions, like two different error formats or two ways of checking a role. Git merges those cleanly, and your tests or your users find them later. Review is serial. You can run five agents in parallel, but you read diffs one at a time. If an agent produces a 600-line change in 20 minutes and you need 40 minutes to review it properly, adding a second agent mostly doubles your review queue. Interruptions. A limit that hits halfway through a task stalls it. Recent Claude Code versions (2.1.234 and later) wait and continue on their own after the reset, but the first request after a long break misses the prompt cache and reprocesses your whole context. Meanwhile, the half-finished branch blocks whatever depended on it. flowchart LR G[Agents generate code<br/>parallel] --> R[You review<br/>serial] --> T[Tests and fixes] --> M[Merged and verified] R -. rework .-> G The bottleneck in AI-assisted development is usually the review step, not the generation step. Add agents until your review queue is full, and stop there. --- How to measure this on your own plans No article can tell you which workflow wins on your codebase, your plans and your review speed. A small, controlled comparison can, and it's the only way to stop trusting the feeling of speed that METR measured. This is the setup I'd use. The project. A TypeScript REST API with PostgreSQL, authentication, role-based access control (RBAC), automated tests and one small frontend screen. Every run starts from the same commit, the same written task files and the same acceptance tests. The tasks. A mix of independent and dependent work: | # | Task | Depends on | | --- | --- | --- | | T1 | Add a roles table, migration and seed | none | | T2 | RBAC middleware: deny by default, check role and resource owner | T1 | | T3 | Audit log of security events (login, failed login, role change) | none | | T4 | Rate limiting on login with progressive lockout | none | | T5 | Admin screen listing users and their roles | T2 | | T6 | Tests that try IDOR and privilege escalation against T2 | T2 | The workflows. Single agent, tmux sessions (one task per session, same checkout, to expose conflicts), subagents, an Agent Team, tmux with worktrees, and worktrees split across Claude Code and Codex. If you use Orca, run the last one from it as a seventh. Change one thing at a time: same models, same task files, same tests, and at least two runs per workflow, because one run of an agent is an anecdote. The metrics. Wall-clock time to the last merged task, active human time (time you spend typing, reviewing or deciding), input, output and cache tokens, quota consumed, sessions interrupted by a limit, acceptance test pass rate, security issues found in review, merge conflicts, rework rounds, and verified tasks per hour: tasks that passed the acceptance tests and your review, divided by wall-clock hours. Both tools expose token data. Claude Code exports claude_code.token.usage through OpenTelemetry when CLAUDE_CODE_ENABLE_TELEMETRY=1 is set and an exporter is configured (for example OTEL_METRICS_EXPORTER=console), with input, output and cache tokens as separate types, and codex exec --json emits a turn.completed event with input_tokens, cached_input_tokens and output_tokens (docs). Quota is harder: neither plan shows a raw number, so record the percentage from /usage or /status before and after each run. Put one row per workflow and one column per metric in a spreadsheet, and read verified tasks per hour first. A workflow that finishes faster but needs more rework or more of your review time hasn't won anything. What I'd expect, as a hypothesis and not a result: worktrees across two providers will win on verified tasks per hour for T1, T3 and T4, and a single agent will win on T2, T5 and T6, because those three share one design decision (how a role is checked) that is cheaper to make once than to explain to three agents. --- How to get more from your AI subscription These are the habits I'd apply before upgrading any plan. Each one comes from the vendors' own guidance or follows from how usage is counted. 1. Clear between tasks. /clear when switching to unrelated work, /compact with a focus when continuing a long task. Every turn resends the history, so stale history is the most expensive thing in your session. 2. Pick the model per task. Sonnet for most Claude Code work, Opus only when it's stuck or for wide changes (/model opusplan plans with Opus and executes with Sonnet). On Codex, a lighter model for routine edits buys you a much larger allowance. 3. Keep the always-loaded files small. Anthropic suggests keeping CLAUDE.md under 200 lines; OpenAI suggests reducing the size of AGENTS.md. Both get read on every session. 4. Turn off what you don't use. Every MCP server adds to the context: in Claude Code its tool names and instructions (full definitions load only when a tool is used), in Codex context on every message. Both vendors say to disable the servers you don't need, and Anthropic suggests CLI tools like gh when they exist. 5. Delegate verbose work, not judgement. Send searches, test runs and log reading to a subagent with a cheap model, and keep design decisions in the main session. 6. Split by provider, not only by pane. Put independent projects or tasks on the plan that has quota left. 7. Write the task down. A task file with acceptance criteria and the test command saves the back-and-forth that burns tokens, and it lets you hand the same task to a different agent after a reset. 8. Watch the meter before you start, not when it stops you. Check /usage or /status before launching parallel work. If the window is 80% spent, start one task, not four. 9. Turn on paid overflow deliberately. Usage credits are opt-in and billed at API rates. Set a monthly cap if you enable them, so a forgotten agent can't run up a bill. 10. Check that ANTHROPIC_API_KEY is unset in shells where you mean to use your subscription. --- A decision framework | Workload | Best fit | Why | | --- | --- | --- | | One feature, steps depend on each other | Single agent, /clear between features | Shared decisions stay in one context | | Unrelated projects | tmux sessions, mixed providers | Clean parallelism, two quotas | | Independent tasks in one repository | Worktrees, one agent each | File isolation, simple merges | | Search, test runs, log analysis, review | Subagents with a cheaper model | Keeps the main context small | | Debugging with competing hypotheses, broad research | Agent Team, few teammates | Teammates challenge each other; worth the tokens | | Same files, shared schema, tight dependencies | Single agent | Parallel agents create semantic conflicts | | Three or more agents, or you lose track of which is blocked | Orca or a similar tool | Pays back in attention, not quota | | Window almost spent | One small task, or switch provider | Interrupted work stalls, and resuming re-reads the whole context | --- Final verdict So, are parallel AI agents making developers more productive, or just reaching the limit faster? Both, depending on the work. Parallel agents are worth it when tasks are truly independent, when each one has written acceptance criteria and tests, when the work is spread across two providers' quotas, and when your review capacity keeps up with what they produce. A single agent is the better choice when the tasks share decisions, touch the same files or depend on each other, which, according to Anthropic's own engineering team, describes more coding work than research work. What doesn't hold up is the idea that more agents means more software. Every architecture in this post spends from a limited pool, and every one of them ends at the same place: a person reading a diff and deciding whether it's right. The best AI coding workflow is not the one running the most agents. It's the one producing the most verified engineering value within its constraints. Takeaway - Your quota is shared. Every Claude Code pane, subagent and chat draws from one Pro pool; Codex local and cloud work share one Plus pool. - Subagents save context, not tokens. Use them for verbose, read-heavy work, with a cheaper model. - Agent Teams cost about 7x in plan mode. Use them for work that benefits from discussion, not for routine edits. - Worktrees isolate files, not processes. Separate databases, ports and credentials need their own isolation. - Two $20 plans are two pools. Splitting work by provider is the cleanest way to get more allowance without upgrading. - Count verified tasks per hour, not agents running or lines generated. How many agents can you run before your review becomes the bottleneck, and what did you change when you hit that point? Tell me in the comments. --- I'm Diogo Soares, a Staff AI Engineer working on AI agents and legacy modernization. If this was useful, follow me here on DEV.to and on Instagram at @diogosoares.dev, where the habits from this post become a carousel you can save for your next planning session. This article also has a video walkthrough on my YouTube channel, Diogo Soares Dev, so subscribe there for the next ones. Let's also connect on LinkedIn, or check out diogosoares.dev.
you might enjoy learning more about this zed.dev in case it sparks new ideas ACP helps with agent interoperability and helps a lot of IDEs and ADEs integrate all the major harnesses seamlessly zed zed-industries/zed orca github.com/stablyai/orca/tree/main/src/main I haven't looked at the cli implementation but you can get very far with integrating a harness while not invoking the model directly via API
Conheça o Orca: orquestrador para agentes de IA de código O que é O Orca é uma ferramenta de orquestração para trabalhar com múltiplos agentes de inteligência artificial de código, como Codex, ClaudeCode, OpenCode e Pi. O sistema permite executar os agentes lado a lado, utilizando sua própria assinatura. O aplicativo funciona em computadores com macOS, Windows e Linux, além de oferecer suporte a execuções remotas via SSH e um aplicativo móvel complementar. Para quem serve É voltado para pessoas que desenvolvem software e utilizam ferramentas de IA em seu fluxo de trabalho. É útil para quem deseja enviar o mesmo comando para múltiplos agentes em worktrees isoladas do Git e comparar as respostas. O aplicativo também atende a quem precisa acompanhar tarefas pelo celular, integrar projetos do GitHub e Linear, editar arquivos ou inspecionar elementos visuais em Chromium com o Design Mode. Como começar 1. Faça o download do Orca para o seu sistema operacional (macOS, Windows ou Linux). 2. Configure o acesso aos seus agentes de código usando sua assinatura. 3. Instale o aplicativo móvel no iOS ou Android para receber notificações e controlar agentes à distância. 4. Abra seus projetos no Orca para criar worktrees paralelas, gerenciar terminais e integrar seu fluxo de trabalho. Instalação brew install --cask stablyai/orca/orca brew upgrade --cask stablyai/orca/orca yay -S stably-orca-bin 🔗 Repositório oficial: stablyai/orca Veja em 1 minuto {% embed youtube.com %} 📚 Mais conteúdos do canal: gist.github.com
[개발자들의 PICK] 이번 주 깃허브 트렌딩 결산, 인기 오픈소스 TOP 10 이번 주 깃허브에서 가장 많은 별을 받은 오픈 소스 TOP 10을 10위부터 소개합니다. 소개한 저장소 링크는 고정 댓글에 있습니다. 00:00 이번 주 TOP 10 00:05 10위 안드로이드 스킬 00:51 9위 오르카 01:38 8위 오픈코드 02:15 7위 루플로 02:47 6위 그래피파이 03:32 5위 트레이딩 에이전츠 04:17 4위 카파시 스킬 04:56 3위 클로드 SEO 05:35 2위 지식 노동 플러그인 06:14 1위 클라우드플레어 시큐리티 오딧 스킬 06:55 마무리 📌 이번 주! 깃허브 트렌딩 TOP 10 저장소 10위 안드로이드 스킬 — android/skills 9위 오르카 — stablyai/orca 8위 오픈코드 — anomalyco/opencode 7위 루플로 — ruvnet/ruflo 6위 그래피파이 — Graphify-Labs/graphify 5위 트레이딩 에이전츠 — TauricResearch/TradingAgents 4위 카파시 스킬 — multica-ai/andrej-karpathy-skills 3위 클로드 SEO — AgriciDaniel/claude-seo 2위 지식 노동 플러그인 — anthropics/knowledge-work-plugins 1위 클라우드플레어 시큐리티 오딧 스킬 — cloudflare/security-audit-skill [en-US] [Developer's PICK] This Week's GitHub Trending Roundup, Top 10 Popular Open Source Projects Here are the Top 10 Open Sources with the Most Stars on GitHub this week, starting from 10th place. Links to the featured repositories are in the pinned comment. 00:00 This Week's Top 10 00:05 10th Android Skills 00:51 9th Orca 01:38 8th OpenCode 02:15 7th Luplo 02:47 6th Graphify 03:32 5th Trading Agents 04:17 4th Kapasi Skills 04:56 3rd Claude SEO 05:35 2nd Knowledge Work Plugin 06:14 1st Cloudflare Security Audit Skills 06:55 Wrap-up 📌 This Week! GitHub Trending Top 10 Repositories 10th Android Skills — android/skills 9th Orca — stablyai/orca 8th Open Code — anomalyco/opencode 7th Ruflo — ruvnet/ruflo 6th Graphify — Graphify-Labs/graphify 5th Trading Agents — TauricResearch/TradingAgents 4th Karpathy Skills — multica-ai/andrej-karpathy-skills 3rd Claude SEO — AgriciDaniel/claude-seo 2nd Knowledge Work Plugins — anthropics/knowledge-work-plugins 1st Cloudflare Security Audit Skills — cloudflare/security-audit-skill [id] [Pilihan Pengembang] Rekap Trending GitHub Minggu Ini, 10 Open Source Terpopuler Berikut adalah 10 Open Source Teratas dengan Bintang Terbanyak di GitHub minggu ini, dimulai dari peringkat ke-10. Tautan ke repositori unggulan ada di komentar yang disematkan. 00:00 10 Teratas Minggu Ini 00:05 Peringkat ke-10 Android Skills 00:51 Peringkat ke-9 Orca 01:38 Peringkat ke-8 OpenCode 02:15 Peringkat ke-7 Luplo 02:47 Peringkat ke-6 Graphify 03:32 Peringkat ke-5 Trading Agents 04:17 Peringkat ke-4 Kapasi Skills 04:56 Peringkat ke-3 Claude SEO 05:35 Peringkat ke-2 Knowledge Work Plugin 06:14 Peringkat ke-1 Cloudflare Security Audit Skills 06:55 Ringkasan 📌 Minggu Ini! 10 Repositori Terpopuler di GitHub 10 Android Skills — android/skills 9 Orca — stablyai/orca 8 Open Code — anomalyco/opencode 7 Ruflo — ruvnet/ruflo 6 Graphify — Graphify-Labs/graphify 5 Trading Agents — TauricResearch/TradingAgents 4 Karpathy Skills — multica-ai/andrej-karpathy-skills 3 Claude SEO — AgriciDaniel/claude-seo 2 Knowledge Work Plugins — anthropics/knowledge-work-plugins 1 Cloudflare Security Audit Skills — cloudflare/security-audit-skill
Top 10 GitHub Repos This Week | Oct 18 – Oct 24 | The Harness Beats the Model This week the biggest gains went to the harness around the agent, not the model: Cloudflare's security audit skill took #1 with 12,680 new stars, and three of the ten are instructions rather than apps. ⏱️ TIMESTAMPS 0:00 — Intro 0:46 — #10 andrej-karpathy-skills — One rules file for coding agents (223.6K⭐️) 2:37 — #9 claude-plugins-official — Anthropic's official plugin directory (44.5K⭐️) 4:36 — #8 ruflo — An agent meta-harness (79.2K⭐️) 6:38 — #7 ai-memory — Shared memory across coding agents (13.4K⭐️) 8:46 — #6 ComfyUI — Node-graph engine for AI images and video (142.8K⭐️) 10:50 — #5 hyperframes — Write HTML, render video (71.9K⭐️) 13:13 — #4 opencode — The open source coding agent (221.4K⭐️) 15:21 — #3 graphify — Your codebase as a knowledge graph (134.8K⭐️) 18:01 — #2 orca — A command center for a fleet of agents (105.4K⭐️) 20:18 — #1 security-audit-skill — Turn your agent into a security auditor (46K⭐️) 23:17 — Recap & Trends 🔗 REPOS • #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills • #9 claude-plugins-official → anthropics/claude-plugins-official • #8 ruflo → ruvnet/ruflo • #7 ai-memory → akitaonrails/ai-memory • #6 ComfyUI → Comfy-Org/ComfyUI • #5 hyperframes → heygen-com/hyperframes • #4 opencode → anomalyco/opencode • #3 graphify → Graphify-Labs/graphify • #2 orca → stablyai/orca • #1 security-audit-skill → cloudflare/security-audit-skill 👍 Like, 💬 Comment, 🔔 Subscribe, ⭐️ Star the repos! #github #opensource #ai #coding #programming #trending #devtools #developer [ar] أفضل 10 مستودعات على GitHub لهذا الأسبوع | 18 أكتوبر – 24 أكتوبر | "إطار العمل" يتفوق على النموذج هذا الأسبوع، كانت أكبر المكاسب من نصيب البنية التحتية المحيطة بالوكيل، وليس النموذج نفسه: فقد تصدّرت مهارة التدقيق الأمني من كلاود فلير القائمة بحصولها على 12,680 نجمة جديدة، وثلاث من هذه النجوم العشر عبارة عن تعليمات وليست تطبيقات. ⏱️ الطوابع الزمنية 0:00 — مقدمة 0:46 — #10 مهارات أندريه كارباثي — ملف قواعد واحد لوكلاء البرمجة (223.6 ألف نجمة) 2:37 — #9 دليل إضافات كلود الرسمي — دليل إضافات أنثروبيك الرسمي (44.5 ألف نجمة) 4:36 — #8 روفلو — أداة شاملة لوكلاء البرمجة (79.2 ألف نجمة) 6:38 — #7 ذاكرة الذكاء الاصطناعي — ذاكرة مشتركة بين وكلاء البرمجة (13.4 ألف نجمة) 8:46 — #6 كومفي يو آي — محرك رسم بياني للعقد لصور وفيديوهات الذكاء الاصطناعي (142.8 ألف نجمة) 10:50 — #5 هايبر فريمز — كتابة HTML، عرض الفيديو (71.9 ألف نجمة) 13:13 — #4 أوبن كود — وكيل البرمجة مفتوح المصدر (221.4 ألف نجمة) 15:21 — #3 graphify — قاعدة بياناتك البرمجية كرسم بياني معرفي (134.8 ألف نجمة) 18:01 — #2 orca — مركز قيادة لأسطول من العملاء (105.4 ألف نجمة) 20:18 — #1 security-audit-skill — حوّل عميلك إلى مدقق أمني (46 ألف نجمة) 23:17 — ملخص واتجاهات 🔗 المستودعات • #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills • #9 claude-plugins-official → anthropics/claude-plugins-official • #8 ruflo → ruvnet/ruflo • #7 ai-memory → akitaonrails/ai-memory • #6 ComfyUI → Comfy-Org/ComfyUI • #5 hyperframes → heygen-com/hyperframes • #4 opencode → anomalyco/opencode • #3 graphify → Graphify-Labs/graphify • #2 orca → staablyai/orca • #1 security-audit-skill → cloudflare/security-audit-skill 👍 إعجاب، 💬 تعليق، 🔔 اشتراك، ⭐️ ضع نجمة على المستودعات! #github #opensource #ai #coding #programming #trending #devtools #developer [bn] এই সপ্তাহের শীর্ষ ১০ গিটহাব রিপো | ১৮ অক্টোবর – ২৪ অক্টোবর | মডেলকে হার মানালো হারনেস এই সপ্তাহে সবচেয়ে বেশি অগ্রগতি হয়েছে এজেন্টের চারপাশের হারনেসের, মডেলের নয়: ক্লাউডফ্লেয়ারের সিকিউরিটি অডিট স্কিল ১২,৬৮০টি নতুন স্টার পেয়ে প্রথম স্থান অধিকার করেছে, এবং এই দশটির মধ্যে তিনটিই অ্যাপ না হয়ে নির্দেশনা। ⏱️ টাইমস্ট্যাম্প ০:০০ — ভূমিকা ০:৪৬ — #১০ andrej-karpathy-skills — কোডিং এজেন্টদের জন্য একটি রুলস ফাইল (২২৩.৬ হাজার⭐️) ২:৩৭ — #৯ claude-plugins-official — অ্যানথ্রোপিকের অফিসিয়াল প্লাগইন ডিরেক্টরি (৪৪.৫ হাজার⭐️) ৪:৩৬ — #৮ ruflo — একটি এজেন্ট মেটা-হারনেস (৭৯.২ হাজার⭐️) ৬:৩৮ — #৭ ai-memory — কোডিং এজেন্টদের মধ্যে শেয়ার্ড মেমরি (১৩.৪ হাজার⭐️) ৮:৪৬ — #৬ ComfyUI — AI ইমেজ এবং ভিডিওর জন্য নোড-গ্রাফ ইঞ্জিন (১৪২.৮ হাজার⭐️) ১০:৫০ — #৫ hyperframes — HTML লেখা, ভিডিও রেন্ডার করা (৭১.৯ হাজার⭐️) ১৩:১৩ — #৪ opencode — ওপেন সোর্স কোডিং এজেন্ট (২২১.৪ হাজার ⭐️) ১৫:২১ — #৩ গ্রাফিফাই — আপনার কোডবেসকে একটি নলেজ গ্রাফ হিসেবে ব্যবহার করুন (১৩৪.৮ হাজার ⭐️) ১৮:০১ — #২ ওরকা — একদল এজেন্টের জন্য একটি কমান্ড সেন্টার (১০৫.৪ হাজার ⭐️) ২০:১৮ — #১ সিকিউরিটি-অডিট-স্কিল — আপনার এজেন্টকে একজন সিকিউরিটি অডিটরে পরিণত করুন (৪৬ হাজার ⭐️) ২৩:১৭ — সারসংক্ষেপ ও ট্রেন্ডস 🔗 রিপো • #১০ আন্দ্রেজ-কারপ্যাথি-স্কিলস → multica-ai/andrej-karpathy-skills • #৯ ক্লড-প্লাগইনস-অফিশিয়াল → anthropics/claude-plugins-official • #৮ রুফলো → ruvnet/ruflo • #৭ ai-memory → akitaonrails/ai-memory • #৬ ComfyUI → Comfy-Org/ComfyUI • #৫ hyperframes → heygen-com/hyperframes • #৪ opencode → anomalyco/opencode • #৩ graphify → Graphify-Labs/graphify • #২ orca → stablyai/orca • #১ security-audit-skill → cloudflare/security-audit-skill 👍 লাইক, 💬 কমেন্ট, 🔔 সাবস্ক্রাইব, ⭐️ রিপোজিটরিগুলোতে স্টার দিন! #github #opensource #ai #coding #programming #trending #devtools #developer [de-DE] Die 10 besten GitHub-Repos der Woche | 18. Okt. – 24. Okt. | Das Framework schlägt das Modell Diese Woche erzielten die Anwender die größten Zuwächse, nicht das Modell selbst: Cloudflares Sicherheitsaudit-Funktion belegte mit 12.680 neuen Sternen den ersten Platz, und drei der zehn besten Funktionen sind Anleitungen und keine Apps. ⏱️ ZEITSTEMPEL 0:00 — Intro 0:46 — #10 andrej-karpathy-skills — Eine Regeldatei für Coding-Agenten (223,6K⭐️) 2:37 — #9 claude-plugins-official — Das offizielle Plugin-Verzeichnis von Anthropic (44,5K⭐️) 4:36 — #8 ruflo — Ein Agenten-Meta-Harness (79,2K⭐️) 6:38 — #7 ai-memory — Gemeinsamer Speicher für Coding-Agenten (13,4K⭐️) 8:46 — #6 ComfyUI — Node-Graph-Engine für KI-Bilder und -Videos (142,8K⭐️) 10:50 — #5 hyperframes — HTML schreiben, Video rendern (71,9K⭐️) 13:13 — #4 Opencode – Der Open-Source-Codierungsagent (221,4K⭐️) 15:21 – #3 Graphify – Ihre Codebasis als Wissensgraph (134,8K⭐️) 18:01 – #2 Orca – Eine Kommandozentrale für eine Flotte von Agenten (105,4K⭐️) 20:18 – #1 Security-Audit-Skill – Machen Sie Ihren Agenten zum Sicherheitsauditor (46K⭐️) 23:17 – Zusammenfassung & Trends 🔗 REPOS • #10 Andrej-Karpathy-Skills → multica-ai/andrej-karpathy-skills • #9 Claude-Plugins-Official → anthropics/claude-plugins-official • #8 Ruflo → ruvnet/ruflo • #7 ai-memory → akitaonrails/ai-memory • #6 ComfyUI → Comfy-Org/ComfyUI • #5 hyperframes → heygen-com/hyperframes • #4 opencode → anomalyco/opencode • #3 graphify → Graphify-Labs/graphify • #2 orca → stablyai/orca • #1 security-audit-skill → cloudflare/security-audit-skill 👍 Gefällt mir, 💬 Kommentar, 🔔 Abonnieren, ⭐️ Repos mit Stern markieren! #github #opensource #ai #coding #programming #trending #devtools #developer [es-US] Los 10 mejores repositorios de GitHub esta semana | 18 al 24 de octubre | The Harness Beats the M... Esta semana, las mayores ganancias se concentraron en la plataforma que rodea al agente, no en el modelo: la habilidad de auditoría de seguridad de Cloudflare alcanzó el primer puesto con 12.680 nuevas estrellas, y tres de las diez mejores son instrucciones, no aplicaciones. Esta semana, el mayor avance se centró en la plataforma que rodea al agente, no en el modelo: la habilidad de auditoría de seguridad de Cloudflare se posicionó en el primer lugar con 12.680 nuevas estrellas, y tres de las diez mejores son instrucciones, no aplicaciones. ⏱️ MARCAS DE TIEMPO 0:00 — Introducción 0:46 — #10 andrej-karpathy-skills — Un archivo de reglas para agentes de codificación (223.6K⭐️) 2:37 — #9 claude-plugins-official — Directorio oficial de plugins de Anthropic (44.5K⭐️) 4:36 — #8 ruflo — Un meta-arnés para agentes (79.2K⭐️) 6:38 — #7 ai-memory — Memoria compartida entre agentes de codificación (13.4K⭐️) 8:46 — #6 ComfyUI — Motor de grafo de nodos para imágenes y vídeo con IA (142.8K⭐️) 10:50 — #5 hyperframes — Escribe HTML, renderiza vídeo (71.9K⭐️) 13:13 — #4 opencode — OpenCode Agente de codificación fuente (221.4K⭐️) 15:21 — #3 graphify — Tu base de código como un grafo de conocimiento (134.8K⭐️) 18:01 — #2 orca — Un centro de mando para una flota de agentes (105.4K⭐️) 20:18 — #1 security-audit-skill — Convierte a tu agente en un auditor de seguridad (46K⭐️) 23:17 — Resumen y tendencias 🔗 REPOSICIONES • #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills • #9 claude-plugins-official → anthropics/claude-plugins-official • #8 ruflo → ruvnet/ruflo • #7 ai-memory → akitaonrails/ai-memory • #6 ComfyUI → Comfy-Org/ComfyUI • #5 hyperframes → heygen-com/hyperframes • #4 opencode → anomalyco/opencode • #3 graphify → Graphify-Labs/graphify • #2 orca → stablyai/orca • #1 security-audit-skill → cloudflare/security-audit-skill 👍 Dale Me gusta, 💬 Comenta, 🔔 Suscríbete, ⭐️ ¡Marca los repositorios como favoritos! #github #opensource #ai #codificación #programación #tendencias #devtools #desarrollador [fr-FR] Top 10 des dépôts GitHub de la semaine | 18-24 oct. | Le harnais surpasse le modèle Cette semaine, ce sont les outils autour de l'agent, et non le modèle, qui ont enregistré les plus fortes progressions : la fonctionnalité d'audit de sécurité de Cloudflare s'est hissée à la première place avec 12 680 nouvelles étoiles, et trois des dix meilleures sont des instructions plutôt que des applications. ⏱️ HORODATAGE 0:00 — Introduction 0:46 — #10 andrej-karpathy-skills — Un fichier de règles pour la programmation d'agents (223,6K⭐️) 2:37 — #9 claude-plugins-official — Répertoire officiel des plugins d'Anthropic (44,5K⭐️) 4:36 — #8 ruflo — Un méta-harnais pour agents (79,2K⭐️) 6:38 — #7 ai-memory — Mémoire partagée entre agents de programmation (13,4K⭐️) 8:46 — #6 ComfyUI — Moteur de graphes de nœuds pour les images et vidéos IA (142,8K⭐️) 10:50 — #5 hyperframes — Écrire du HTML, générer de la vidéo (71,9K⭐️) 13:13 — #4 opencode — L'agent de codage open source (221,4K⭐️) 15:21 — #3 Graphify — Votre code source sous forme de graphe de connaissances (134,8K⭐️) 18:01 — #2 Orca — Un centre de commandement pour une flotte d'agents (105,4K⭐️) 20:18 — #1 Security-audit-skill — Transformez votre agent en auditeur de sécurité (46K⭐️) 23:17 — Récapitulatif et tendances 🔗 DÉPÔTS • #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills • #9 claude-plugins-official → anthropics/claude-plugins-official • #8 ruflo → ruvnet/ruflo • #7 ai-memory → akitaonrails/ai-memory • #6 ComfyUI → Comfy-Org/ComfyUI • #5 hyperframes → heygen-com/hyperframes • #4 opencode → anomalyco/opencode • #3 graphify → Graphify-Labs/graphify • #2 orca → stablyai/orca • #1 security-audit-skill → cloudflare/security-audit-skill 👍 Aimez, 💬 Commentez, 🔔 Abonnez-vous, ⭐️ Mettez les dépôts en favoris ! #github #opensource #ai #coding #programming #trending #devtools #developer [hi] इस सप्ताह के शीर्ष 10 GitHub रिपोज़ | 18 अक्टूबर - 24 अक्टूबर | हार्नेस मॉडल से बेहतर इस सप्ताह सबसे अधिक लाभ एजेंट के आसपास के हार्नेस को मिला, न कि मॉडल को: क्लाउडफ्लेयर के सुरक्षा ऑडिट कौशल ने 12,680 नए स्टार्स के साथ पहला स्थान प्राप्त किया, और इनमें से दस में से तीन निर्देश हैं, न कि ऐप्स। ⏱️ समय-सारणी 0:00 — परिचय 0:46 — #10 andrej-karpathy-skills — कोडिंग एजेंटों के लिए एक नियम फ़ाइल (223.6K⭐️) 2:37 — #9 claude-plugins-official — Anthropic की आधिकारिक प्लगइन निर्देशिका (44.5K⭐️) 4:36 — #8 ruflo — एक एजेंट मेटा-हार्नेस (79.2K⭐️) 6:38 — #7 ai-memory — कोडिंग एजेंटों के बीच साझा मेमोरी (13.4K⭐️) 8:46 — #6 ComfyUI — AI छवियों और वीडियो के लिए नोड-ग्राफ़ इंजन (142.8K⭐️) 10:50 — #5 hyperframes — HTML लिखें, वीडियो रेंडर करें (71.9K⭐️) 13:13 — #4 opencode — ओपन सोर्स कोडिंग एजेंट (221.4K⭐️) 15:21 — #3 ग्राफीफाई — आपका कोडबेस एक नॉलेज ग्राफ के रूप में (134.8K⭐️) 18:01 — #2 ओर्का — एजेंटों के बेड़े के लिए एक कमांड सेंटर (105.4K⭐️) 20:18 — #1 सिक्योरिटी ऑडिट स्किल — अपने एजेंट को सिक्योरिटी ऑडिटर में बदलें (46K⭐️) 23:17 — सारांश और रुझान 🔗 रिपॉजिटरी • #10 आंद्रेज कार्पेथी स्किल्स → multica-ai/andrej-karpathy-skills • #9 क्लाउड प्लगइन्स ऑफिशियल → anthropics/claude-plugins-official • #8 रुफ्लो → ruvnet/ruflo • #7 ai-memory → akitaonrails/ai-memory • #6 ComfyUI → Comfy-Org/ComfyUI • #5 hyperframes → heygen-com/hyperframes • #4 opencode → anomalyco/opencode • #3 graphify → Graphify-Labs/graphify • #2 orca → stablyai/orca • #1 security-audit-skill → cloudflare/security-audit-skill 👍 लाइक करें, 💬 टिप्पणी करें, 🔔 सब्सक्राइब करें, ⭐️ रिपॉजिटरी को स्टार दें! #github #opensource #ai #coding #programming #trending #devtools #developer [id] 10 Repositori GitHub Teratas Minggu Ini | 18 Okt – 24 Okt | The Harness Beats the Model Minggu ini, peningkatan terbesar terjadi pada sistem pendukung agen, bukan pada modelnya: keterampilan audit keamanan Cloudflare menduduki peringkat #1 dengan 12.680 bintang baru, dan tiga dari sepuluh bintang tersebut berupa instruksi, bukan aplikasi. ⏱️ CAP WAKTU 0:00 — Pendahuluan 0:46 — #10 andrej-karpathy-skills — Satu file aturan untuk agen pengkodean (223,6K⭐️) 2:37 — #9 claude-plugins-official — Direktori plugin resmi Anthropic (44,5K⭐️) 4:36 — #8 ruflo — Meta-harness agen (79,2K⭐️) 6:38 — #7 ai-memory — Memori bersama di seluruh agen pengkodean (13,4K⭐️) 8:46 — #6 ComfyUI — Mesin node-graph untuk gambar dan video AI (142,8K⭐️) 10:50 — #5 hyperframes — Tulis HTML, render video (71,9K⭐️) 13:13 — #4 opencode — Agen pengkodean sumber terbuka (221,4 ribu ⭐️) 15:21 — #3 graphify — Basis kode Anda sebagai grafik pengetahuan (134,8 ribu ⭐️) 18:01 — #2 orca — Pusat komando untuk armada agen (105,4 ribu ⭐️) 20:18 — #1 security-audit-skill — Ubah agen Anda menjadi auditor keamanan (46 ribu ⭐️) 23:17 — Rekap & Tren 🔗 REPOS • #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills • #9 claude-plugins-official → anthropics/claude-plugins-official • #8 ruflo → ruvnet/ruflo • #7 ai-memory → akitaonrails/ai-memory • #6 ComfyUI → Comfy-Org/ComfyUI • #5 hyperframes → heygen-com/hyperframes • #4 opencode → anomalyco/opencode • #3 graphify → Graphify-Labs/graphify • #2 orca → stablyai/orca • #1 security-audit-skill → cloudflare/security-audit-skill 👍 Suka, 💬 Komentar, 🔔 Berlangganan, ⭐️ Beri bintang pada repositori! #github #opensource #ai #coding #programming #trending #devtools #developer [it] I 10 migliori repository GitHub di questa settimana | 18 ott – 24 ott | L'infrastruttura batte il... Questa settimana i maggiori progressi sono andati all'infrastruttura che circonda l'agente, non al modello: la skill di audit di sicurezza di Cloudflare si è aggiudicata il primo posto con 12.680 nuove stelle, e tre delle prime dieci sono istruzioni anziché applicazioni. ⏱️ INDICE DEI CONTENUTI 0:00 — Introduzione 0:46 — #10 andrej-karpathy-skills — Un file di regole per agenti di codifica (223.600⭐️) 2:37 — #9 claude-plugins-official — La directory ufficiale dei plugin di Anthropic (44.500⭐️) 4:36 — #8 ruflo — Un meta-sistema di controllo per agenti (79.200⭐️) 6:38 — #7 ai-memory — Memoria condivisa tra agenti di codifica (13.400⭐️) 8:46 — #6 ComfyUI — Motore a grafo di nodi per immagini e video AI (142.800⭐️) 10:50 — #5 hyperframes — Scrivi HTML, renderizza video (71.900⭐️) 13:13 — #4 opencode — Il progetto open source agente di codifica (221.400⭐️) 15:21 — #3 graphify — Il tuo codice sorgente come grafo della conoscenza (134.800⭐️) 18:01 — #2 orca — Un centro di comando per una flotta di agenti (105.400⭐️) 20:18 — #1 security-audit-skill — Trasforma il tuo agente in un revisore della sicurezza (46.000⭐️) 23:17 — Riepilogo e tendenze 🔗 REPOS • #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills • #9 claude-plugins-official → anthropics/claude-plugins-official • #8 ruflo → ruvnet/ruflo • #7 ai-memory → akitaonrails/ai-memory • #6 ComfyUI → Comfy-Org/ComfyUI • #5 hyperframes → heygen-com/hyperframes • #4 opencode → anomalyco/opencode • #3 graphify → Graphify-Labs/graphify • #2 orca → stablyai/orca • #1 security-audit-skill → cloudflare/security-audit-skill 👍 Metti Mi piace, 💬 Commenta, 🔔 Iscriviti, ⭐️ Aggiungi i repository ai preferiti! #github #opensource #ai #coding #programming #trending #devtools #developer [iw] 10 מאגרי ה-GitHub המובילים השבוע | 18 באוקטובר – 24 באוקטובר | המעטפת מנצחת את המודל השבוע, הרווחים הגדולים ביותר הלכו לרתמה סביב הסוכן, לא למודל: מיומנות ביקורת האבטחה של Cloudflare תפסה את המקום הראשון עם 12,680 כוכבים חדשים, ושלושה מתוך עשרתם הם הוראות ולא אפליקציות. ⏱️ חותמות זמן 0:00 — מבוא 0:46 — #10 andrej-karpathy-skills — קובץ כללים אחד עבור סוכני קידוד (223.6K⭐️) 2:37 — #9 claude-plugins-official — ספריית התוספים הרשמית של Anthropic (44.5K⭐️) 4:36 — #8 ruflo — רתמת מטא של סוכן (79.2K⭐️) 6:38 — #7 ai-memory — זיכרון משותף בין סוכני קידוד (13.4K⭐️) 8:46 — #6 ComfyUI — מנוע Node-graph עבור תמונות ווידאו של בינה מלאכותית (142.8K⭐️) 10:50 — #5 hyperframes — כתיבת HTML, עיבוד וידאו (71.9K⭐️) 13:13 — #4 opencode — סוכן קידוד בקוד פתוח (221.4K⭐️) 15:21 — #3 graphify — בסיס הקוד שלך כגרף ידע (134.8K⭐️) 18:01 — #2 orca — מרכז פיקוד עבור צי סוכנים (105.4K⭐️) 20:18 — #1 security-audit-skill — הפוך את הסוכן שלך למבקר אבטחה (46K⭐️) 23:17 — סיכום ומגמות 🔗 REPOS • #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills • #9 claude-plugins-official → anthropics/claude-plugins-official • #8 ruflo → ruvnet/ruflo • #7 ai-memory → akitaonrails/ai-memory • #6 ComfyUI → Comfy-Org/ComfyUI • #5 היפר-פריימים → heygen-com/hyperframes • #4 קוד פתוח → anomalyco/opencode • #3 גרפיפי → Graphify-Labs/graphify • #2 אורקה → stablyai/orca • #1 סקיל ביקורת-על-ביטחון → cloudflare/security-audit-skill 👍 לייק, 💬 הגיבו, 🔔 הירשמו, ⭐️ סמנו בכוכב את המאגרים! #github #קודפתוח #בינה מלאכותית #קידוד #תכנות #טרנדי #כליפיתוח #מפתח [ja] 今週のGitHub注目リポジトリTOP10 | 10月18日～10月24日 | モデルを凌駕するハーネス 今週、最も大きな伸びを見せたのはエージェントのモデルではなく、その周辺技術でした。Cloudflareのセキュリティ監査スキルが12,680個の新たなスターを獲得し、1位に輝きました。上位10件のうち3件はアプリではなく、手順書でした。 ⏱️ タイムスタンプ 0:00 — はじめに 0:46 — #10 andrej-karpathy-skills — コーディングエージェントのためのルールファイル (223.6K⭐️) 2:37 — #9 claude-plugins-official — Anthropic の公式プラグインディレクトリ (44.5K⭐️) 4:36 — #8 ruflo — エージェントメタハーネス (79.2K⭐️) 6:38 — #7 ai-memory — コーディングエージェント間で共有されるメモリ (13.4K⭐️) 8:46 — #6 ComfyUI — AI 画像と動画のためのノードグラフエンジン (142.8K⭐️) 10:50 — #5 hyperframes — HTML の書き込み、動画のレンダリング (71.9K⭐️) 13:13 — #4 opencode — オープンソースのコーディングエージェント (221.4K⭐️) 15:21 — #3 graphify — コードベースをナレッジグラフとして活用 (134.8K⭐️) 18:01 — #2 orca — エージェント群のためのコマンドセンター (105.4K⭐️) 20:18 — #1 security-audit-skill — エージェントをセキュリティ監査ツールに変える (46K⭐️) 23:17 — まとめとトレンド 🔗 リポジトリ • #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills • #9 claude-plugins-official → anthropics/claude-plugins-official • #8 ruflo → ruvnet/ruflo • #7 ai-memory → akitaonrails/ai-memory • #6 ComfyUI → Comfy-Org/ComfyUI • #5 ハイパーフレーム → heygen-com/hyperframes • #4 オープンコード → anomalyco/opencode • #3 グラフィファイ → Graphify-Labs/graphify • #2 オルカ → stablyai/orca • #1 セキュリティ監査スキル → cloudflare/security-audit-skill 👍 いいね、💬 コメント、🔔 チャンネル登録、⭐️ スターをリポジトリに追加！ #github #opensource #ai #coding #programming #trending #devtools #developer [ko] 이번 주 GitHub Top 10 저장소 | 10월 18일 – 10월 24일 | 모델을 능가하는 활용 도구 이번 주 가장 큰 성과는 모델이 아닌 에이전트 관련 도구에서 나타났습니다. 클라우드플레어의 보안 감사 스킬이 12,680개의 새로운 별점을 얻으며 1위를 차지했고, 상위 10개 중 3개는 앱이 아닌 사용법 안내였습니다. ⏱️ 타임스탬프 0:00 — 소개 0:46 — #10 andrej-karpathy-skills — 코딩 에이전트를 위한 하나의 규칙 파일 (223.6K⭐️) 2:37 — #9 claude-plugins-official — Anthropic의 공식 플러그인 디렉토리 (44.5K⭐️) 4:36 — #8 ruflo — 에이전트 메타 하네스 (79.2K⭐️) 6:38 — #7 ai-memory — 코딩 에이전트 간 공유 메모리 (13.4K⭐️) 8:46 — #6 ComfyUI — AI 이미지 및 비디오용 노드 그래프 엔진 (142.8K⭐️) 10:50 — #5 hyperframes — HTML 작성 및 비디오 렌더링 (71.9K⭐️) 13:13 — #4 opencode — 오픈 소스 코딩 에이전트 (221.4K⭐️) 15:21 — #3 Graphify — 코드베이스를 지식 그래프로 (134.8K⭐️) 18:01 — #2 Orca — 에이전트 함대를 위한 명령 센터 (105.4K⭐️) 20:18 — #1 Security-Audit-Skill — 에이전트를 보안 감사자로 전환 (46K⭐️) 23:17 — 요약 및 트렌드 🔗 저장소 • #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills • #9 claude-plugins-official → anthropics/claude-plugins-official • #8 ruflo → ruvnet/ruflo • #7 ai-memory → akitaonrails/ai-memory • #6 ComfyUI → Comfy-Org/ComfyUI • #5 hyperframes → heygen-com/hyperframes • #4 opencode → anomalyco/opencode • #3 graphify → Graphify-Labs/graphify • #2 orca → stablyai/orca • #1 security-audit-skill → cloudflare/security-audit-skill 👍 좋아요, 💬 댓글, 🔔 구독, ⭐️ 저장소에 별표 표시! #github #opensource #ai #coding #programming #trending #devtools #developer [ml] ഈ ആഴ്ചയിലെ മികച്ച 10 GitHub റിപ്പോസിറ്ററികൾ | ഒക്ടോബർ 18 – ഒക്ടോബർ 24 | മോഡലിനേക്കാൾ കേമൻ ഹാർനെസ് ഈ ആഴ്ച ഏറ്റവും വലിയ നേട്ടം മോഡലിനെയല്ല, ഏജന്റിനെ ചുറ്റിപ്പറ്റിയുള്ളതാണ്: 12,680 പുതിയ നക്ഷത്രങ്ങളുമായി ക്ലൗഡ്ഫ്ലെയറിന്റെ സുരക്ഷാ ഓഡിറ്റ് വൈദഗ്ദ്ധ്യം ഒന്നാം സ്ഥാനത്തെത്തി, പത്തിൽ മൂന്നെണ്ണം ആപ്പുകളേക്കാൾ നിർദ്ദേശങ്ങളാണ്. ⏱️ TIMESTAMPS 0:00 — ആമുഖം 0:46 — #10 andrej-karpathy-skills — കോഡിംഗ് ഏജന്റുകൾക്കുള്ള ഒരു റൂൾ ഫയൽ (223.6K⭐️) 2:37 — #9 claude-plugins-official — ആന്ത്രോപിക്കിന്റെ ഔദ്യോഗിക പ്ലഗിൻ ഡയറക്ടറി (44.5K⭐️) 4:36 — #8 ruflo — ഒരു ഏജന്റ് മെറ്റാ-ഹാർനെസ് (79.2K⭐️) 6:38 — #7 ai-memory — കോഡിംഗ് ഏജന്റുകളിലുടനീളം പങ്കിട്ട മെമ്മറി (13.4K⭐️) 8:46 — #6 ComfyUI — AI ഇമേജുകൾക്കും വീഡിയോയ്ക്കുമുള്ള നോഡ്-ഗ്രാഫ് എഞ്ചിൻ (142.8K⭐️) 10:50 — #5 ഹൈപ്പർഫ്രെയിമുകൾ — HTML എഴുതുക, വീഡിയോ റെൻഡർ ചെയ്യുക (71.9K⭐️) 13:13 — #4 ഓപ്പൺകോഡ് — ഓപ്പൺ സോഴ്സ് കോഡിംഗ് ഏജന്റ് (221.4K⭐️) 15:21 — #3 ഗ്രാഫിഫൈ — നിങ്ങളുടെ കോഡ്ബേസ് ഒരു നോളജ് ഗ്രാഫ് ആയി (134.8K⭐️) 18:01 — #2 ഓർക്ക — ഏജന്റുമാരുടെ ഒരു കൂട്ടത്തിനായുള്ള ഒരു കമാൻഡ് സെന്റർ (105.4K⭐️) 20:18 — #1 സുരക്ഷാ-ഓഡിറ്റ്-സ്കിൽ — നിങ്ങളുടെ ഏജന്റിനെ ഒരു സുരക്ഷാ ഓഡിറ്ററാക്കി മാറ്റുക (46K⭐️) 23:17 — റീക്യാപ്പ് & ട്രെൻഡുകൾ 🔗 REPOS • #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills • #9 claude-plugins-official → anthropics/claude-plugins-official • #8 ruflo → ruvnet/ruflo • #7 ai-memory → akitaonrails/ai-memory • #6 ComfyUI → Comfy-Org/ComfyUI • #5 ഹൈപ്പർഫ്രെയിമുകൾ → heygen-com/hyperframes • #4 ഓപ്പൺകോഡ് → anomalyco/opencode • #3 ഗ്രാഫിഫൈ → Graphify-Labs/graphify • #2 ഓർക്ക → stablyai/orca • #1 സെക്യൂരിറ്റി-ഓഡിറ്റ്-സ്കിൽ → cloudflare/security-audit-%E0%B4%B8%E0%B5%8D%E0%B4%95%E0%B4%BF%E0%B5%BD 👍 ലൈക്ക് ചെയ്യുക, 💬 കമന്റ് ചെയ്യുക, 🔔 സബ്സ്ക്രൈബ് ചെയ്യുക, ⭐️ റിപ്പോകളിൽ സ്റ്റാർ ചെയ്യുക! #github #opensource #ai #coding #programming #trending #devtools #developer [nl-NL] Top 10 GitHub-repo's van deze week | 18 okt – 24 okt | Het harnas verslaat het model Deze week ging de grootste winst naar de hardware rondom de agent, niet naar het model zelf: Cloudflare's beveiligingsauditvaardigheid behaalde de eerste plaats met 12.680 nieuwe sterren, waarvan drie van de tien instructies zijn in plaats van apps. ⏱️ TIJDSTEMPELS 0:00 — Intro 0:46 — #10 andrej-karpathy-skills — Eén regelsbestand voor codeeragenten (223,6K⭐️) 2:37 — #9 claude-plugins-official — De officiële plugin-directory van Anthropic (44,5K⭐️) 4:36 — #8 ruflo — Een agent-meta-harness (79,2K⭐️) 6:38 — #7 ai-memory — Gedeeld geheugen voor codeeragenten (13,4K⭐️) 8:46 — #6 ComfyUI — Node-graph engine voor AI-afbeeldingen en -video (142,8K⭐️) 10:50 — #5 hyperframes — Schrijf HTML, render video (71,9K⭐️) 13:13 — #4 opencode — De open broncodeagent (221,4K⭐️) 15:21 — #3 graphify — Je codebase als kennisgrafiek (134,8K⭐️) 18:01 — #2 orca — Een commandocentrum voor een vloot agenten (105,4K⭐️) 20:18 — #1 security-audit-skill — Verander je agent in een beveiligingsauditor (46K⭐️) 23:17 — Samenvatting & Trends 🔗 REPOS • #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills • #9 claude-plugins-official → anthropics/claude-plugins-official • #8 ruflo → ruvnet/ruflo • #7 ai-memory → akitaonrails/ai-memory • #6 ComfyUI → Comfy-Org/ComfyUI • #5 hyperframes → heygen-com/hyperframes • #4 opencode → anomalyco/opencode • #3 graphify → Graphify-Labs/graphify • #2 orca → stablyai/orca • #1 security-audit-skill → cloudflare/security-audit-skill 👍 Vind ik leuk, 💬 Reageer, 🔔 Abonneer, ⭐️ Geef de repositories een ster! #github #opensource #ai #coding #programming #trending #devtools #developer [pa] ਇਸ ਹਫ਼ਤੇ ਦੀਆਂ ਚੋਟੀ ਦੀਆਂ 10 GitHub ਰਿਪੋਜ਼ | 18 ਅਕਤੂਬਰ – 24 ਅਕਤੂਬਰ | ਮਾਡਲ ਨਾਲੋਂ ਹਾਰਨੇਸ ਬਿਹਤਰ ਇਸ ਹਫ਼ਤੇ ਸਭ ਤੋਂ ਵੱਧ ਲਾਭ ਏਜੰਟ ਦੇ ਆਲੇ-ਦੁਆਲੇ ਦੇ ਹਾਰਨੈੱਸ ਨੂੰ ਹੋਇਆ, ਮਾਡਲ ਨੂੰ ਨਹੀਂ: ਕਲਾਉਡਫਲੇਅਰ ਦੇ ਸੁਰੱਖਿਆ ਆਡਿਟ ਹੁਨਰ ਨੇ 12,680 ਨਵੇਂ ਸਿਤਾਰਿਆਂ ਨਾਲ #1 ਸਥਾਨ ਪ੍ਰਾਪਤ ਕੀਤਾ, ਅਤੇ ਦਸ ਵਿੱਚੋਂ ਤਿੰਨ ਐਪਸ ਦੀ ਬਜਾਏ ਨਿਰਦੇਸ਼ ਹਨ। ⏱️ ਟਾਈਮਸਟੈਂਪਸ 0:00 — ਜਾਣ-ਪਛਾਣ 0:46 — #10 andrej-karpathy-skills — ਕੋਡਿੰਗ ਏਜੰਟਾਂ ਲਈ ਇੱਕ ਨਿਯਮ ਫਾਈਲ (223.6K⭐️) 2:37 — #9 claude-plugins-official — Anthropic ਦੀ ਅਧਿਕਾਰਤ ਪਲੱਗਇਨ ਡਾਇਰੈਕਟਰੀ (44.5K⭐️) 4:36 — #8 ruflo — ਇੱਕ ਏਜੰਟ ਮੈਟਾ-ਹਾਰਨੈੱਸ (79.2K⭐️) 6:38 — #7 ai-ਮੈਮੋਰੀ — ਕੋਡਿੰਗ ਏਜੰਟਾਂ ਵਿੱਚ ਸਾਂਝੀ ਮੈਮੋਰੀ (13.4K⭐️) 8:46 — #6 ComfyUI — AI ਚਿੱਤਰਾਂ ਅਤੇ ਵੀਡੀਓ ਲਈ ਨੋਡ-ਗ੍ਰਾਫ ਇੰਜਣ (142.8K⭐️) 10:50 — #5 ਹਾਈਪਰਫ੍ਰੇਮ — HTML ਲਿਖੋ, ਵੀਡੀਓ ਰੈਂਡਰ ਕਰੋ (71.9K⭐️) 13:13 — #4 ਓਪਨਕੋਡ — ਓਪਨ ਸੋਰਸ ਕੋਡਿੰਗ ਏਜੰਟ (221.4K⭐️) 15:21 — #3 ਗ੍ਰਾਫੀਫਾਈ — ਤੁਹਾਡਾ ਕੋਡਬੇਸ ਇੱਕ ਗਿਆਨ ਗ੍ਰਾਫ਼ ਵਜੋਂ (134.8K⭐️) 18:01 — #2 ਓਰਕਾ — ਏਜੰਟਾਂ ਦੇ ਫਲੀਟ ਲਈ ਇੱਕ ਕਮਾਂਡ ਸੈਂਟਰ (105.4K⭐️) 20:18 — #1 ਸੁਰੱਖਿਆ-ਆਡਿਟ-ਹੁਨਰ — ਆਪਣੇ ਏਜੰਟ ਨੂੰ ਸੁਰੱਖਿਆ ਆਡੀਟਰ ਵਿੱਚ ਬਦਲੋ (46K⭐️) 23:17 — ਸੰਖੇਪ ਅਤੇ ਰੁਝਾਨ 🔗 REPOS • #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills • #9 claude-plugins-official → anthropics/claude-plugins-official • #8 ruflo → ruvnet/ruflo • #7 ai-memory → akitaonrails/ai-memory • #6 ComfyUI → Comfy-Org/ComfyUI • #5 ਹਾਈਪਰਫ੍ਰੇਮ → heygen-com/hyperframes • #4 ਓਪਨਕੋਡ → anomalyco/opencode • #3 graphify → Graphify-Labs/graphify • #2 orca → stablyai/orca • #1 security-audit-skill → cloudflare/security-audit-skill 👍 ਪਸੰਦ ਕਰੋ, 💬 ਟਿੱਪਣੀ ਕਰੋ, 🔔 ਗਾਹਕ ਬਣੋ, ⭐️ ਰਿਪੋਜ਼ ਨੂੰ ਸਟਾਰ ਕਰੋ! #github #opensource #ai #ਕੋਡਿੰਗ #ਪ੍ਰੋਗਰਾਮਿੰਗ #ਟ੍ਰੇਂਡਿੰਗ #devtools #developer [pl] 10 najlepszych repozytoriów GitHub w tym tygodniu | 18–24 października | Oprzyrządowanie lepsze n... W tym tygodniu największe zyski odnotowały uprząż wokół agenta, a nie sam model: umiejętność audytu bezpieczeństwa Cloudflare zajęła pierwsze miejsce z 12 680 nowymi gwiazdkami, a trzy z dziesięciu to instrukcje, a nie aplikacje. ⏱️ ZNACZNIKI CZASU 0:00 — Wprowadzenie 0:46 — #10 andrej-karpathy-skills — Jeden plik reguł dla agentów kodujących (223,6 tys.⭐️) 2:37 — #9 claude-plugins-official — Oficjalny katalog wtyczek Anthropic (44,5 tys.⭐️) 4:36 — #8 ruflo — Meta-uprząż dla agentów kodujących (79,2 tys.⭐️) 6:38 — #7 ai-memory — Pamięć współdzielona przez agentów kodujących (13,4 tys.⭐️) 8:46 — #6 ComfyUI — Silnik Node-graph dla obrazów i wideo AI (142,8 tys.⭐️) 10:50 — #5 hyperframes — Pisanie HTML, renderowanie wideo (71,9 tys.⭐️) 13:13 — #4 opencode — Agent kodujący open source (221,4 tys.⭐️) 15:21 — #3 graphify — Twoja baza kodu jako graf wiedzy (134,8 tys.⭐️) 18:01 — #2 orca — Centrum dowodzenia dla floty agentów (105,4 tys.⭐️) 20:18 — #1 security-audit-skill — Zmień swojego agenta w audytora bezpieczeństwa (46 tys.⭐️) 23:17 — Podsumowanie i trendy 🔗 REPOZYTORIA • #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills • #9 claude-plugins-official → anthropics/claude-plugins-official • #8 ruflo → ruvnet/ruflo • #7 ai-memory → akitaonrails/ai-memory • #6 ComfyUI → Comfy-Org/ComfyUI • #5 hyperframes → heygen-com/hyperframes • #4 opencode → anomalyco/opencode • #3 graphify → Graphify-Labs/graphify • #2 orca → stablyai/orca • #1 security-audit-skill → cloudflare/security-audit-skill 👍 Polub, 💬 Skomentuj, 🔔 Subskrybuj, ⭐️ Oznacz repozytoria gwiazdką! #github #opensource #ai #kodowanie #programowanie #trendy #devtools #deweloper [pt-BR] Top 10 Repos do GitHub Esta Semana | 18 de out – 24 de out | A Estrutura Supera o Modelo Nesta semana, os maiores ganhos foram para a estrutura em torno do agente, não para o modelo: a skill de auditoria de segurança da Cloudflare conquistou o primeiro lugar com 12.680 novas estrelas, e três dessas dez estrelas são para instruções, não para aplicativos. ⏱️ MARCAÇÕES DE TEMPO 0:00 — Introdução 0:46 — #10 andrej-karpathy-skills — Um arquivo de regras para agentes de codificação (223,6 mil ⭐️) 2:37 — #9 claude-plugins-official — Diretório oficial de plugins do Anthropic (44,5 mil ⭐️) 4:36 — #8 ruflo — Um meta-arnês para agentes (79,2 mil ⭐️) 6:38 — #7 ai-memory — Memória compartilhada entre agentes de codificação (13,4 mil ⭐️) 8:46 — #6 ComfyUI — Mecanismo de grafo de nós para imagens e vídeos com IA (142,8 mil ⭐️) 10:50 — #5 hyperframes — Escreva HTML, renderize vídeo (71,9 mil ⭐️) 13:13 — #4 opencode — O código aberto Agente de codificação (221,4 mil estrelas) 15:21 — #3 graphify — Sua base de código como um grafo de conhecimento (134,8 mil estrelas) 18:01 — #2 orca — Um centro de comando para uma frota de agentes (105,4 mil estrelas) 20:18 — #1 security-audit-skill — Transforme seu agente em um auditor de segurança (46 mil estrelas) 23:17 — Resumo e Tendências 🔗 REPOS • #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills • #9 claude-plugins-official → anthropics/claude-plugins-official • #8 ruflo → ruvnet/ruflo • #7 ai-memory → akitaonrails/ai-memory • #6 ComfyUI → Comfy-Org/ComfyUI • #5 hyperframes → heygen-com/hyperframes • #4 opencode → anomalyco/opencode • #3 graphify → Graphify-Labs/graphify • #2 orca → stablyai/orca • #1 security-audit-skill → cloudflare/security-audit-skill 👍 Curtir, 💬 Comentar, 🔔 Inscrever-se, ⭐️ Favoritar os repositórios! #github #opensource #ai #codificação #programação #tendências #devtools #developer [ru] Топ-10 репозиториев GitHub за неделю | 18 окт – 24 окт | Оболочка важнее модели На этой неделе наибольший прирост достался инструменту, используемому в агенте, а не модели: навык аудита безопасности Cloudflare занял первое место с 12 680 новыми звездами, и три из десяти из них — это инструкции, а не приложения. ⏱️ ВРЕМЕННЫЕ МЕТКИ 0:00 — Вступление 0:46 — #10 andrej-karpathy-skills — Один файл правил для агентов кодирования (223,6 тыс.⭐️) 2:37 — #9 claude-plugins-official — Официальный каталог плагинов Anthropic (44,5 тыс.⭐️) 4:36 — #8 ruflo — Мета-инструмент для агентов (79,2 тыс.⭐️) 6:38 — #7 ai-memory — Общая память для агентов кодирования (13,4 тыс.⭐️) 8:46 — #6 ComfyUI — Графовый движок для изображений и видео ИИ (142,8 тыс.⭐️) 10:50 — #5 hyperframes — Написание HTML, рендеринг видео (71,9 тыс.⭐️) 13:13 — #4 opencode — Агент для разработки кода с открытым исходным кодом (221,4 тыс. ⭐️) 15:21 — #3 graphify — Ваша кодовая база как граф знаний (134,8 тыс. ⭐️) 18:01 — #2 orca — Командный центр для флота агентов (105,4 тыс. ⭐️) 20:18 — #1 security-audit-skill — Превратите своего агента в аудитора безопасности (46 тыс. ⭐️) 23:17 — Краткий обзор и тренды 🔗 РЕПОЗИЦИИ • #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills • #9 claude-plugins-official → anthropics/claude-plugins-official • #8 ruflo → ruvnet/ruflo • #7 ai-memory → akitaonrails/ai-memory • #6 ComfyUI → Comfy-Org/ComfyUI • #5 hyperframes → heygen-com/hyperframes • #4 opencode → anomalyco/opencode • #3 graphify → Graphify-Labs/graphify • #2 orca → stablyai/orca • #1 security-audit-skill → cloudflare/security-audit-skill 👍 Лайк, 💬 Комментарий, 🔔 Подписка, ⭐️ Отметьте репозитории звездочкой! #github #opensource #ai #coding #programming #trending #devtools #developer [ta] இந்த வாரத்தின் டாப் 10 GitHub களஞ்சியங்கள் | அக் 18 – அக் 24 | மாடலை விட ஹார்னஸ் சிறந்தது இந்த வாரம், மாடலை விட ஏஜென்ட்டைச் சுற்றியுள்ள கட்டமைப்புக்கே மிகப்பெரிய ஆதாயங்கள் கிடைத்தன: கிளவுட்ஃபிளேரின் பாதுகாப்புத் தணிக்கைத் திறன் 12,680 புதிய நட்சத்திரங்களுடன் முதலிடத்தைப் பிடித்தது, மேலும் பத்தில் மூன்று செயலிகள் அல்ல, மாறாக அறிவுறுத்தல்களாகும். ⏱️ நேரக்குறிப்புகள் 0:00 — அறிமுகம் 0:46 — #10 andrej-karpathy-skills — கோடிங் ஏஜென்ட்களுக்கான ஒரே விதிக் கோப்பு (223.6K⭐️) 2:37 — #9 claude-plugins-official — ஆந்த்ரோபிக்கின் அதிகாரப்பூர்வ பிளகின் கோப்பகம் (44.5K⭐️) 4:36 — #8 ruflo — ஒரு ஏஜென்ட் மெட்டா-ஹார்னஸ் (79.2K⭐️) 6:38 — #7 ai-memory — கோடிங் ஏஜென்ட்கள் முழுவதும் பகிரப்பட்ட நினைவகம் (13.4K⭐️) 8:46 — #6 ComfyUI — AI படங்கள் மற்றும் வீடியோவிற்கான நோட்-கிராஃப் எஞ்சின் (142.8K⭐️) 10:50 — #5 hyperframes — HTML எழுது, வீடியோவை ரெண்டர் செய் (71.9K⭐️) 13:13 — #4 opencode — திறந்த மூல குறியீட்டு முகவர் (221.4K⭐️) 15:21 — #3 கிராஃபிஃபை — உங்கள் குறியீட்டுத் தொகுப்பை ஒரு அறிவு வரைபடமாக மாற்றுதல் (134.8K⭐️) 18:01 — #2 ஓர்கா — முகவர்களின் குழுவிற்கான ஒரு கட்டளை மையம் (105.4K⭐️) 20:18 — #1 செக்யூரிட்டி-ஆடிட்-ஸ்கில் — உங்கள் முகவரை ஒரு பாதுகாப்பு தணிக்கையாளராக மாற்றுங்கள் (46K⭐️) 23:17 — மீள்பார்வை & போக்குகள் 🔗 ரெப்போக்கள் • #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills • #9 claude-plugins-official → anthropics/claude-plugins-official • #8 ரூஃப்லோ → ruvnet/ruflo • #7 ai-memory → akitaonrails/ai-memory • #6 ComfyUI → Comfy-Org/ComfyUI • #5 hyperframes → heygen-com/hyperframes • #4 opencode → anomalyco/opencode • #3 graphify → Graphify-Labs/graphify • #2 orca → stablyai/orca • #1 security-audit-skill → cloudflare/security-audit-skill 👍 லைக், 💬 கமெண்ட், 🔔 சப்ஸ்கிரைப், ⭐️ ரெப்போக்களுக்கு ஸ்டார் கொடுங்கள்! #github #opensource #ai #coding #programming #trending #devtools #developer [te] ఈ వారం టాప్ 10 GitHub రిపోలు | అక్టోబర్ 18 – అక్టోబర్ 24 | మోడల్ కంటే హార్నెస్దే పైచేయి ఈ వారం అత్యధిక ప్రయోజనాలు మోడల్కు కాకుండా, ఏజెంట్ చుట్టూ ఉన్న హార్నెస్కు దక్కాయి: క్లౌడ్ఫ్లేర్ సెక్యూరిటీ ఆడిట్ స్కిల్ 12,680 కొత్త స్టార్లతో మొదటి స్థానాన్ని దక్కించుకుంది, మరియు ఆ పదింటిలో మూడు యాప్లకు బదులుగా సూచనలే ఉన్నాయి. ⏱️ టైమ్స్టాంప్లు 0:00 — పరిచయం 0:46 — #10 andrej-karpathy-skills — కోడింగ్ ఏజెంట్ల కోసం ఒక రూల్స్ ఫైల్ (223.6K⭐️) 2:37 — #9 claude-plugins-official — ఆంత్రోపిక్ యొక్క అధికారిక ప్లగిన్ డైరెక్టరీ (44.5K⭐️) 4:36 — #8 ruflo — ఒక ఏజెంట్ మెటా-హార్నెస్ (79.2K⭐️) 6:38 — #7 ai-memory — కోడింగ్ ఏజెంట్ల అంతటా షేర్డ్ మెమరీ (13.4K⭐️) 8:46 — #6 ComfyUI — AI చిత్రాలు మరియు వీడియో కోసం నోడ్-గ్రాఫ్ ఇంజిన్ (142.8K⭐️) 10:50 — #5 hyperframes — HTML రాయండి, వీడియోను రెండర్ చేయండి (71.9K⭐️) 13:13 — #4 ఓపెన్కోడ్ — ఓపెన్ సోర్స్ కోడింగ్ ఏజెంట్ (221.4K⭐️) 15:21 — #3 గ్రాఫిఫై — మీ కోడ్బేస్ను ఒక నాలెడ్జ్ గ్రాఫ్గా మార్చడం (134.8K⭐️) 18:01 — #2 ఓర్కా — ఏజెంట్ల సముదాయానికి ఒక కమాండ్ సెంటర్ (105.4K⭐️) 20:18 — #1 సెక్యూరిటీ-ఆడిట్-స్కిల్ — మీ ఏజెంట్ను ఒక సెక్యూరిటీ ఆడిటర్గా మార్చడం (46K⭐️) 23:17 — రీక్యాప్ & ట్రెండ్స్ 🔗 REPOS • #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills • #9 claude-plugins-official → anthropics/claude-plugins-official • #8 ruflo → ruvnet/ruflo • #7 ai-memory → akitaonrails/ai-memory • #6 ComfyUI → Comfy-Org/ComfyUI • #5 hyperframes → heygen-com/hyperframes • #4 opencode → anomalyco/opencode • #3 graphify → Graphify-Labs/graphify • #2 orca → stablyai/orca • #1 security-audit-skill → cloudflare/security-audit-skill 👍 లైక్ చేయండి, 💬 కామెంట్ చేయండి, 🔔 సబ్స్క్రైబ్ చేయండి, ⭐️ రిపోలకు స్టార్ ఇవ్వండి! #github #opensource #ai #coding #programming #trending #devtools #developer [uk] Топ-10 репозиторіїв GitHub цього тижня | 18 жовтня – 24 жовтня | Обв'язка перемагає модель Цього тижня найбільших успіхів досягла система, що працює навколо агента, а не модель: навичка аудиту безпеки Cloudflare посіла перше місце з 12 680 новими зірками, і три з десяти – це інструкції, а не програми. ⏱️ ЧАСОВІ ПОМІТКИ 0:00 — Вступ 0:46 — #10 andrej-karpathy-skills — Один файл правил для агентів кодування (223.6 тис.⭐️) 2:37 — #9 claude-plugins-official — Офіційний каталог плагінів Anthropic (44.5 тис.⭐️) 4:36 — #8 ruflo — Мета-обладнання агента (79.2 тис.⭐️) 6:38 — #7 ai-memory — Спільна пам'ять між агентами кодування (13.4 тис.⭐️) 8:46 — #6 ComfyUI — Двигун графів вузлів для зображень та відео на основі штучного інтелекту (142.8 тис.⭐️) 10:50 — #5 гіперфрейми — Написання HTML, рендеринг відео (71.9 тис.⭐️) 13:13 — #4 opencode — Агент кодування з відкритим вихідним кодом (221.4 тис.⭐️) 15:21 — #3 graphify — Ваша кодова база як граф знань (134.8 тис.⭐️) 18:01 — #2 orca — Командний центр для флоту агентів (105.4 тис.⭐️) 20:18 — #1 security-audit-skill — Перетворіть свого агента на аудитора безпеки (46 тис.⭐️) 23:17 — Підсумки та тенденції 🔗 РЕПОРТАЖІЇ • #10 andrej-karpathy-skills → multica-ai/andrej-karpathy-skills • #9 claude-plugins-official → anthropics/claude-plugins-official • #8 ruflo → ruvnet/ruflo • #7 ai-memory → akitaonrails/ai-memory • #6 ComfyUI → Comfy-Org/ComfyUI • #5 гіперфрейми → heygen-com/hyperframes • #4 відкритий код → anomalyco/opencode • #3 графіка → Graphify-Labs/graphify • #2 орка → stablyai/orca • #1 навичка аудиту безпеки → cloudflare/security-audit-skill 👍 Вподобайкайте, 💬 Коментуйте, 🔔 Підпишіться, ⭐️ Поставте зірочку на репозиторії! #github #відкритийвихіднийкод #штучнийінтелект #кодування #програмування #тренди #інструментирозробки #розробник