Mentions

@deepak_raaaz Hey, I’m interested in the freelance UI/UX Designer opportunity. I have 4 years of experience in UI/UX and Product Design, alongside 4 years of software development experience. Portfolio: getbndlabs.com GitHub: github.com/godadcore I’d love to connect and learn more about the project!

Anyone tried this yet? Open source tools bypass NVIDIA’s half-rate tensor limit on supported GeForce cards. The Linux gpu-unlock project reports community gains of 30–55% in image generation and 25–50% in BF16 fine-tuning. Memory-bound token generation generally doesn’t benefit. preview.redd.it Curious what people are seeing on their own hardware. Project and reported results · Tom’s Hardware coverage

Location: Lahore, Pakistan (UTC+5) Remote: Yes, remote only Willing to relocate: No Technologies: TypeScript, Playwright, Node.js, React, API testing, GitHub Actions, MCP servers Résumé/CV: https://www.linkedin.com/in/junaidnasir1001 Website: https://sqaline.com GitHub: https://github.com/junaidnasir1001 Email: junaid@sqaline.com QA automation engineer, 4+ years in QA. I write Playwright/TypeScript end-to-end and API tests that run in CI, so login and payments don't quietly break on a Friday release. I built 50 Playwright tests for an enterprise HR platform (auth, leave, shifts, payroll), run by GitHub Actions on every push. A full run took about 17 minutes, and an early CI failure exposed a role-assignment bug before release: junaidnasir1001/onehrm-playwright-e2e Open to part-time, contract or freelance work. If you'd rather start small: a fixed $300 pilot, up to three Playwright checks on your most important flow, running in GitHub Actions and delivered as a PR.

@made_by_dy Oh, you haven’t tried Silk yet. silk-lang/silk t.co

RoboParty just launched RP1 a full-stack open-source humanoid robot THE FIRST OPEN SOURCE AUTONOMOUS BOT MODEL it already walks, recovers from pushes and gets back up after a fall auganix.org Github : github.com/Roboparty Sending fees to his github t.co

The daily loop, as an installable package Last week I counted every caller on my own platform: 4,247 distinct callers over seven days, and 98.5% of them were active on exactly one day. 17 callers came back on three or more days. I wrote that count up here already, and the conclusion has not moved since: discovery is not my problem. Return is. The 17 who stayed share a shape. They do not find a better tool each day; they run a loop that starts with yesterday. Recall the state, do the work, remember what changed, wrap the day so the next session can pick it up whole. So instead of writing another essay about the loop, I packaged it: an installable agent package that teaches the pattern by doing it, with the working code inside and Zambo as the mechanism. It is live on npm as zambo-loop, and as a template repo on GitHub. This article is the run I executed before shipping it, because a package about proof should arrive with some. The pattern, in one paragraph One agent, one persistent caller handle, one job. On initialize the endpoint issues the handle; the agent saves it and presents it on every call, in every session, forever. Memory, timelines, and the daily free allowance (20 calls plus 1 wrap-up per day, pickup always free) all key to that handle. Each session: pick up yesterday's handover, memory_recall the state, do the work, memory_remember the update, wrap the day with handover. That is the whole loop. Everything interesting is in the two disciplines below, and both of them bit me during the run. The run One fresh identity, daily-loop-agent, one job (daily-loop-demo-2026-11-02), a BTC and ETH watch, three sessions as separate processes under the same saved handle. Session 1 priced the watch: BTC $76,786.70, down 1.29% (receipt: zambo.dev), ETH $2,247.14, down 0.69% (receipt: zambo.dev). Then it tried to save the baseline state, and the save was refused before execution: zambo.dev Session 2 opened by recalling, and the recall came back honestly empty, count 0: zambo.dev. It re-checked BTC at $76,848.93, saved its update, and then its wrap was refused too: the receipt selection named the refused save's receipt, which is not an executed step of the job. A wrap holds only its own job's receipts: zambo.dev The repair was one call: the same baseline state at 378 characters instead of 533, saved clean: zambo.dev Session 3 recalled that state and the check was mechanical, three string matches: "BTC baseline $76,786.70", "ETH baseline $2,247.14", and the alert rule, all present in the recalled text verbatim (receipt: zambo.dev). It re-checked BTC at $76,875.00, a move of +0.115% from baseline, inside the 3% band, no alert (receipt: zambo.dev), remembered the update, and wrapped the day: zambo.dev Open the handover. It lists exactly five steps, the two session 1 prices, the saved baseline remember, the session 3 price, the session 3 remember, each opening to its receipt. The wrap's own receipt is here: zambo.dev The two disciplines, because they are the package Facts are short, and results get checked. A saved fact has a hard limit of 500 characters. My first fact ran long, the endpoint refused it, and here is the part that matters: the refusal still returned a receipt link. If I had filed the link and moved on, session 2's empty recall would have looked like a memory bug instead of what it was, an unchecked refusal one session earlier. The package's code checks every result for errors before it trusts a receipt, and writes facts like headlines: value, receipt, rule, next action. A wrap holds only its own job's receipts. The wrap binds the job's executed steps and runs a proof loop over them. Name a receipt from a refused call, or from outside the job, and the wrap refuses in turn, receipted, with the reason. Track the job's receipt ids as you go and the wrap is a formality. This is not bureaucracy; it is what makes the final handover a record of work that actually happened. What the loop costs Counted from the run's own record: session 1 spent 2 counted calls (the refused save executed nothing), the repair 1, session 3 spent 3, and its wrap was the free daily wrap-up. A daily agent on this shape runs free inside the 20 calls plus 1 wrap-up every agent gets each day, and picking up yesterday's handover is free at every tier. Past free, the scaling line is $0.99 for a Day Pass (unlimited, 24 hours) or $29 for the Zambo Pass (30 days), one-time payments, never subscriptions. Get the package - npm: npm install zambo-loop (npmjs.com) - GitHub, template repo: zambodotdev/zambo-daily-loop - The guide, with the full run and the standing instructions: rambozambodotdev.gitlab.io - The sibling pattern, swarm coordination as a package: pypi.org The loop does not need my platform's permission to matter; any agent that keeps state and seals its day has the shape. Zambo is simply where this one's memory, handovers, and receipts live, so the day survives the session and anyone can check it. A receipt proves the saved result was not changed since it was saved. It does not prove the baseline was right, and I am not claiming otherwise. --- Try it free: add Zambo to your AI in one step at zambo.dev/add. 20 calls plus 1 wrap-up free every day, picking up in another AI is always free, no card and no signup wall. - Zambo: zambo.dev - Add Zambo to your AI: zambo.dev - The daily loop package on npm: npmjs.com - The daily loop package on GitHub: zambodotdev/zambo-daily-loop - The guide, with the full run: rambozambodotdev.gitlab.io - The data: 4,247 callers came, 17 stayed: dev.to - AER-1 conformance corpus: zambo.dev - Verify any receipt: zambo.dev - AI agent handover, the signature product: dev.to

lalalune/pumpfun-source pumpfun-source is a completed open-source project that exactly reconstructs the bytecode of pump.fun’s on-chain Solana programs (Pump Main, PumpSwap/AMM, Fees, Mayhem, and Donation Relay) for research and auditing purposes.

Same pain here, so I keep skills in one structured source and reuse it across projects. It's open research (MPL-2.0): The-Interdependency/pubskill-lib. Would it end the copy-paste for you?

9/ Both are live today 📊 Pay with work: x402.qu.ai Inference: hashference.com Spec: x402#3 Builders on x402, we welcome your feedback! @CoinbaseDev @base @yugacohler @stevekaliski @jeff_weinstein @MurrLincoln

LidCommit: Safe Git auto-save triggered by your laptop lid Most Git autosave tools run on continuous intervals or cron jobs, which can clutter your commit history with partial keystrokes. LidCommit takes a different approach: it only commits when you actually close your laptop lid to step away from your desk. Features: - Monitors OS power broadcast interrupts (0% CPU impact). - Only inspects projects actively open in an IDE (VS Code, Cursor, JetBrains). - Pre-commit secret scanning engine prevents pushing credentials or `.env` files. - Generates clean semantic commits with LLMs or fallback timestamps. - Native dashboard for pausing specific repositories. Open-source on GitHub: Gingaaa/lid-commit

Github: valvesky/velocitty Write up: valvesky.github.io Benchmarks also in write up.

The price was wrong, the receipt was not: catching a drifted retelling with a verify pass Your agents are handing each other results all day, and some of those results are wrong in a way nobody notices: not fabricated, just drifted. A digit changes between the tool call and the summary. A qualifier drops. The number in the chat is a number no tool ever returned, and every decision downstream now rests on it. I run Zambo, a work layer for AI agents where every call returns a verifiable receipt. Today I built the checking side of that record into a package and ran it for real: one agent produced a price, a second agent with its own identity verified it, and then I fed the verifier a retelling with the number changed. Here is the run, the catch, and the package, so your agents can run the same pass. Start with no code at all Add the Zambo endpoint (zambo.dev) to one chat AI. The two-minute setup is at zambo.dev. Then paste this into the verifier's chat: Verify before you trust, on Zambo: 1. Connect to zambo.dev. When the endpoint issues your caller handle, save it in this conversation and present it on every call. You are a verifier; your verdicts are recorded under your handle. 2. For every claim another agent hands you, demand the receipt link with it. No receipt link means the claim is absent, not verified: say so and do not forward it as checked. 3. Check the receipt: open zambo.dev and read verification_status and the checks. Note any check marked not_checked; never report those as passed. 4. Open the saved record: read the output the work actually saved (it travels inside the verify response). Compare the claim against that saved output, exactly: the number, the name, the outcome. Never compare against the summary you were handed. 5. Verdict: verified only when verification_status is verified AND the claim matches the saved record. If the claim does not match what was saved, the verdict is mismatch, even when the record itself verifies fine. Trust the record, not the retelling. 6. Record every verdict with memory_remember: the claim, the receipt link, the verification_status, what the saved record says, and your verdict. Your verdict is now a receipted step the next agent can check. 7. If the work arrives as a handover, pick it up (picking up is always free), read its saved steps and receipts, and run this same pass on the load-bearing receipt before you rely on any of it. That is the whole pass at hand scale. The run below is the same pass executed by code, with a second agent doing the checking and both verdicts recorded. The run November 2, 2026, two fresh identities under one shared job. The producer checked ETH with live_price: $2,242.99, down 0.75 percent in 24 hours, saved at 20:43:50 UTC. Its work receipt: zambo.dev The producer saved the finding to memory (receipt: zambo.dev) and wrapped it into a handover addressed to the verifier: zambo.dev The verifier picked the handover up (pickup is always free), read the price and the work receipt from the pickup record rather than from the summary, and ran the pass. The verify endpoint's own answer is public, read it yourself: zambo.dev It returned verification_status verified. Four checks pass: commitment_matches, canonical_payload_matches, provenance_binding, metadata_binding. Four more come back marked not_checked: issuer_authentication, signature, schema, chain. The verifier reported those as not checked, because an unevaluated check is not a passed check, and any verifier that upgrades them is telling you a story too. Then the comparison. The saved record's output says ETH at $2,242.99. Claim one, the true retelling: "ETH at $2,242.99". It matches the saved record, and the record verifies. Verdict: verified. The verdict is itself a receipted step, so the checking can be checked: zambo.dev Claim two, the wrong retelling: "ETH at $2,354.10". I changed the number myself, deliberately, and labeled it as the teaching case in the run and in its verdict record. Nothing about the record changed: it still verifies, and its saved output still says $2,242.99. But the claim does not match the saved record, so the verdict is mismatch: zambo.dev That second verdict is the whole point. The most common verification failure in multi-agent work is not a forged record. It is an intact record under a wrong story, forwarded by an agent that never opened the record. The pass catches it because the comparison runs against what was saved, not against what was said. The verdict vocabulary, because words drift too - verified: the receipt's verification_status is verified AND the claim matches the saved record. - mismatch: the record was opened and the claim does not match what was saved. - verification failed: the endpoint's checks fail on the record itself. - not checked: the pass was not run, or a check was not evaluated. - absent: no receipt was produced for the claim. And the boundary, stated plainly: a receipt proves the saved result was not changed since it was saved. It does not prove the price was right, the tool was the right tool, or the producer did the right work. The pass checks fidelity between a claim, a receipt, and a record. Judgment about the work itself stays yours. What the pass costs Almost nothing, and that is why it can be a habit instead of an event. Reading the verify endpoint is a plain HTTPS read and costs no quota. Picking up a handover is always free. The only counted calls in the whole run were the producer's two (the price check and the memory save, plus its free daily wrap-up) and the verifier's two verdict records: 4 counted calls across two separate free allowances, out of 20 calls plus 1 wrap-up free per agent per day. Past free, the per-agent line is a Day Pass at $0.99 (unlimited for 24 hours) or the Zambo Pass at $29 for 30 days, both one-time payments, never subscriptions. The package The pass now ships as an installable agent package, zambo-verify-pass, so an agent can learn it by installing it: the skill, a runnable verify.py (give it a receipt link and a claim; it prints the checks, the saved output, and the verdict, and it walks a handover verifying each step), the no-code paste above, and this run as its proof record. - PyPI: pypi.org - npm: npmjs.com - GitHub (template repo): zambodotdev/zambo-verify-pass - The full guide: rambozambodotdev.gitlab.io Run verify.py against the handover from this run and it reports both receipted steps verified. Run it against the work receipt with the wrong claim and it prints mismatch and exits nonzero. The verifier your swarm's coordinator needs is the same one: in the swarm package (pypi.org), the coordinator runs this exact pass at every pickup instead of trusting worker summaries. Your framework runs your agents. Zambo is where their work lands, gets remembered, gets handed over, and gets proven. The verify pass is how the next agent checks all of that before building on it, and every link above is the evidence. --- Try it free: add Zambo to your AI in one step at zambo.dev/add. 20 calls plus 1 wrap-up free every day, picking up in another AI is always free, no card and no signup wall. - Zambo: zambo.dev - Add Zambo to your AI: zambo.dev - The verify pass guide, with the full run and both verdicts: rambozambodotdev.gitlab.io - The verify pass package (template repo): zambodotdev/zambo-verify-pass - The swarm package, whose coordinator runs this pass: zambodotdev/zambo-swarm-coordination - AER-1 conformance corpus: zambo.dev - Verify any receipt: zambo.dev - AI agent handover, the signature product: dev.to

AhtapotAgent v1.0.0 açık kaynak yayında 🐙 Planner → Developer → canlı test → QA → PR Çok-agent'lı geliştirme orkestratörü; agent koşarken her aşamada onunla konuşabilirsin. Docker imajı hazır, geri bildirimlere açığım 👇 firatoltulu/AhtapotAgentHq #OpenSource #AIAgents

@ShayanelH @Pumpfun lalalune/pumpfun-source pumpfun-source is a completed open-source project that exactly reconstructs the bytecode of pump.fun’s on-chain Solana programs (Pump Main, PumpSwap/AMM, Fees, Mayhem, and Donation Relay) for research and auditing purposes.

@mns_gs Kolla här, under Artifacts har du den senaste versionen. github.com/tildearrow/furnace/actions/runs/410467… Den "riktiga" versionen har inte blivit uppdaterad på typ ett år, så skippa den.

I Built LLM Explained: 43 Interactive Pages That Take You From Tokens to AI Agents I kept running into the same problem while learning about large language models. I'd read a blog post about attention, nod along, and two days later I couldn't tell you why we divide by √d_k. I'd see "GQA", "MLA", "MoE", "LoRA", "HNSW" or "context rot" in a paper or a tweet, open five tabs, and close them all with the uneasy feeling that I sort of got it. And the field keeps moving, so there's always a new term on top of the ones I hadn't really nailed down. So I built the resource I wished I had: LLM Explained. It's a free, interactive course that goes from "why did RNNs hit a wall?" all the way to "how does a production agent retrieve, reason, act and get evaluated?" I built it to learn, and writing each page forced me to understand things properly. I'm sharing it because I think it can help other people too. 🔗 Live site: llm-explained-lovat.vercel.app 💻 Source code: amananandrai/llm-explained > 💌 This is a work in progress and I'd love your help. Suggestions are always welcome. If you find it useful, please ⭐ star the repo on GitHub. Spotted a mistake or have an idea? Open an issue. Want to fix or add something yourself? Pull requests are very welcome! !The LLM Explained home page: an attention matrix for "The cat sat on the mat" --- What is LLM Explained? It's 42 modules in seven parts plus a capstone (43 interactive pages if you count the KL divergence sub-page). Every concept appears as a picture you can play with before you see its equation. A few principles shaped every page: 1. Picture first, symbol second. Each equation sits next to the animation that computes it, and they use the same colours. If the query is blue in the diagram, it's blue in the formula. 2. One idea per scroll step. Animations move forward as you scroll and never run on without you. 3. Real numbers at toy scale. 4-dimensional embeddings and 3–5 token sentences, so every value fits on screen and you can check it. 4. Touch the knob. Every module has at least one widget you control. 5. Run it yourself. Optional in-browser Python (NumPy) cells reproduce the figures. 6. Honest limits. Every module ends with a "what this picture leaves out" box, because simplified diagrams can mislead you if you don't know what they skip. Also, every number on screen is computed in your browser. When something is a simulation or an illustrative figure, the page says so. --- How to use the site 1. Start with the curriculum map The Curriculum link in the top navigation shows the whole course. Parts 1 and 2 are meant to be read in order, and everything after them builds on the attention module. Beyond that you can jump around: - Parts 3, 4 and 7 can be read in any order within each part. - Part 5 (RAG) follows the order of a retrieval pipeline. - Part 6 (Agents) starts from the agents and ReAct module. If you already know the transformer well, skip to whatever you're curious about. If you're new, start at Module 1 (or the optional maths primer, Module 0). !Going from the home page to the curriculum map and into a module 2. Pick your depth: Intuition, Mechanics or Maths This is my favourite feature. Every page has a depth switch with three levels: | Depth | What you get | Good for | |---|---|---| | Intuition | Pictures and plain language, no symbols | A first read, or a quick refresher | | Mechanics | Tensor shapes and step-by-step operations | Engineers who want to implement it | | Maths | Full derivations, colour-linked KaTeX equations | Going deep, or interview prep | !Three buddies: Intuition with a crayon drawing, Mechanics in a hard hat, Maths with glasses and a chalkboard You can read a page at Intuition level, come back a week later and flip to Mechanics. The page grows with you. !Flipping the depth switch between Intuition, Mechanics and Maths And here's what the Maths depth looks like. Notice that Q, K and V keep the same blue, orange and green as in the animations: !Maths depth: the attention formula and the √d_k variance argument in colour-linked KaTeX 3. Scroll, step and scrub the animations Each page has a hero animation driven by your scroll position. There are also play, pause, step back, step forward and a scrubber, so you can pause on exactly the frame that confuses you. For example, in the attention module a 5-token attention matrix fills in cell by cell, the heads split into colours, and you see each output vector built up as a weighted sum of value vectors. !Scrolling through the 8-step attention animation in Module 5 !Kawaii tokens: "mat" gives 34% of its attention to "cat" Every animation also has a text transcript, and if your system has reduced motion turned on, animations turn into numbered static frames. 4. Play with the widgets This is where things click. Some examples: - A "remove √d_k" toggle that shows softmax saturating when you drop the scaling factor. You can see why the scale is there. !Toggling √d_k on and off, then exploring attention-head patterns !With √d_k everyone gets a share; without it, key 5 eats 99.8% of the attention - A parameter counter that checks the 12·d² rule against GPT-2 and GPT-3. !The parameter counter widget - A real byte-level BPE tokeniser running in the browser. Try the Hindi example and watch the token bill go up. !The tokenizer playground switching between examples !A bread loaf labelled "unbelievable" gets sliced into "un", "believ" and "able" - A numerical KL divergence explorer and the closed-form RLHF optimum. 5. Run the Python yourself Most modules include a "Run it yourself" cell: editable Python running in your browser through Pyodide with NumPy. Change a number, hit Run, and watch the result update. You don't need to install anything. (Pyodide downloads on your first run, so give it a moment.) !An editable Python cell: scaled dot-product attention by hand 6. Check yourself with the quiz Each page ends with a "what this picture leaves out" box, a 3-question quiz and a further reading list linking the primary papers. Every module cites its sources, from Attention Is All You Need to LoRA, DPO and PagedAttention. !Answering the end-of-module quiz --- What's covered Here's the full curriculum. I tried to cover both the core fundamentals and the newer ideas that keep showing up in papers and on Twitter/X. !The curriculum map Part 1 · Foundations: how text becomes numbers - M0 Maths primer (optional), plus a dedicated KL divergence page - M1 How models learn: training terms - M2 Why transformers were needed - M3 Tokenisation - M4 Embeddings Part 2 · The Transformer and GPTs - M5 Attention and the transformer block - M6 Encoder, decoder and encoder–decoder - M7 GPTs: from pretraining to generation - M8 Post-training: SFT, RLHF, DPO and reasoning - M9 Prompt engineering: zero-shot, few-shot and beyond Part 3 · Faster, bigger, smaller - M10 Evolution of attention: MHA vs GQA vs MLA (and LRKV) - M11 Taming the KV cache - M12 Mixture of experts - M13 Scaling training: parallelism, ZeRO and FSDP - M14 Distillation - M15 Quantisation: FP8, FP4 and TurboQuant Part 4 · Real models, new ideas and adapting them - M16 Open-source LLM architectures compared - M17 New block designs: Attention Residuals and beyond - M18 Beyond next-token LLMs: concept models, JEPA and decision models - M19 Multimodality - M20 Fine-tuning: full, LoRA and QLoRA Part 5 · Retrieval and RAG - M21 Embedding models in depth - M22 Vector search and HNSW - M23 Chunking strategies - M24 Re-ranking with cross-encoders - M25 The seven types of RAG - M26 Graph RAG, open knowledge graphs and vectorless RAG Part 6 · Agents and harnesses - M27 Agents, tool use and the ReAct framework - M28 Context engineering and context rot - M29 Types of memory - M30 Harness engineering: building the harness - M31 Loop engineering and the Ralph Wiggum loop - M32 MCP: the Model Context Protocol - M33 Skills and plugins - M34 Agent orchestration and subagents - M35 Agent-to-agent communication - M36 Agentic engineering !An agent buddy running in a Think → Act → Observe hamster wheel !The ReAct agent trace in Module 27 Part 7 · Production and safety - M37 Benchmarking and evaluation - M38 LLMOps - M39 Safety, alignment and interpretability - M40 Model governance Capstone - M41 Follow one request end to end. One prompt's whole journey: text → tokens → embeddings with RoPE → transformer blocks (GQA attention with a KV cache, MoE feed-forward) → logits → sampling → text. Then the same request inside an agent harness that chunks, retrieves and re-ranks context, calls a tool, writes to memory, and is traced and evaluated. A tiny real transformer block runs in your browser, and you can inspect every intermediate tensor. !Scrolling through the capstone: one request, end to end --- One visual language across every page Something I cared about a lot: colours mean the same thing everywhere. The blue you learn as "query" in Module 5 is still "query" in the capstone. | Element | Colour | |---|---| | Query (Q) | Blue | | Key (K) | Orange | | Value (V) | Green | | Residual stream | Neutral grey | | Router and experts (MoE) | Purple | | Frozen weights vs trainable adapters (LoRA) | Grey vs bright pink | | Retrieved passages (RAG) | Filled teal | | Pass / fail / needs review (evals) | Green / red / amber, always with an icon | | Untrusted or injected content | Red hatching | Once you learn the colours, later diagrams are much easier to read, because half the explanation is already done for you. Colour never carries meaning on its own, though. There are icons, labels and transcripts too, and both light and dark themes aim for WCAG AA contrast. !The attention module in dark mode --- Who is this for? - Software engineers and students who know some Python and school-level maths and want to really understand what's going on inside an LLM. - ML practitioners who want the maths and architecture details collected in one place. - Anyone building with LLMs (RAG apps, agents, MCP servers) who wants a mental model of the stack underneath. Two goals I used to test the site: > After Module 7, you should be able to sketch a decoder block and estimate its parameter count to within 10%. > > After Module 36, you should be able to sketch a RAG agent's harness and name where it can fail. --- Under the hood (for the curious) I deliberately kept the tech simple: - Plain JavaScript and static files, no build step. index.html is the shell, and each module is its own file (assets/m/m<id>.js) that loads lazily when you navigate to it. - A small reusable component library (core.js, kit.js): router, depth switch, ScrollyStage (sticky visual next to scrolling text), sliders, probability bars, matrix grids, line charts, quizzes, colour-linked math blocks, pipeline diagrams and agent traces. - KaTeX for the maths and Pyodide + NumPy for the runnable Python cells. - Plan-driven content. The whole course is written as a single build plan in Markdown. A Python script (scripts/build_data.py) parses it into the curriculum, tables and reading lists. If a module script fails to load, the page falls back to an outline generated from the plan. - Deployed on Vercel as a static site. To run it locally: git clone https://github.com/amananandrai/llm-explained cd llm-explained ./scripts/dev.sh # wraps index.html into dev.html python3 -m http.server 8765 # open http://localhost:8765/dev.html --- Honest limits In the same spirit as the "what this picture leaves out" boxes, here's what the site doesn't do yet: - It doesn't use real production tokenisers, recorded agent traces or live LLM calls. Widgets that would need those use in-browser computation (byte-level BPE, a real HNSW, numerical KL, a tiny real transformer block) or written examples with illustrative numbers, and the page labels them. - The model spec cards in Module 16 are transcribed from published configs. If you spot an error, please tell me! --- Why I built it, and why I'm sharing it Building this was the best way I've found to learn. You can't animate attention cell by cell, or write a widget that shows a KV cache growing, without understanding exactly what's happening. Every page exposed a gap in my own understanding that I then had to fill. I'm sharing it because if it helped me, it may help you too. And sharing it means people will find my mistakes, which is how I keep learning. --- 🤝 Help make it better !Three buddies: one holding a star, one catching a bug, one sending a love-letter PR This project gets better with every pair of eyes on it. Suggestions are always welcome, big or small. Here's how you can help: - ⭐ Star the repo on GitHub. It helps more learners find it, and it makes my day. - 🐛 Raise an issue for anything wrong, confusing or broken: open an issue. - 🔧 Raise a PR to fix a typo, improve an explanation, add a widget or even a whole module: pull requests are welcome. - 💡 Suggest a topic you want explained, right here in the comments. - 🔁 Share it with a friend, classmate or teammate who's learning about LLMs. Pick a module, flip the depth switch, play with a knob, and tell me which concept finally clicked for you. 👇 👉 llm-explained-lovat.vercel.app

GambetaGame's Python ETL kept shipping duplicate player rows from 1891 records, so React rendered the same striker twice. I added a deterministic dedupe key at ingest. Bad rows now fail before the game loop. RanuK12/GambetaGame

lalalune/pumpfun-source pumpfun-source is a completed open-source project that exactly reconstructs the bytecode of pump.fun’s on-chain Solana programs (Pump Main, PumpSwap/AMM, Fees, Mayhem, and Donation Relay) for research and auditing purposes.

I made a tiny Windows widget that shows your Google Antigravity /usage quota, inspired by clawd-usage-winwidget Hi everyone! I built agy-usage-winwidget, a small floating window and tray icon for Windows. It shows your Google Antigravity weekly quota, the same numbers you get from /usage in the Antigravity CLI, and refreshes them automatically. Features: - Two progress bars: Gemini models (Flash, Pro) and Claude & GPT models (Opus, Sonnet, GPT-OSS), each with its own percentage and reset countdown - Colours change from green to yellow to red as usage grows - Hexagonal tray icon that shows the current percentage at a glance - 24-hour history chart in the details panel - Remembers its position, and you can zoom it with the mouse wheel - No dependencies: just PowerShell 5.1 + WPF (built into Windows) and agy on your PATH - English and Spanish UI Download: IberianSoldierPC/agy-usage-winwidget (grab the latest release ZIP and double-click start-widget.vbs) Huge thanks to Venger Sergey (Enhed) for clawd-usage-winwidget (original post), a lovely Claude Code usage widget. It inspired the architecture, the UI and many of the patterns I used here, and it's MIT-licensed. If you use Claude Code on Windows, go check it out! 🧡 Feedback and PRs are welcome.

おー、アストロノーカRTA新1位の人、凄いチャートと資料だーー mogg-rta/astronoka mogg-rta.github.io

@goicoquill Por lo que sea, no entres aqui: kushagrasinghx/BitChord Y, sobretodo, no descargues el apk de android en releases, eso seria algo escandaloso😱

6 kbps is enough for encrypted Mumble-style voice! Partyline is open source. Spin up a server in under 30 seconds. Source: RFnexus/partyline Would you run group voice over LoRa? #OpenSource #MeshNetworking

@razaaitech Thanks Raza! Would greatly appreciate an upvote on our product hunt launch and definitely check out our Github repo: Asymptote-Labs/agent-beacon

CD DVD BD의 ISO를 넣어서 굽기만 하면 그림이 나타나는 JiaFeiMiao-K-Cat/DiscImageStudio 천재적이다.

Show HN: Kubernetes Operator for the OpenAI Managed Agents API

Every Claude Code session starts by reloading memory. Freshlint checks it first. At session start it lists, in 10 lines or fewer, each note whose cited code changed, is gone, or was never fingerprinted. All clear? It stays quiet. Free and open source: KellerAI/freshlint t.co

.NET 8・.NET 9のサポート終了は2026年11月10日｜同日終了の理由と.NET 10への移行ガイド Microsoftは標準期間サポート（STS）の期間を18か月から24か月に延長しました。その結果、.NET 9は.NET 8と同じ2026年11月10日にサポートが終了します。本記事では、その理由と.NET 10へのアップグレード方法を解説します。 .NET 9のサポートは2026年11月10日に終了します。.NET 8も同じ日です。残りは3週間を切りました。.NET 8は2023年11月14日にリリースされた長期サポート（LTS）版、.NET 9はその1年後の2024年11月12日にリリースされた標準期間サポート（STS）版です。この2つが同じ日にサポート終了を迎えます。誤植ではありません。11月10日以降にサポートされるバージョンは.NET 10で、LTSとして2028年11月14日までサポートされます。 2026年11月10日に.NET 8と.NET 9で何が終わるのか？ 終わるのはサービシング（保守提供）です。.NET BlogでRahul Bhandari氏が公表した告知によると、Microsoftは.NET 8と.NET 9に対する「サービシング更新、セキュリティ修正、技術サポート」を終了します。 アプリケーションは引き続き動作します。自動でアンインストールされることもありません。ランタイム、SDK、コンテナイメージもダウンロードできます。ただし、今後は修正が提供されなくなります。 11月10日はパッチ・チューズデーでもあります。Microsoftによると、既知の重大な問題がある場合に限り、.NET 8と.NET 9は同日に最後の更新を1回ずつ受け取る可能性があります。それ以降は、ランタイム、ASP.NET Core、基底クラスライブラリ（BCL）に影響する新たなCVEはすべて自己責任で対処することになります。 本記事執筆時点の最新パッチは8.0.32と9.0.21で、どちらも2026年10月13日にリリースされています。これらを適用していない場合は、期限を迎える前から対応が遅れている状態です。 ツール面にも影響があります。今後のVisual Studio 2022のサービシング更新で、.NET 8と.NET 9のコンポーネントがサポート終了として扱われるようになります。Visual Studioは更新時に、サポート終了のコンポーネントの削除を提案します。ビルドエージェントでこの設定を事前に確認しておきましょう。 なぜ.NET 9は.NET 8と同じ日にサポートが終わるのか？ .NET 9のサポート期間中に、MicrosoftがSTSのライフサイクルを変更したためです。 旧ポリシーでは、STSのサポート期間は18か月でした。これは次のリリースから6か月後にあたります。.NET 9は2026年5月12日にサポートが終了する予定でした。 2025年9月16日、.NET BlogでJamshed Damkewala氏が、STSリリースのサポート期間を24か月に延長すると発表しました。.NET 9から適用されます。LTSは従来どおり3年です。これにより、.NET 9のサポート終了日は2026年5月12日から2026年11月10日に移り、.NET 8の終了日とちょうど重なりました。 STSを24か月に延ばしたことで、STSリリースの終了日は直前のLTSリリースと同じになります。STS版の依存関係を使っていても、LTS版アプリと同じ日にサポートが終わる形です。なお、.NET Aspireのようなアウトオブバンド（OOB）コンポーネントは独自のライフサイクルを持つため、別途確認が必要です。 実際の問題を解消する、妥当な見直しだと私は考えています。一方で、副作用として2つのリリースが同じ日にサポートカレンダーから外れることになりました。.NET 9の終了を2026年5月と見込んで計画していた方は、6か月の猶予が増えていたことに気づいていないかもしれません。 この構造は今後も繰り返されます。偶数番号のLTSは11月にリリースされ、3年間サポートされます。奇数番号のSTSは翌年の11月にリリースされ、新ポリシーでは2年間サポートされます。どちらも同じ11月に終了します。.NET 10と.NET 11も、2028年11月に同じ日にサポートが終わると私は見ています。今回は例外ではなく、これからの標準パターンです。 各.NETバージョンのサポート状況は？ 出典: .NET and .NET Core Support Policy（2026年10月19日時点） どのバージョンにアップグレードすべきか？ .NET 10です。 現行のLTSリリースで、2028年11月14日までサポートされます。24か月のSTSポリシーのもとでは、.NET 11を待っても猶予は延びません。得られるのは、同じ月にサポートが終わると私が見ている、より新しいリリースだけです。 .NET 9をお使いなら、.NET 10へは1バージョン上げるだけで、多くの場合は小規模な変更で済みます。.NET 8をお使いなら、2リリース分の破壊的変更をまたぐため、工数を多めに見込んでください。ASP.NET Coreアプリは、ASP.NET Core 9から10への移行ガイドも確認しておきましょう。 最も単純な場合、アップグレードは各プロジェクトファイルの1行の変更です。 net10.0 ただし、この1行で済むことはまれです。実際の作業は次のような部分に生じます。 - 互換リリースが必要なNuGetパッケージ - 古いSDKを固定しているglobal.json - mcr.microsoft.com/dotnet/aspnet:8.0を参照しているDockerfile - 新しいランタイムのインストールが必要なCI/CDパイプラインとホスティング環境 自社で運用していても開発はしていないサードパーティ製アプリケーションについては、ベンダーに.NET 10対応版のリリースを問い合わせてください。 GitHub Copilotで.NET 10にアップグレードするには？ .NET Upgrade Assistantは使いません。Microsoftのドキュメントでは、「.NET Upgrade Assistant is officially deprecated.」と明記されています。サポート終了の告知にはまだリンクが残っていて紛らわしいのですが、このツールは後継に置き換えられています。 後継はGitHub Copilot upgrade agentです。ソースコードとプラグインはmicrosoft/upgrade-agent-pluginsにあります。Mika Dumont氏がModernize .NET Anywhere with GitHub Copilotで使い方を解説しています。 作業は3つの段階で進みます。各段階の成果物はリポジトリの.github/upgrades/配下にMarkdownファイルとして出力されるので、レビューやコミットが可能です。 1. 評価（Assess）: プロジェクトと依存関係を調べ、assessment.mdを出力します。破壊的変更、API互換性の問題、非推奨パターンが一覧化されます。 2. 計画（Plan）: plan.mdを出力します。アップグレード戦略、依存関係の順序、リスクが記載されます。 3. 実行（Execute）: 計画をtasks.mdのタスクに分割して順に実行し、作業単位ごとにGitコミットを作成します。検証やロールバックを段階的に行えます。 利用できる環境は4つあります。普段使っているものを選んでください。 - Visual Studio: Visual Studio 2026、またはVisual Studio 2022 17.14.16以降で、ソリューションエクスプローラーのソリューションまたはプロジェクトを右クリックし、Modernizeを選択します。 - VS Code: GitHub Copilot upgrade extensionをインストールし、Copilot ChatのエージェントピッカーでUpgradeを選択します。 - GitHub Copilot CLI: 次のコマンドを実行します。 /plugin marketplace add microsoft/upgrade-agent-plugins /plugin install upgrade-agent@upgrade-agent-plugins /agent Upgradeを選び、「upgrade my solution to .NET 10」のように指示します。 - GitHub: Copilotクラウドエージェントとして追加すると、プルリクエストを自動で作成できます。手順はクラウドエージェントのREADMEを参照してください。この方法には、クラウドエージェントが使える有料のCopilotプランと、リポジトリへの書き込み権限が必要です。 どの方法を選ぶにしても、次の点をおすすめします。 - 最初は、モノリスではなく小さなライブラリやサービスから始めましょう。自社のコードベースでエージェントがどこでつまずくかを把握できます。 - 大規模なコードでは、ガイドモード（Guided）を使いましょう。「pause」でガイドモードに、「continue」で自動モードに戻せます。 - 最後にまとめてではなく、コミットごとにテストスイート全体を実行しましょう。タスクごとにコミットされるため、コストを抑えられます。 - 完了後は、次のコマンドで結果を確認しましょう。 dotnet --list-runtimes dotnet list package --outdated 大規模なレガシーソリューションでは、エージェントが自力で最後までやり遂げられるとは限りません。大きなアプリで処理が止まるという初期ユーザーの報告もあり、Microsoftがリポジトリでフィードバックを集めています。移行の全工程ではなく、非常に速い初回パスとして使ってください。 2026年11月10日までに.NET 8・.NET 9からアップグレードできない場合は？ その場合は、運用中のバージョンにパッチを提供してくれる存在が必要です。 HeroDevsのNever-Ending Support（NES）for .NETは、.NET 6、.NET 8、.NET 9をそのまま置き換えられる、安全なドロップイン代替です。ランタイム、ASP.NET、Entity Framework、.NET SDK、WPF、WinFormsを対象とし、NES for .NET Containersを使えばコンテナイメージもカバーします。コードの変更は不要です。 HeroDevsは.NET Security Groupのメンバーです。そのため、.NETに影響する脆弱性の事前開示を受け、MicrosoftのパッチTuesdayのリリースと同時に、EOLバージョン向けの修正済みビルドを提供できます。 これは仮定の話ではありません。.NET 6は2024年11月12日のサポート終了以来、HeroDevsがパッチを提供し続けています。System.Net.MailのSMTPインジェクションの脆弱性であるCVE-2026-32178では、.NET 6に上流の修正が提供されませんでしたが、NESのお客様には修正が提供されました。2026年11月11日からは、.NET 8と.NET 9もこの対象に加わります。 NESは.NET 10への移行の代わりにはなりません。移行のスケジュールを、パッチ・チューズデーではなく、エンジニアリングチームが決められるようになるということです。 よくある質問（FAQ） .NET 8と.NET 9のサポートが終了するのは正確にいつですか？ どちらも2026年11月10日です。この日はパッチ・チューズデーで、既知の重大な問題がある場合に限り、Microsoftが各バージョンに最後の更新を1回提供する可能性があります。 .NET 9は2026年5月にサポート終了の予定ではなかったですか？ はい、旧ポリシー（STS 18か月）では2026年5月12日でした。Microsoftが2025年9月16日にSTSを24か月に延長し（.NET 9から適用）、終了日が2026年11月10日に移りました。 .NET 8や.NET 9のアプリケーションは動かなくなりますか？ いいえ、引き続き動作します。ただし、Microsoftからのセキュリティ修正、バグ修正、技術サポートは提供されなくなります。 .NET Upgrade Assistantはまだサポートされていますか？ いいえ。MicrosoftはGitHub Copilot upgrade agentに置き換える形で非推奨としました。後継はVisual Studio 2026とVisual Studio 2022 17.14.16以降に付属し、VS Code、Copilot CLI、GitHubでも利用できます。 .NET 10ではなく.NET 11を待つべきですか？ いいえ。.NET 11はSTSリリースで、24か月ポリシーのもとでは.NET 10と同じ2028年11月ごろにサポートが終了する見込みです。.NET 10はすでに利用でき、より安全な移行先です。 HeroDevsは11月10日以降も.NET 9をサポートしますか？ はい。NES for .NETは、.NET 6、.NET 8、.NET 9をカバーします。 11月10日の期限までにアップグレードが間に合わない場合 .NET 10への移行が2026年11月10日に間に合わないアプリケーションについては、NES for .NETが.NET 6、8、9にパッチを提供し続け、監査対応も維持します。その間に、慌てず適切に移行を進められます。保証範囲についてはHeroDevsにお問い合わせください(日本語で対応可能です）。 --- お問い合わせ 本記事の内容やHeroDevsのソリューション（NES等）について、日本語でのお問い合わせに対応しています。お気軽にHeroDevsお問い合わせページからご連絡ください。 --- 原文: herodevs.com （出典: herodevs.com）

MLXRL supports experimental, opt-in score centering with actual sampler probabilities for 4-bit QLoRA. Open source, running locally on your Mac. inductiveML/mlxrl

Agents Make Trunk-Based Development Cheap: One Task, One Branch, Landed Same Day - Book: RAG Pocket Guide - The series: Pocket Guides for Developers — 8 short books on agents, RAG, prompts, observability, events, databases and system design — the whole series - My project: Hermes IDE | GitHub — an IDE for developers who ship with Claude Code and other AI coding tools - Me: xgabriel.com | GitHub --- DORA's bar for trunk-based development fits in one sentence: three or fewer active branches in the repository, and every branch merged into trunk at least once a day. Most teams never got close. Feature branches lived for a week or a sprint, and the merge at the end was a small project of its own. Now picture your repo after a few months of coding agents. There is a branch called agent-work. Several agent sessions have committed to it, each one finishing a tidy little task. The branch touches files all over the codebase, it is well past a week old, and it is waiting for "the big review" that nobody has blocked out an afternoon for. My take: the agent era is the cheapest moment there has ever been to adopt trunk-based development, and a lot of teams are spending it rebuilding the exact merge pain DORA measured. What DORA has been saying for years Trunk-based development, as DORA describes it, means developers merge small batches into the main line "at least once (and potentially several times) a day", on branches that "typically last no more than a few hours". DORA ties the practice to its 2016 and 2017 data, where teams that followed it achieved higher software delivery and operational performance. The capability page gives three goals you can measure: three or fewer active branches, at least one merge to trunk per day, and no code freezes. It is just as direct about the alternative. Long-lived branches "require bigger and more complex merge events", large merges "frequently introduce bugs or regressions", and "the longer a merge is delayed, the more likely it is to create merge conflicts and associated issues." None of that surprised anyone, and teams kept the long branches anyway. !Short orange branches each carrying a small robot sprout from a single black trunk and rejoin it right away, while one long black branch drifts off and knots up Many short branches that rejoin the trunk the same day, and the one long branch that drifts away. Humans batch. Agent tasks don't have to. The reason sits on the same DORA page, under common pitfalls: when code review "is laborious and takes hours or days, developers avoid working in small batches." If every merge costs a trip through the review queue and a context switch, you save changes up so you only pay once. That is a rational move for a person. It is also how a two-day feature turns into a branch nobody wants to rebase. Google's code review study shows what the other side looks like. Sadowski et al. analysed review logs for 9 million reviewed changes (ICSE SEIP 2018). The median change modified 24 lines, over 35% of changes touched a single file, and about 90% touched fewer than 10 files. Authors waited a median of under an hour for first feedback on small changes and about 5 hours on very large ones, and the median for the whole review process was under 4 hours. The paper notes that developers there "are strongly encouraged to make small, incremental changes", and cites earlier studies where review latency rises as change size grows. A coding agent's task arrives already cut to that size. You write one prompt: fix the flaky login test, or add a refund endpoint with a test. The agent works until that prompt is done, then it stops. The task has a clear end and its own diff, and nothing about it needs to wait for the rest of the week. The agent has no batching instinct. It doesn't find small merges tedious, and it doesn't sit on half-finished work to dodge a context switch. The habit DORA kept fighting was a human one. The agent doesn't have it. You still might. The agent branch that waits a week The numbers say the agent era can go either way. DORA's 2024 report estimated that as AI adoption increased, delivery throughput fell by 1.5% and delivery stability by 7.2% (Google Cloud, October 2024). Its advice pointed back at the basics of successful software delivery: small batch sizes and solid testing. A year later, DORA's AI Capabilities Model (September 2025) listed working in small batches as one of seven capabilities, saying it "amplifies the positive influence of AI on product performance and reduces friction for development teams." Faros AI's Q2 2026 report used two years of telemetry from 22,000 developers across 4,000 teams. Compared with low-adoption teams in the same organizations, high-adoption teams had a 16.2% higher PR merge rate, 51% larger PRs, 5x the median review time and 28% more bugs per PR. Faros labels these findings correlations. In that data, more work lands, in bigger pieces that take longer to read. On a single repo, the agent-work branch is how you get there. Each agent session produced a small diff. Stacking them onto one branch and reviewing them together throws away the one property that made them easy to review, and rebuilds the delayed merge DORA warned about. What reaches the reviewer is a wide diff with no clear author per change, against a main that kept moving the whole time. One task, one branch, landed the same day These are the rules I would hold an agent workflow to: - One task per branch, cut from trunk when the task starts. A second task never commits onto it. - The branch lands the same day, or the task gets smaller. If the diff is too big to read in one sitting, split the prompt and delete the branch. Rerunning a narrower task is usually cheaper than reviewing a wide one. - Review while the task is fresh. DORA's pitfall list warns against asynchronous review, where a request sits in a queue while its author moves on. When an agent finishes, read its diff before you start the next thing. - Unfinished feature? Merge it switched off behind a flag instead of parking it on a branch. - Watch the count. Three agents running in parallel already puts you at DORA's limit of three active branches. That is fine if all three land today. Plain git does all of it. git worktree gives each task its own folder and branch, so parallel agents never share a checkout: # start a task: own branch, own folder, cut from main git switch main && git pull --ff-only git worktree add -b task/fix-login ../fix-login # ...the agent works in ../fix-login and commits... # land it the same day: refresh main first git pull --ff-only git -C ../fix-login rebase main git merge --ff-only task/fix-login git push git worktree remove ../fix-login git branch -d task/fix-login If your team merges through pull requests, push the branch and run gh pr create --fill from the worktree instead of the local merge. The rule stays the same: the PR is opened and reviewed the day the agent finishes. To see how far you are from DORA's numbers, list local branches by their last commit, oldest first: git for-each-ref refs/heads --sort=committerdate \ --format='%(committerdate:relative) %(refname:short)' Any unmerged branch near the top whose last commit says "days ago" has missed the once-a-day merge. Where Hermes fits I build Hermes IDE, so weigh this section with that in mind. You don't need it for any of the above: the git commands are the whole technique. Hermes is built around the same shape. It runs Claude Code, Codex and other agent CLIs side by side, each in its own terminal, and ⌘N (Ctrl+Shift+N on Windows and Linux) starts each task on its own hermes/<name> branch in its own worktree, with the task as the agent's first prompt. !The Hermes New task sheet with a refund endpoint task typed, chips for Claude Code, the orders-api project, a new hermes/ worktree, Accept edits, model and effort, and a preview of the claude command The ⌘N New task sheet: Claude Code, the orders-api project, a new hermes/ worktree, Accept edits, model and effort, and the "Hermes will run" preview of the claude command. When the agent finishes, the Review Desk (⌘G) shows its changes by turn or by file, with risk flags. Land then commits, opens a pull request or merges locally in one step, into the branch the task started from, and it can be undone. Undo data for a landed task is cleared after 14 days (release notes). Your own checks can decide when a task counts as done, which is where the "tests before commit" rule from DORA's pitfall list belongs. !The Review Desk Worktrees tab listing one Hermes worktree each for orders-api, web-app and orders-types, with each hermes/ branch, task, age and disk size The Worktrees tab: one Hermes worktree each for orders-api, web-app and orders-types, with each worktree's hermes/ branch, task, age and disk size, and the free disk space. Under the hood these are ordinary git branches and worktrees. Hermes is free to download, source-available under BSL 1.1, and runs on macOS, Windows and Linux. It is not affiliated with Nous Research, Anthropic, OpenAI or any agent vendor. Where this take breaks Some work doesn't fit in a day. A schema change with a data backfill, or a framework upgrade that breaks call sites across the codebase, is several tasks wearing one name. Split it into steps that each land on their own, and keep the old path working until the last one is in. Trunk-based development without fast tests ships breakage faster. DORA calls the practice a requirement for continuous integration, which pairs it with fast automated tests after every commit, and lists skipping tests before commit as a pitfall. If your suite takes an hour, fix that before you raise the merge rate. Review is still the bottleneck. The 5x median review time in Faros's data is the warning: small branches only help if a human reads them the day they appear. Short branches also shrink the window in which two parallel agents edit the same file, but they don't close it, so you still sequence work that overlaps. An agent's task is small when it finishes. The only way to make it big again is to let it wait, so land it today. --- If this was useful If you want to try the one-task-one-branch flow with the agents you already pay for, Hermes IDE is a free download and the source is on GitHub. A task stays small more easily when the agent finds the right code before it starts editing, and that is a retrieval problem. My RAG Pocket Guide covers retrieval, chunking and reranking, the ideas you need when a model has to find the right context in a large codebase or docs set before it answers. It is one of 8 short books in the Pocket Guides for Developers series, covering agents, RAG, prompts, observability, events, databases and system design: the whole series is here. 

WinUI 3 cosplay or power tool? Two faces of Bloatynosy, my Windows 11 debloater github.com/builtbybel/Bloatynosy/releases a week in, still figuring out which needs less explaining...🤔 t.co

Web preview (no signup): tryhivecontent.com GitHub: leonidasrocky123-cell/edited-agent Drop a video topic below and I'll run it through the agent for you. #ArtificialIntelligence #OpenSource #BuildInPublic #ContentCreation #VideoEditing #Python

Código em C++ que resolve o problema: #programming #leetcode #dsa #cpplus github.com/ThiagoFBastos/competitive-programming/…

Repo: mrdoob/three.js (MIT license), branch dev, commit fa01dd6 Code: examples/jsm/postprocessing/LUTPass.js and examples/jsm/loaders/LUTCubeLoader.js are used unchanged (only the import path of ShaderPass was adjusted). The pass order follows examples/webgl_postprocessing_3dlut.html: render, OutputPass, then LUTPass. The four .cube LUTs were generated by my own script; no commercial or third-party LUT packs. Scene, lighting, grain pass and video overlay are my own.

kudu ⭐ 4.1k Kudu is a cross-platform tool that removes temporary files, scans for malware, and monitors system performance on Windows, macOS, and Linux. 🔗 AdventDevInc/kudu #opensource t.co

Hi, just vibecoded a smart-app for our not-so smart bubbles - markussstaub-dot/bubble-log

Bend2 laws are great but long, so I built a companion tool: toph. toph check finds counterexamples to your laws in milliseconds, before anyone tries a proof. toph build lets you write laws in a shorter syntax that compiles to plain Bend. oxiglade/toph

Can Free Open-Source Beat Devin? Testing Crewai AI Agent (Full Setup Guide) Stop paying expensive monthly API subscriptions! In today's deep dive, we put Crewai (32,000 GitHub Stars) through the ultimate real-world developer capability benchmark on DailyDev AI. 👉 Grab the official GitHub Repository: crewAIInc/crewAI ========================================================================= ⏳ TIMESTAMPS & CHAPTERS (WATCH BEFORE YOU DEPLOY): 00:00 The Closed AI Subscription Trap & Monthly API Bills 00:48 Why Developers Are Switching to Crewai 01:35 Codebase Architecture & Under-The-Hood Tour 02:20 Step-by-Step Live Terminal Sandbox Installation 03:45 Real-World Capability Benchmark & Memory Consumption 04:50 Production Score, Gotchas & Final Engineering Verdict ========================================================================= 🔍 WHAT IS CREWAI & HOW DOES IT WORK? Framework for orchestrating role-playing, autonomous AI agents. Foster collaborative intelligence. ⚡ KEY DEVELOPER HIGHLIGHTS: • 100% Free & Open-Source: Full codebase transparency under open license • Localhost Privacy: Zero data tracking, zero telemetry, full offline support • Written in Python: Exceptional performance with minimal system overhead • Massive Community Adoption: 32,000+ developers on GitHub 💻 STEP-BY-STEP TERMINAL INSTALLATION COMMANDS: git clone crewAIInc/crewAI cd CrewAI python -m venv .venv .venv\Scripts\activate # On Linux/macOS: source .venv/bin/activate pip install -e . ========================================================================= 🔔 SUBSCRIBE TO DAILYDEV AI: We test and break down two brand-new trending open-source AI repositories every single day at US Peak Time (11:00 AM EST & 5:00 PM EST). Subscribe and hit the bell so you never miss the next viral open-source AI tool! #OpenSourceAI #LocalLLM #AIAgents #Python #DeveloperTools #DailyDevAI [ar] هل يمكن للمصادر المفتوحة المجانية التفوق على Devin؟ اختبار وكيل CrewAI للذكاء الاصطناعي (دليل الإ... توقف عن دفع اشتراكات واجهات برمجة التطبيقات الشهرية الباهظة! في هذا التحليل المعمق، قمنا باختبار قدرات مطوري Crewai (الحائزة على 32,000 نجمة على GitHub) باستخدام منصة DailyDev AI، وهو اختبار عملي شامل. 👈 حمّل مستودع GitHub الرسمي: crewAIInc/crewAI ========================================================================== ⏳ الفواصل الزمنية والفصول (شاهد قبل النشر): 00:00 فخ اشتراك الذكاء الاصطناعي المغلق وفواتير واجهة برمجة التطبيقات الشهرية 00:48 لماذا يتحول المطورون إلى Crewai 01:35 بنية قاعدة البيانات وجولة في تفاصيلها الداخلية 02:20 تثبيت بيئة الاختبار الطرفية المباشرة خطوة بخطوة 03:45 معيار الأداء العملي واستهلاك الذاكرة 04:50 نتيجة الإنتاج، والمشاكل المحتملة، والهندسة النهائية الخلاصة ========================================================================= 🔍 ما هو Crewai وكيف يعمل؟ إطار عمل لتنظيم وكلاء الذكاء الاصطناعي المستقلين الذين يتقمصون الأدوار. تعزيز الذكاء التعاوني. ⚡ أبرز مميزات المطورين: • مجاني بالكامل ومفتوح المصدر: شفافية كاملة لقاعدة الكود بموجب ترخيص مفتوح • خصوصية تامة على الخادم المحلي: لا تتبع للبيانات، ولا قياس عن بُعد، ودعم كامل للعمل دون اتصال بالإنترنت • مكتوب بلغة بايثون: أداء استثنائي مع أقل قدر من استهلاك موارد النظام • اعتماد واسع النطاق من قبل المجتمع: أكثر من 32,000 مطور على GitHub 💻 أوامر التثبيت عبر سطر الأوامر خطوة بخطوة: git clone crewAIInc/crewAI cd CrewAI python -m venv .venv .venv\Scripts\activate # على أنظمة Linux/macOS: source .venv/bin/activate pip install -e . ========================================================================= 🔔 اشترك في قناة DailyDev AI: نختبر ونحلل مستودعين جديدين من مستودعات الذكاء الاصطناعي مفتوحة المصدر الرائجة يوميًا في أوقات الذروة في الولايات المتحدة (11:00 صباحًا و5:00 مساءً بتوقيت شرق الولايات المتحدة). اشترك وفعل جرس التنبيهات لتصلك آخر أخبار أدوات الذكاء الاصطناعي مفتوحة المصدر الرائجة! #OpenSourceAI #LocalLLM #AIAgents #Python #DeveloperTools #DailyDevAI [bn] ফ্রি ওপেন সোর্স কি Devin-কে হারাতে পারবে? CrewAI এআই এজেন্ট পরীক্ষা (ফুল সেটআপ গাইড) দামী মাসিক এপিআই সাবস্ক্রিপশনের টাকা দেওয়া বন্ধ করুন! আজকের এই গভীর বিশ্লেষণে, আমরা ডেইলিডেভ এআই-তে ক্রুওয়াইকে (৩২,০০০ গিটহাব স্টার) ডেভেলপারদের সক্ষমতা যাচাইয়ের চূড়ান্ত বাস্তব-জগতের পরীক্ষায় ফেলেছি। 👉 অফিসিয়াল গিটহাব রিপোজিটরি ডাউনলোড করুন: crewAIInc/crewAI ========================================================================= ⏳ টাইমস্ট্যাম্প ও অধ্যায়সমূহ (ডিপ্লয় করার আগে দেখুন): ০০:০০ ক্লোজড এআই সাবস্ক্রিপশনের ফাঁদ এবং মাসিক এপিআই বিল ০০:৪৮ কেন ডেভেলপাররা Crewai-তে ঝুঁকছেন ০১:৩৫ কোডবেস আর্কিটেকচার এবং এর ভেতরের কার্যপ্রণালী ০২:২০ ধাপে ধাপে লাইভ টার্মিনাল স্যান্ডবক্স ইনস্টলেশন ০৩:৪৫ বাস্তব-জগতের সক্ষমতা বেঞ্চমার্ক এবং মেমরি খরচ ০৪:৫০ প্রোডাকশন স্কোর, সম্ভাব্য সমস্যা এবং চূড়ান্ত ইঞ্জিনিয়ারিং রায় ========================================================================= 🔍 CREWAI কী এবং এটি কীভাবে কাজ করে? ভূমিকা-পালনকারী, স্বায়ত্তশাসিত এআই এজেন্টদের সমন্বয় সাধনের জন্য একটি ফ্রেমওয়ার্ক। সহযোগিতামূলক বুদ্ধিমত্তাকে উৎসাহিত করে। ⚡ ডেভেলপারদের জন্য বিশেষ আকর্ষণ: • ১০০% ফ্রি ও ওপেন-সোর্স: ওপেন লাইসেন্সের অধীনে সম্পূর্ণ কোডবেস স্বচ্ছতা • লোকালহোস্টের গোপনীয়তা: কোনো ডেটা ট্র্যাকিং নেই, কোনো টেলিমেট্রি নেই, সম্পূর্ণ অফলাইন সাপোর্ট • পাইথনে লেখা: ন্যূনতম সিস্টেম ওভারহেড সহ অসাধারণ পারফরম্যান্স • বিশাল কমিউনিটির সমর্থন: গিটহাবে ৩২,০০০-এর বেশি ডেভেলপার 💻 ধাপে ধাপে টার্মিনাল ইনস্টলেশনের কমান্ড: git clone crewAIInc/crewAI cd CrewAI python -m venv .venv .venv\Scripts\activate # লিনাক্স/ম্যাকওএস-এ: source .venv/bin/activate pip install -e . ========================================================================= 🔔 ডেইলিডেভ এআই-তে সাবস্ক্রাইব করুন: আমরা প্রতিদিন ইউএস পিক টাইমে (সকাল ১১:০০ EST এবং বিকাল ৫:০০ EST) দুটি একেবারে নতুন এবং ট্রেন্ডিং ওপেন-সোর্স এআই রিপোজিটরি পরীক্ষা ও বিশ্লেষণ করি। সাবস্ক্রাইব করুন এবং বেল আইকনে ক্লিক করুন, যাতে আপনি পরবর্তী ভাইরাল ওপেন-সোর্স এআই টুলটি কখনো মিস না করেন! #OpenSourceAI #LocalLLM #AIAgents #Python #DeveloperTools #DailyDevAI [de-DE] Kann kostenlose Open-Source Devin schlagen? CrewAI-KI-Agent im Test (Vollständige Einrichtungsanl... Schluss mit teuren monatlichen API-Abonnements! In unserem heutigen Deep Dive unterziehen wir Crewai (32.000 GitHub-Sterne) dem ultimativen Praxistest für Entwicklerfähigkeiten auf DailyDev AI. ... 👉 Hol dir das offizielle GitHub-Repository: crewAIInc/crewAI ============================================================================ ⏳ ZEITSTEMPEL & KAPITEL (VOR DEM SETUP ANSEHEN): 00:00 Die Falle geschlossener KI-Abonnements & monatliche API-Rechnungen 00:48 Warum Entwickler zu Crewai wechseln 01:35 Codebasis-Architektur & Einblick in die Funktionsweise 02:20 Schritt-für-Schritt-Installation in der Live-Terminal-Sandbox 03:45 Leistungsvergleich & Speicherverbrauch in der Praxis 04:50 Ergebnisse in der Produktion, Fallstricke & abschließende technische Optimierung Urteil ========================================================================== 🔍 WAS IST CREWAI UND WIE FUNKTIONIERT ES? Ein Framework zur Orchestrierung von rollenspielenden, autonomen KI-Agenten. Fördert kollaborative Intelligenz. ⚡ WICHTIGSTE ENTWICKLER-HIGHLIGHTS: • 100 % kostenlos & Open Source: Volle Transparenz des Quellcodes unter einer offenen Lizenz • Datenschutz auf dem lokalen Rechner: Keine Datenerfassung, keine Telemetrie, volle Offline-Unterstützung • Geschrieben in Python: Hervorragende Performance bei minimalem Systemaufwand • Große Community: Über 32.000 Entwickler auf GitHub 💻 SCHRITT-FÜR-SCHRITT-ANLEITUNG ZUR TERMINALINSTALLATION: git clone crewAIInc/crewAI cd CrewAI python -m venv .venv .venv\Scripts\activate # Unter Linux/macOS: source .venv/bin/activate pip install -e . ========================================================================== 🔔 ABONNIEREN SIE DAILYDEV AI: Wir testen und analysieren täglich zwei brandneue, trendige Open-Source-KI-Repositories zur US-amerikanischen Spitzenzeit (11:00 Uhr EST & 17:00 Uhr EST). Abonnieren Sie uns und aktivieren Sie die Benachrichtigungen, um kein virales Open-Source-KI-Tool mehr zu verpassen! #OpenSourceAI #LocalLLM #AIAgents #Python #DeveloperTools #DailyDevAI [es-US] ¿Puede el código abierto gratuito superar a Devin? Probando el agente de IA de CrewAI (Guía de co... ¡Deja de pagar costosas suscripciones mensuales a API! En este análisis exhaustivo, sometimos a Crewai (32 000 estrellas en GitHub) a la prueba de rendimiento definitiva para desarrolladores en el mundo real, realizada por DailyDev AI. 👉 Descarga el repositorio oficial de GitHub: crewAIInc/crewAI =========================================================================== ⏳ MARCAS DE TIEMPO Y CAPÍTULOS (VER ANTES DE IMPLEMENTAR): 00:00 La trampa de las suscripciones de IA cerradas y las facturas mensuales de la API 00:48 Por qué los desarrolladores se están pasando a Crewai 01:35 Arquitectura del código base y análisis interno 02:20 Instalación paso a paso del entorno de pruebas en vivo 03:45 Prueba de rendimiento y consumo de memoria en entornos reales 04:50 Puntuación de producción, posibles problemas y análisis final de ingeniería Veredicto ========================================================================= 🔍 ¿QUÉ ES CREWAI Y CÓMO FUNCIONA? Marco para la orquestación de agentes de IA autónomos con capacidad de juego de roles. Fomenta la inteligencia colaborativa. ⚡ CARACTERÍSTICAS PRINCIPALES PARA DESARROLLADORES: • 100 % gratuito y de código abierto: Transparencia total del código bajo licencia abierta • Privacidad en localhost: Sin seguimiento de datos, sin telemetría, soporte completo sin conexión • Escrito en Python: Rendimiento excepcional con mínima sobrecarga del sistema • Gran adopción por parte de la comunidad: Más de 32 000 desarrolladores en GitHub 💻 INSTRUCCIONES DE INSTALACIÓN PASO A PASO EN LA TERMINAL: git clone crewAIInc/crewAI cd CrewAI python -m venv .venv .venv\Scripts\activate # En Linux/macOS: source .venv/bin/activate pip install -e . =========================================================================== 🔔 SUSCRÍBETE A DAILYDEV AI: Probamos y analizamos dos nuevos repositorios de IA de código abierto que marcan tendencia todos los días durante la hora pico en EE. UU. (11:00 a. m. EST y 5:00 p. m. EST). ¡Suscríbete y activa las notificaciones para no perderte la próxima herramienta viral de IA de código abierto! #OpenSourceAI #LocalLLM #AIAgents #Python #DeveloperTools #DailyDevAI [fr-FR] L'open source gratuit peut-il surpasser Devin ? Test de l'agent IA CrewAI (Guide d'installation c... Arrêtez de payer des abonnements API mensuels hors de prix ! Dans cette analyse approfondie, nous avons soumis Crewai (32 000 étoiles sur GitHub) au test ultime de performance pour développeurs en conditions réelles sur DailyDev AI. 👉 Téléchargez le dépôt GitHub officiel : crewAIInc/crewAI ========================================================================= ⏳ HORODATAGE ET CHAPITRES (À VISIONNER AVANT LE DÉPLOIEMENT) : 00:00 Le piège des abonnements IA fermés et les factures API mensuelles 00:48 Pourquoi les développeurs optent pour Crewai 01:35 Architecture du code et visite guidée 02:20 Installation pas à pas du bac à sable en direct 03:45 Évaluation des performances en conditions réelles et consommation de mémoire 04:50 Résultats en production, points faibles et verdict technique final ========================================================================= 🔍 QU'EST-CE QUE CREWAI ET COMMENT ÇA MARCHE ? Framework pour orchestrer des agents IA autonomes de jeu de rôle. Favorisez l'intelligence collaborative. ⚡ POINTS FORTS POUR LES DÉVELOPPEURS : • 100 % gratuit et open source : transparence totale du code source sous licence libre • Confidentialité en local : aucune donnée collectée, aucune télémétrie, fonctionnement hors ligne complet • Écrit en Python : performances exceptionnelles avec une charge système minimale • Forte adoption par la communauté : plus de 32 000 développeurs sur GitHub 💻 COMMANDES D'INSTALLATION PAS À PAS : git clone crewAIInc/crewAI cd CrewAI python -m venv .venv .venv\Scripts\activate # Sous Linux/macOS : source .venv/bin/activate pip install -e . ========================================================================= 🔔 ABONNEZ-VOUS À DAILYDEV AI : Chaque jour, aux heures de pointe aux États-Unis (11 h et 17 h HNE), nous testons et analysons deux nouveaux dépôts d’IA open source très populaires. Abonnez-vous et activez les notifications pour ne manquer aucun outil d’IA open source viral ! #OpenSourceAI #LocalLLM #AIAgents #Python #DeveloperTools #DailyDevAI [hi] क्या मुफ्त ओपन-सोर्स Devin को मात दे सकता है? CrewAI AI एजेंट का परीक्षण (पूर्ण सेटअप गाइड) महंगे मासिक एपीआई सब्सक्रिप्शन का भुगतान करना बंद करें! आज के इस विस्तृत विश्लेषण में, हम डेलीडेव एआई पर क्रेवाई (32,000 गिटहब स्टार्स) की वास्तविक दुनिया की डेवलपर क्षमता का सबसे कठिन परीक्षण करेंगे। 👉 आधिकारिक GitHub रिपॉजिटरी डाउनलोड करें: crewAIInc/crewAI ========================================================================= ⏳ टाइमस्टैम्प और अध्याय (तैनाती से पहले देखें): 00:00 बंद AI सदस्यता का जाल और मासिक API बिल 00:48 डेवलपर Crewai की ओर क्यों रुख कर रहे हैं 01:35 कोडबेस आर्किटेक्चर और आंतरिक कार्यप्रणाली का अवलोकन 02:20 चरण-दर-चरण लाइव टर्मिनल सैंडबॉक्स इंस्टॉलेशन 03:45 वास्तविक दुनिया में क्षमता का बेंचमार्क और मेमोरी खपत 04:50 प्रोडक्शन स्कोर, कमियां और अंतिम इंजीनियरिंग निर्णय ========================================================================= 🔍 Crewai क्या है और यह कैसे काम करता है? रोल-प्लेइंग और स्वायत्त एआई एजेंटों के समन्वय हेतु फ्रेमवर्क। सहयोगात्मक बुद्धिमत्ता को बढ़ावा देता है। ⚡ प्रमुख डेवलपर विशेषताएँ: • 100% मुफ़्त और ओपन-सोर्स: ओपन लाइसेंस के तहत पूर्ण कोडबेस पारदर्शिता • लोकलहोस्ट गोपनीयता: शून्य डेटा ट्रैकिंग, शून्य टेलीमेट्री, पूर्ण ऑफ़लाइन समर्थन • पायथन में लिखा गया: न्यूनतम सिस्टम ओवरहेड के साथ असाधारण प्रदर्शन • व्यापक सामुदायिक स्वीकृति: GitHub पर 32,000+ डेवलपर 💻 चरण-दर-चरण टर्मिनल इंस्टॉलेशन कमांड: git clone crewAIInc/crewAI cd CrewAI python -m venv .venv .venv\Scripts\activate # Linux/macOS पर: source .venv/bin/activate pip install -e . ========================================================================= 🔔 डेलीडेव एआई को सब्सक्राइब करें: हम हर दिन अमेरिका के पीक टाइम (सुबह 11:00 बजे ईएसटी और शाम 5:00 बजे ईएसटी) पर दो बिल्कुल नए और ट्रेंडिंग ओपन-सोर्स एआई रिपॉजिटरी का परीक्षण और विश्लेषण करते हैं। सब्सक्राइब करें और बेल आइकन दबाएं ताकि आप किसी भी नए वायरल ओपन-सोर्स एआई टूल को मिस न करें! #OpenSourceAI #LocalLLM #AIAgents #Python #DeveloperTools #DailyDevAI [id] Bisakah Open-Source Gratis Mengalahkan Devin? Menguji Agen AI CrewAI (Panduan Pengaturan Lengkap) Berhenti membayar biaya langganan API bulanan yang mahal! Dalam ulasan mendalam hari ini, kami menguji Crewai (32.000 Bintang GitHub) melalui tolok ukur kemampuan pengembang dunia nyata terbaik di DailyDev AI. 👉 Unduh Repositori GitHub resmi: crewAIInc/crewAI ========================================================================= ⏳ CAP WAKTU & BAB (TONTON SEBELUM ANDA MENGGUNAKAN): 00:00 Jebakan Langganan AI Tertutup & Tagihan API Bulanan 00:48 Mengapa Pengembang Beralih ke Crewai 01:35 Arsitektur Basis Kode & Tur di Balik Layar 02:20 Instalasi Sandbox Terminal Langsung Langkah demi Langkah 03:45 Tolok Ukur Kemampuan Dunia Nyata & Konsumsi Memori 04:50 Skor Produksi, Masalah yang Perlu Diperhatikan & Keputusan Teknik Akhir ========================================================================= 🔍 APA ITU CREWAI & BAGAIMANA CARA KERJANYA? Kerangka kerja untuk mengatur agen AI otonom yang berperan. Mendorong kecerdasan kolaboratif. ⚡ SOROTAN PENGEMBANG UTAMA: • 100% Gratis & Sumber Terbuka: Transparansi basis kode penuh di bawah lisensi terbuka • Privasi Localhost: Nol pelacakan data, nol telemetri, dukungan offline penuh • Ditulis dalam Python: Kinerja luar biasa dengan overhead sistem minimal • Adopsi Komunitas Besar: 32.000+ pengembang di GitHub 💻 PERINTAH INSTALASI TERMINAL LANGKAH DEMI LANGKAH: git clone crewAIInc/crewAI cd CrewAI python -m venv .venv .venv\Scripts\activate # Di Linux/macOS: source .venv/bin/activate pip install -e . ========================================================================= 🔔 BERLANGGANAN DAILYDEV AI: Kami menguji dan menganalisis dua repositori AI open-source terbaru yang sedang tren setiap hari pada Waktu Puncak AS (11:00 AM EST & 5:00 PM EST). Berlangganan dan tekan lonceng agar Anda tidak pernah melewatkan alat AI open-source viral berikutnya! #OpenSourceAI #LocalLLM #AIAgents #Python #DeveloperTools #DailyDevAI [it] L'open source gratuito può battere Devin? Testiamo l'agente AI CrewAI (Guida completa alla config... Smettetela di pagare costosi abbonamenti mensili alle API! Nell'analisi approfondita di oggi, abbiamo messo alla prova Crewai (32.000 stelle su GitHub) con il benchmark definitivo delle capacità di sviluppo nel mondo reale di DailyDev AI. 👉 Scarica il repository GitHub ufficiale: crewAIInc/crewAI ========================================================================== ⏳ INDICE DEI CONTENUTI E CAPITOLI (GUARDA PRIMA DI DISTRIBUIRE): 00:00 La trappola dell'abbonamento AI chiuso e le fatture API mensili 00:48 Perché gli sviluppatori stanno passando a Crewai 01:35 Architettura del codice sorgente e tour interno 02:20 Installazione passo passo della sandbox del terminale live 03:45 Benchmark delle capacità reali e consumo di memoria 04:50 Punteggio di produzione, insidie ​​e ingegneria finale Verdetto =========================================================================== 🔍 COS'È CREWAI E COME FUNZIONA? Framework per orchestrare agenti IA autonomi che interpretano ruoli. Promuove l'intelligenza collaborativa. ⚡ PUNTI SALIENTI DELLO SVILUPPATORE: • 100% gratuito e open source: completa trasparenza del codice sorgente con licenza open source • Privacy in locale: nessun tracciamento dei dati, nessuna telemetria, supporto offline completo • Scritto in Python: prestazioni eccezionali con un sovraccarico di sistema minimo • Ampia adozione da parte della community: oltre 32.000 sviluppatori su GitHub 💻 COMANDI DI INSTALLAZIONE DA TERMINALE PASSO PASSO: git clone crewAIInc/crewAI cd CrewAI python -m venv .venv .venv\Scripts\activate # Su Linux/macOS: source .venv/bin/activate pip install -e . =========================================================================== 🔔 ISCRIVITI A DAILYDEV AI: Ogni giorno, durante l'orario di punta negli Stati Uniti (11:00 EST e 17:00 EST), testiamo e analizziamo due nuovissimi repository di IA open source di tendenza. Iscriviti e attiva le notifiche per non perderti il ​​prossimo strumento di IA open source virale! #OpenSourceAI #LocalLLM #AIAgents #Python #DeveloperTools #DailyDevAI [iw] האם קוד פתוח חינמי יכול לנצח את Devin? בדיקת סוכן ה-AI של CrewAI (מדריך התקנה מלא) הפסיקו לשלם מנויים חודשיים יקרים עבור API! בבדיקה מעמיקה של היום, בדקנו את קריוואי (32,000 כוכבי GitHub) באמצעות מדד היכולות האולטימטיבי של פיתוח בעולם האמיתי בבינה מלאכותית של DailyDev. 👉 הורידו את מאגר GitHub הרשמי: crewAIInc/crewAI ========================================================================= ⏳ חותמות זמן ופרקים (צפו לפני הפריסה): 00:00 מלכודת המנוי הסגורה לבינה מלאכותית וחיובי API חודשיים 00:48 מדוע מפתחים עוברים ל-Crewai 01:35 ארכיטקטורת בסיס קוד וסיור מתחת למכסה המנוע 02:20 התקנת ארגז חול של טרמינל חי שלב אחר שלב 03:45 מדד יכולות בעולם האמיתי וצריכת זיכרון 04:50 ציון ייצור, תקלות ופסק דין הנדסי סופי ======================================================================== 🔍 מה זה CREWAI ואיך זה עובד? מסגרת לתזמור משחקי תפקידים, סוכני בינה מלאכותית אוטונומיים. טיפוח אינטליגנציה שיתופית. ⚡ נקודות עיקריות של המפתחים: • 100% חופשי וקוד פתוח: שקיפות מלאה של בסיס הקוד תחת רישיון פתוח • פרטיות Localhost: אפס מעקב נתונים, אפס טלמטריה, תמיכה מלאה במצב לא מקוון • נכתב בפייתון: ביצועים יוצאי דופן עם תקורת מערכת מינימלית • אימוץ קהילתי מסיבי: מעל 32,000 מפתחים ב-GitHub 💻 פקודות התקנה שלב אחר שלב במסוף: git clone crewAIInc/crewAI cd CrewAI python -m venv .venv .venv\Scripts\activate # ב-Linux/macOS: source .venv/bin/activate pip install -e . ========================================================================== 🔔 הירשמו ל-DAILYDEV AI: אנו בודקים ומנתחים שני מאגרי קוד פתוח חדשים ומגוונים בכל יום בשעות השיא של ארה"ב (11:00 בבוקר שעון EST ו-17:00 אחר הצהריים שעון EST). הירשמו ולחצו על הפעמון כדי שלעולם לא תפספסו את כלי ה-AI הוויראלי הבא בקוד פתוח! #OpenSourceAI #LocalLLM #AIAgents #Python #DeveloperTools #DailyDevAI [ja] 無料のオープンソースはDevinに勝てるのか？CrewAIエージェントの検証（完全セットアップガイド） 高額な月額API利用料はもう不要！今回の徹底分析では、Crewai（GitHubスター数32,000）をDailyDev AI上で究極の実世界開発者能力ベンチマークテストにかけました。 👉 公式GitHubリポジトリはこちら：crewAIInc/crewAI =========================================================================== ⏳ タイムスタンプとチャプター（デプロイ前に必ずご覧ください）： 00:00 クローズドAIサブスクリプションの落とし穴と月額API料金 00:48 開発者がCrewaiに移行する理由 01:35 コードベースアーキテクチャと内部構造ツアー 02:20 ライブターミナルサンドボックスのインストール手順 03:45 実環境での性能ベンチマークとメモリ消費量 04:50 本番環境でのスコア、注意点、最終エンジニアリング評決 =========================================================================== 🔍 CREWAIとは何か、そしてどのように機能するのか？ ロールプレイングを行う自律型AIエージェントをオーケストレーションするためのフレームワーク。協調的な知能を促進します。 ⚡ 主な開発者向け特長： • 100%無料＆オープンソース：オープンライセンスによる完全なコードベース透明性 • ローカルホストのプライバシー：データ追跡なし、テレメトリなし、完全オフライン対応 • Pythonで記述：最小限のシステム負荷で卓越したパフォーマンスを実現 • 大規模なコミュニティによる採用：GitHubには32,000人以上の開発者が参加 💻 ターミナルでのインストール手順： git clone crewAIInc/crewAI cd CrewAI python -m venv .venv .venv\Scripts\activate # Linux/macOSの場合：source .venv/bin/activate pip install -e . ============================================================================ 🔔 DAILYDEV AI を購読してください: 私たちは、米国ピークタイム (東部標準時午前 11:00 と午後 5:00) に、毎日 2 つの最新の話題のオープンソース AI リポジトリをテストし、分析しています。購読してベルマークをクリックすれば、次に話題のオープンソース AI ツールを見逃すことはありません！ #OpenSourceAI #LocalLLM #AIAgents #Python #DeveloperTools #DailyDevAI [ko] 무료 오픈 소스가 Devin을 이길 수 있을까? CrewAI AI 에이전트 테스트 (전체 설정 가이드) 더 이상 비싼 월별 API 구독료를 지불하지 마세요! 이번 심층 분석에서는 DailyDev AI를 사용하여 Crewai(GitHub 스타 32,000개)의 실제 개발자 역량을 극한까지 끌어올린 벤치마크 테스트를 진행했습니다. 👉 공식 GitHub 저장소에서 다운로드하세요: crewAIInc/crewAI ============================================================================ ⏳ 타임스탬프 및 목차 (배포 전 시청): 00:00 폐쇄형 AI 구독의 함정 및 월별 API 요금 00:48 개발자들이 Crewai로 전환하는 이유 01:35 코드베이스 아키텍처 및 내부 작동 방식 살펴보기 02:20 단계별 라이브 터미널 샌드박스 설치 03:45 실제 성능 벤치마크 및 메모리 사용량 04:50 실제 운영 환경 점수, 주의 사항 및 최종 엔지니어링 결론 ============================================================================= 🔍 CREWAI란 무엇이며 어떻게 작동하나요? 롤플레잉 및 자율 AI 에이전트를 조율하는 프레임워크입니다. 협업 지능을 향상시킵니다. ⚡ 주요 개발자 특징: • 100% 무료 오픈 소스: 오픈 라이선스 하에 코드베이스 전체 공개 • 로컬 환경 개인정보 보호: 데이터 추적 및 원격 측정 없음, 완벽한 오프라인 지원 • Python으로 작성: 최소한의 시스템 오버헤드로 뛰어난 성능 제공 • 활발한 커뮤니티 참여: GitHub에 32,000명 이상의 개발자 참여 💻 단계별 터미널 설치 명령어: git clone crewAIInc/crewAI cd CrewAI python -m venv .venv .venv\Scripts\activate # Linux/macOS: source .venv/bin/activate pip install -e . =========================================================================== 🔔 DAILYDEV AI 구독하기: 저희는 매일 미국 피크 시간대(오전 11시 및 오후 5시, 동부 표준시)에 새롭게 떠오르는 오픈 소스 AI 저장소 두 개를 테스트하고 분석합니다. 구독하고 알림 벨을 눌러 새롭게 주목받는 오픈 소스 AI 도구를 놓치지 마세요! #OpenSourceAI #LocalLLM #AIAgents #Python #DeveloperTools #DailyDevAI [ml] സൗജന്യ ഓപ്പൺ സോഴ്‌സിന് Devin-നെ മറികടക്കാനാകുമോ? CrewAI AI ഏജന്റ് പരീക്ഷണം (സമ്പൂർണ്ണ സെറ്റപ്പ് ഗ... ചെലവേറിയ പ്രതിമാസ API സബ്‌സ്‌ക്രിപ്‌ഷനുകൾ നൽകുന്നത് നിർത്തൂ! ഇന്നത്തെ ആഴത്തിലുള്ള പഠനത്തിൽ, ഡെയ്‌ലിഡെവ് AI-യിലെ ആത്യന്തിക യഥാർത്ഥ ലോക ഡെവലപ്പർ ശേഷി മാനദണ്ഡത്തിൽ ഞങ്ങൾ ക്രെവായിയെ (32,000 GitHub സ്റ്റാർസ്) ഉൾപ്പെടുത്തുന്നു. 👉 ഔദ്യോഗിക GitHub ശേഖരം നേടുക: crewAIInc/crewAI ================================================================================================================= ⏳ ടൈംസ്റ്റാമ്പുകളും അധ്യായങ്ങളും (നിങ്ങൾ വിന്യസിക്കുന്നതിന് മുമ്പ് കാണുക): 00:00 അടച്ച AI സബ്‌സ്‌ക്രിപ്‌ഷൻ ട്രാപ്പും പ്രതിമാസ API ബില്ലുകളും 00:48 ഡെവലപ്പർമാർ ക്രെവായ്യിലേക്ക് മാറുന്നതിന്റെ കാരണം 01:35 കോഡ്‌ബേസ് ആർക്കിടെക്ചറും അണ്ടർ-ദി-ഹുഡ് ടൂറും 02:20 ഘട്ടം ഘട്ടമായുള്ള ലൈവ് ടെർമിനൽ സാൻഡ്‌ബോക്‌സ് ഇൻസ്റ്റാളേഷൻ 03:45 റിയൽ-വേൾഡ് കപ്പാബിലിറ്റി ബെഞ്ച്മാർക്കും മെമ്മറി ഉപഭോഗവും 04:50 പ്രൊഡക്ഷൻ സ്‌കോർ, ഗോച്ചകളും അന്തിമ എഞ്ചിനീയറിംഗും വിധി ============================================================================= 🔍 ക്രൂവൈ എന്താണ്, അത് എങ്ങനെ പ്രവർത്തിക്കുന്നു? റോൾ പ്ലേയിംഗ്, സ്വയംഭരണ AI ഏജന്റുമാരെ സംഘടിപ്പിക്കുന്നതിനുള്ള ചട്ടക്കൂട്. സഹകരണ ബുദ്ധി വളർത്തുക. ⚡ പ്രധാന ഡെവലപ്പർ ഹൈലൈറ്റുകൾ: • 100% സൗജന്യവും ഓപ്പൺ സോഴ്‌സും: ഓപ്പൺ ലൈസൻസിന് കീഴിൽ പൂർണ്ണ കോഡ്‌ബേസ് സുതാര്യത • ലോക്കൽഹോസ്റ്റ് സ്വകാര്യത: സീറോ ഡാറ്റ ട്രാക്കിംഗ്, സീറോ ടെലിമെട്രി, പൂർണ്ണ ഓഫ്‌ലൈൻ പിന്തുണ • പൈത്തണിൽ എഴുതിയത്: കുറഞ്ഞ സിസ്റ്റം ഓവർഹെഡുള്ള അസാധാരണമായ പ്രകടനം • വമ്പിച്ച കമ്മ്യൂണിറ്റി അഡോപ്ഷൻ: GitHub-ൽ 32,000+ ഡെവലപ്പർമാർ 💻 ഘട്ടം ഘട്ടമായുള്ള ടെർമിനൽ ഇൻസ്റ്റാളേഷൻ കമാൻഡുകൾ: git clone crewAIInc/crewAI cd CrewAI python -m venv .venv .venv\Scripts\activate # Linux/macOS-ൽ: source .venv/bin/activate pip install -e . ================================================================================= 🔔 DAILYDEV AI-ലേക്ക് സബ്‌സ്‌ക്രൈബ് ചെയ്യുക: US പീക്ക് ടൈമിൽ (11:00 AM EST & 5:00 PM EST) ഞങ്ങൾ എല്ലാ ദിവസവും രണ്ട് പുതിയ ട്രെൻഡിംഗ് ഓപ്പൺ സോഴ്‌സ് AI ശേഖരണങ്ങൾ പരീക്ഷിച്ച് വിശകലനം ചെയ്യുന്നു. അടുത്ത വൈറൽ ഓപ്പൺ സോഴ്‌സ് AI ടൂൾ ഒരിക്കലും നഷ്ടപ്പെടുത്താതിരിക്കാൻ സബ്‌സ്‌ക്രൈബ് ചെയ്‌ത് ബെൽ അമർത്തുക! #OpenSourceAI #LocalLLM #AIAgents #Python #DeveloperTools #DailyDevAI [nl-NL] Kan gratis open-source winnen van Devin? CrewAI AI-agent testen (Volledige installatiehandleiding) Stop met het betalen van dure maandelijkse API-abonnementen! In deze diepgaande analyse onderwerpen we Crewai (32.000 GitHub-sterren) aan de ultieme praktijktest voor ontwikkelaarsvaardigheden op DailyDev AI. 👉 Download de officiële GitHub-repository: crewAIInc/crewAI =========================================================================== ⏳ TIJDSTEMPELS & HOOFDSTUKKEN (BEKIJK DIT VOORDAT JE IMPLEMENTEERT): 00:00 De valkuil van gesloten AI-abonnementen en maandelijkse API-facturen 00:48 Waarom ontwikkelaars overstappen op Crewai 01:35 Codearchitectuur en een kijkje achter de schermen 02:20 Stapsgewijze installatie van een live terminal sandbox 03:45 Benchmark van de mogelijkheden in de praktijk en geheugenverbruik 04:50 Productiescore, valkuilen en de uiteindelijke technische specificaties Oordeel ========================================================================== 🔍 WAT IS CREWAI EN HOE WERKT HET? Een framework voor het orkestreren van rollenspelende, autonome AI-agenten. Stimuleert collaboratieve intelligentie. ⚡ BELANGRIJKSTE ONTWIKKELAARSPUNTEN: • 100% gratis en open source: Volledige transparantie van de codebase onder een open licentie • Privacy op localhost: Geen gegevensregistratie, geen telemetrie, volledige offline ondersteuning • Geschreven in Python: Uitzonderlijke prestaties met minimale systeembelasting • Massale community: Meer dan 32.000 ontwikkelaars op GitHub 💻 STAP-VOOR-STAP INSTALLATIECOMMANDO'S VIA DE TERMINAL: git clone crewAIInc/crewAI cd CrewAI python -m venv .venv .venv\Scripts\activate # Op Linux/macOS: source .venv/bin/activate pip install -e . ============================================================================ 🔔 ABONNEER JE OP DAILYDEV AI: We testen en analyseren elke dag twee gloednieuwe, trending open-source AI-repositories tijdens de Amerikaanse piekuren (11:00 uur EST en 17:00 uur EST). Abonneer je en klik op het belletje, zodat je nooit meer de volgende virale open-source AI-tool mist! #OpenSourceAI #LocalLLM #AIAgents #Python #DeveloperTools #DailyDevAI [pa] ਕੀ ਮੁਫ਼ਤ ਓਪਨ-ਸੋਰਸ Devin ਨੂੰ ਮਾਤ ਦੇ ਸਕਦਾ ਹੈ? Crewai AI ਏਜੰਟ ਦੀ ਪਰਖ (ਪੂਰੀ ਸੈੱਟਅੱਪ ਗਾਈਡ) ਮਹਿੰਗੇ ਮਾਸਿਕ API ਸਬਸਕ੍ਰਿਪਸ਼ਨ ਦਾ ਭੁਗਤਾਨ ਕਰਨਾ ਬੰਦ ਕਰੋ! ਅੱਜ ਦੀ ਡੂੰਘੀ ਖੋਜ ਵਿੱਚ, ਅਸੀਂ ਡੇਲੀਡੇਵ ਏਆਈ 'ਤੇ ਕਰੂਵਾਈ (32,000 ਗਿੱਟਹੱਬ ਸਟਾਰ) ਨੂੰ ਅਸਲ-ਸੰਸਾਰ ਵਿਕਾਸਕਾਰ ਸਮਰੱਥਾ ਬੈਂਚਮਾਰਕ ਦੇ ਜ਼ਰੀਏ ਪੇਸ਼ ਕਰਦੇ ਹਾਂ। 👉 ਅਧਿਕਾਰਤ GitHub ਰਿਪੋਜ਼ਟਰੀ ਪ੍ਰਾਪਤ ਕਰੋ: crewAIInc/crewAI = ਫੈਸਲਾ ===================================================================================================== 🔍 ਕ੍ਰੇਵਾਈ ਕੀ ਹੈ ਅਤੇ ਇਹ ਕਿਵੇਂ ਕੰਮ ਕਰਦਾ ਹੈ? ਭੂਮਿਕਾ ਨਿਭਾਉਣ ਵਾਲੇ, ਖੁਦਮੁਖਤਿਆਰ ਏਆਈ ਏਜੰਟਾਂ ਨੂੰ ਆਰਕੇਸਟ੍ਰੇਟ ਕਰਨ ਲਈ ਢਾਂਚਾ। ਸਹਿਯੋਗੀ ਬੁੱਧੀ ਨੂੰ ਉਤਸ਼ਾਹਿਤ ਕਰੋ। ⚡ ਮੁੱਖ ਡਿਵੈਲਪਰ ਹਾਈਲਾਈਟਸ: • 100% ਮੁਫ਼ਤ ਅਤੇ ਓਪਨ-ਸੋਰਸ: ਓਪਨ ਲਾਇਸੈਂਸ ਅਧੀਨ ਪੂਰੀ ਕੋਡਬੇਸ ਪਾਰਦਰਸ਼ਤਾ • ਲੋਕਲਹੋਸਟ ਗੋਪਨੀਯਤਾ: ਜ਼ੀਰੋ ਡਾਟਾ ਟਰੈਕਿੰਗ, ਜ਼ੀਰੋ ਟੈਲੀਮੈਟਰੀ, ਪੂਰੀ ਔਫਲਾਈਨ ਸਹਾਇਤਾ • ਪਾਈਥਨ ਵਿੱਚ ਲਿਖਿਆ: ਘੱਟੋ-ਘੱਟ ਸਿਸਟਮ ਓਵਰਹੈੱਡ ਦੇ ਨਾਲ ਬੇਮਿਸਾਲ ਪ੍ਰਦਰਸ਼ਨ • ਵਿਸ਼ਾਲ ਕਮਿਊਨਿਟੀ ਗੋਦ: GitHub 'ਤੇ 32,000+ ਡਿਵੈਲਪਰ 💻 ਕਦਮ-ਦਰ-ਕਦਮ ਟਰਮੀਨਲ ਇੰਸਟਾਲੇਸ਼ਨ ਹੁਕਮ: git ਕਲੋਨ crewAIInc/crewAI cd CrewAI python -m venv .venv .venv\Scripts\activate # Linux/macOS 'ਤੇ: source .venv/bin/activate pip install -e . == [pl] Czy darmowe oprogramowanie open-source pokona Devina? Testowanie agenta AI CrewAI (Pełny przewodn... Przestań płacić drogie, miesięczne subskrypcje API! W dzisiejszym dogłębnym badaniu poddaliśmy Crewai (32 000 gwiazdek GitHub) najbardziej zaawansowanemu testowi porównawczemu możliwości programistów w świecie rzeczywistym na platformie DailyDev AI. 👉 Pobierz oficjalne repozytorium GitHub: crewAIInc/crewAI ================================================================================= ⏳ ZNACZNIKI CZASU I ROZDZIAŁY (OBEJRZYJ PRZED WDROŻENIEM): 00:00 Pułapka zamkniętej subskrypcji AI i miesięczne rachunki za API 00:48 Dlaczego programiści przechodzą na Crewai 01:35 Architektura bazy kodu i przewodnik po systemie 02:20 Instalacja terminala na żywo krok po kroku w środowisku testowym 03:45 Rzeczywisty benchmark możliwości i zużycie pamięci 04:50 Wynik produkcyjny, pułapki i ostateczna inżynieria Werdykt ================================================================================ 🔍 CZYM JEST CREWAI I JAK DZIAŁA? Framework do organizowania autonomicznych agentów AI odgrywających role. Wspieranie współpracy w zakresie inteligencji. ⚡ NAJWAŻNIEJSZE INFORMACJE DLA DEWELOPERÓW: • 100% darmowy i open-source: Pełna transparentność kodu na podstawie otwartej licencji • Prywatność hosta lokalnego: Brak śledzenia danych, brak telemetrii, pełne wsparcie offline • Napisany w Pythonie: Wyjątkowa wydajność przy minimalnym obciążeniu systemu • Masowa adaptacja społeczności: Ponad 32 000 programistów na GitHubie 💻 POLECENIA INSTALACJI KROK PO KROKU W TERMINALU: git clone crewAIInc/crewAI cd CrewAI python -m venv .venv .venv\Scripts\activate # W systemie Linux/macOS: source .venv/bin/activate pip install -e . ================================================================================ 🔔 SUBSKRYBUJ DAILYDEV AI: Testujemy i analizujemy dwa zupełnie nowe, popularne repozytoria AI typu open source każdego dnia w godzinach szczytu w USA (11:00 EST i 17:00 EST). Zasubskrybuj i kliknij dzwonek, aby nigdy nie przegapić kolejnego viralowego narzędzia AI typu open source! #OpenSourceAI #LocalLLM #AIAgents #Python #DeveloperTools #DailyDevAI [pt-BR] O Open-Source Gratuito Consegue Superar o Devin? Testando Agente de IA da CrewAI (Guia Completo d... Pare de pagar assinaturas mensais caras de API! Nesta análise detalhada, colocamos a Crewai (32.000 estrelas no GitHub) à prova no teste definitivo de capacidade de desenvolvimento do DailyDev AI. 👉 Acesse o repositório oficial do GitHub: crewAIInc/crewAI ========================================================================== ⏳ MARCAÇÕES DE TEMPO E CAPÍTULOS (ASSISTA ANTES DE IMPLANTAR): 00:00 A Armadilha da Assinatura Fechada de IA e as Cobranças Mensais de API 00:48 Por que os Desenvolvedores Estão Migrando para a Crewai 01:35 Arquitetura do Código-Fonte e Visão Interna 02:20 Instalação Passo a Passo do Sandbox de Terminal ao Vivo 03:45 Teste de Desempenho em Condições Reais e Consumo de Memória 04:50 Pontuação de Produção, Armadilhas e Engenharia Final Veredito ========================================================================== 🔍 O QUE É CREWAI E COMO FUNCIONA? Framework para orquestrar agentes de IA autônomos que simulam papéis. Promove a inteligência colaborativa. ⚡ PRINCIPAIS DESTAQUES DO DESENVOLVEDOR: • 100% Gratuito e de Código Aberto: Transparência total do código-fonte sob licença aberta • Privacidade em Localhost: Zero rastreamento de dados, zero telemetria, suporte completo offline • Escrito em Python: Desempenho excepcional com sobrecarga mínima do sistema • Adoção Massiva da Comunidade: Mais de 32.000 desenvolvedores no GitHub 💻 COMANDOS DE INSTALAÇÃO PASSO A PASSO NO TERMINAL: git clone crewAIInc/crewAI cd CrewAI python -m venv .venv .venv\Scripts\activate # No Linux/macOS: source .venv/bin/activate pip install -e . ========================================================================== 🔔 INSCREVA-SE NO DAILYDEV AI: Testamos e analisamos dois novos repositórios de IA de código aberto que estão em alta todos os dias no horário de pico dos EUA (11h e 17h EST). Inscreva-se e ative o sino para nunca perder a próxima ferramenta de IA de código aberto viral! #OpenSourceAI #LocalLLM #AIAgents #Python #DeveloperTools #DailyDevAI [ru] Сможет ли бесплатный Open-Source победить Devin? Тестируем CrewAI (полное руководство по настройке) Прекратите платить за дорогие ежемесячные подписки на API! В сегодняшнем подробном обзоре мы протестировали Crewai (32 000 звезд на GitHub) на DailyDev AI, проведя точный тест на проверку навыков разработчиков в реальных условиях. 👉 Скачайте официальный репозиторий GitHub: crewAIInc/crewAI ========================================================================== ⏳ ВРЕМЕННЫЕ МЕТКИ И РАЗДЕЛЫ (ПРОСМОТРИТЕ ПЕРЕД РАЗВЕРТЫВАНИЕМ): 00:00 Ловушка закрытой подписки на ИИ и ежемесячные счета за API 00:48 Почему разработчики переходят на Crewai 01:35 Архитектура кодовой базы и подробный обзор 02:20 Пошаговая установка песочницы в реальном терминале 03:45 Тест производительности в реальных условиях и потребление памяти 04:50 Оценка производительности в производственной среде, подводные камни и финальная разработка Вердикт ========================================================================= 🔍 ЧТО ТАКОЕ CREWAI И КАК ОН РАБОТАЕТ? Фреймворк для организации ролевых автономных агентов ИИ. Способствует развитию коллективного интеллекта. ⚡ ОСНОВНЫЕ ПРЕИМУЩЕСТВА ДЛЯ РАЗРАБОТЧИКОВ: • 100% бесплатно и с открытым исходным кодом: Полная прозрачность кода под открытой лицензией • Конфиденциальность на локальном хосте: Отсутствие отслеживания данных, отсутствие телеметрии, полная поддержка работы в автономном режиме • Написано на Python: Исключительная производительность с минимальными системными затратами • Широкое распространение в сообществе: Более 32 000 разработчиков на GitHub 💻 ПОШАГОВЫЕ КОМАНДЫ УСТАНОВКИ В ТЕРМИНАЛЕ: git clone crewAIInc/crewAI cd CrewAI python -m venv .venv .venv\Scripts\activate # В Linux/macOS: source .venv/bin/activate pip install -e . ========================================================================= 🔔 ПОДПИСЫВАЙТЕСЬ НА DAILYDEV AI: Мы ежедневно тестируем и анализируем два новых популярных репозитория с открытым исходным кодом для ИИ в часы пик в США (11:00 и 17:00 EST). Подпишитесь и нажмите на колокольчик, чтобы не пропустить следующий вирусный инструмент с открытым исходным кодом для ИИ! #OpenSourceAI #LocalLLM #AIAgents #Python #DeveloperTools #DailyDevAI [ta] இலவச ஓப்பன் சோர்ஸ் Devin-ஐ முந்துமா? CrewAI AI ஏஜென்ட் சோதனை (முழுமையான செட்டப் கையேடு) விலையுயர்ந்த மாதாந்திர API சந்தாக்களைச் செலுத்துவதை நிறுத்துங்கள்! இன்றைய ஆழமான ஆய்வில், DailyDev AI-இல் Crewai (32,000 GitHub Stars) மென்பொருளை, டெவலப்பர்களுக்கான ஒரு மிகச்சிறந்த நிஜ உலக செயல்திறன் சோதனைக்கு உட்படுத்துகிறோம். 👉 அதிகாரப்பூர்வ GitHub ரெபாசிட்டரியைப் பெறுங்கள்: crewAIInc/crewAI ========================================================================= ⏳ நேரக்குறிப்புகள் & அத்தியாயங்கள் (செயல்படுத்துவதற்கு முன் பார்க்கவும்): 00:00 மூடிய AI சந்தா பொறி & மாதாந்திர API கட்டணங்கள் 00:48 டெவலப்பர்கள் ஏன் Crewai-க்கு மாறுகிறார்கள் 01:35 கோட்பேஸ் கட்டமைப்பு & உள்ளகச் செயல்பாடு 02:20 படிப்படியான லைவ் டெர்மினல் சாண்ட்பாக்ஸ் நிறுவல் 03:45 நிஜ உலகத் திறன் சோதனை & நினைவகப் பயன்பாடு 04:50 உற்பத்தி மதிப்பெண், சிக்கல்கள் & இறுதிப் பொறியியல் தீர்ப்பு ========================================================================= 🔍 CREWAI என்றால் என்ன & அது எப்படி வேலை செய்கிறது? பங்கு வகிக்கும், தன்னாட்சி AI முகவர்களை ஒருங்கிணைப்பதற்கான கட்டமைப்பு. கூட்டு நுண்ணறிவை வளர்க்கிறது. ⚡ முக்கிய உருவாக்குநர் சிறப்பம்சங்கள்: • 100% இலவசம் & திறந்த மூல மென்பொருள்: திறந்த உரிமத்தின் கீழ் முழுமையான குறியீட்டுத் தொகுப்பு வெளிப்படைத்தன்மை • லோக்கல்ஹோஸ்ட் தனியுரிமை: தரவு கண்காணிப்பு இல்லை, டெலிமெட்ரி இல்லை, முழுமையான ஆஃப்லைன் ஆதரவு • பைத்தானில் எழுதப்பட்டது: குறைந்தபட்ச கணினி மேல்சுமையுடன் சிறப்பான செயல்திறன் • பரந்த சமூக ஏற்பு: GitHub-இல் 32,000-க்கும் மேற்பட்ட உருவாக்குநர்கள் 💻 படிப்படியான டெர்மினல் நிறுவல் கட்டளைகள்: git clone crewAIInc/crewAI cd CrewAI python -m venv .venv .venv\Scripts\activate # லினக்ஸ்/மேக்ஓஎஸ்-இல்: source .venv/bin/activate pip install -e . ========================================================================= 🔔 டெய்லிடெவ் ஏஐ-க்கு சப்ஸ்கிரைப் செய்யுங்கள்: ஒவ்வொரு நாளும் அமெரிக்காவின் உச்ச நேரத்தில் (காலை 11:00 EST & மாலை 5:00 EST) இரண்டு புத்தம் புதிய, பிரபலமாகி வரும் ஓப்பன்-சோர்ஸ் ஏஐ ரெபாசிட்டரிகளை நாங்கள் சோதித்து, விரிவாக விளக்குகிறோம். சப்ஸ்கிரைப் செய்து பெல் ஐகானை அழுத்தவும், இதன் மூலம் அடுத்த வைரலான ஓப்பன்-சோர்ஸ் ஏஐ கருவியை நீங்கள் ஒருபோதும் தவறவிட மாட்டீர்கள்! #OpenSourceAI #LocalLLM #AIAgents #Python #DeveloperTools #DailyDevAI [te] ఉచిత ఓపెన్-సోర్స్ సాధనాలు Devinని ఓడించగలవా? CrewAI AI ఏజెంట్‌ను పరీక్షిస్తున్నాము (పూర్తి సెటప్ ... ఖరీదైన నెలవారీ API సబ్‌స్క్రిప్షన్‌లు చెల్లించడం ఆపండి! నేటి డీప్ డైవ్‌లో, మేము డైలీడెవ్ AIలో క్రూవాయ్ (32,000 గిట్‌హబ్ స్టార్స్) యొక్క అంతిమ వాస్తవ-ప్రపంచ డెవలపర్ సామర్థ్య బెంచ్‌మార్క్‌ను పరీక్షిస్తున్నాము. 👉 అధికారిక గిట్‌హబ్ రిపోజిటరీని పొందండి: crewAIInc/crewAI ========================================================================= ⏳ టైమ్‌స్టాంప్‌లు & అధ్యాయాలు (డిప్లాయ్ చేసే ముందు చూడండి): 00:00 క్లోజ్డ్ AI సబ్‌స్క్రిప్షన్ ఉచ్చు & నెలవారీ API బిల్లులు 00:48 డెవలపర్లు క్రూవాయ్‌కి ఎందుకు మారుతున్నారు 01:35 కోడ్‌బేస్ ఆర్కిటెక్చర్ & అండర్-ది-హుడ్ టూర్ 02:20 స్టెప్-బై-స్టెప్ లైవ్ టెర్మినల్ శాండ్‌బాక్స్ ఇన్‌స్టాలేషన్ 03:45 వాస్తవ-ప్రపంచ సామర్థ్య బెంచ్‌మార్క్ & మెమరీ వినియోగం 04:50 ప్రొడక్షన్ స్కోర్, గొట్చాస్ & ఫైనల్ ఇంజనీరింగ్ తీర్పు ========================================================================= 🔍 క్రూవాయ్ అంటే ఏమిటి & అది ఎలా పనిచేస్తుంది? పాత్ర పోషించే, స్వయంప్రతిపత్తి గల AI ఏజెంట్లను నిర్వహించడానికి ఒక ఫ్రేమ్‌వర్క్. సహకార మేధస్సును ప్రోత్సహించండి. ⚡ డెవలపర్ యొక్క ముఖ్య ముఖ్యాంశాలు: • 100% ఉచితం & ఓపెన్-సోర్స్: ఓపెన్ లైసెన్స్ కింద పూర్తి కోడ్‌బేస్ పారదర్శకత • లోకల్‌హోస్ట్ గోప్యత: డేటా ట్రాకింగ్ లేదు, టెలిమెట్రీ లేదు, పూర్తి ఆఫ్‌లైన్ మద్దతు • పైథాన్‌లో వ్రాయబడింది: కనీస సిస్టమ్ ఓవర్‌హెడ్‌తో అసాధారణమైన పనితీరు • భారీ కమ్యూనిటీ ఆదరణ: GitHubలో 32,000+ డెవలపర్లు 💻 దశలవారీ టెర్మినల్ ఇన్‌స్టాలేషన్ ఆదేశాలు: git clone crewAIInc/crewAI cd CrewAI python -m venv .venv .venv\Scripts\activate # Linux/macOSలో: source .venv/bin/activate pip install -e . ========================================================================= 🔔 డైలీడెవ్ ఏఐకి సబ్స్క్రయిబ్ చేసుకోండి: మేము ప్రతిరోజూ యూఎస్ పీక్ టైమ్ (ఉదయం 11:00 EST & సాయంత్రం 5:00 EST)లో రెండు సరికొత్త ట్రెండింగ్ ఓపెన్-సోర్స్ ఏఐ రిపోజిటరీలను పరీక్షిస్తాము మరియు విశ్లేషిస్తాము. సబ్స్క్రయిబ్ చేసుకొని, బెల్ ఐకాన్‌ను నొక్కండి, తద్వారా మీరు తదుపరి వైరల్ ఓపెన్-సోర్స్ ఏఐ టూల్‌ను ఎప్పటికీ మిస్ అవ్వరు! #OpenSourceAI #LocalLLM #AIAgents #Python #DeveloperTools #DailyDevAI [uk] Чи може безкоштовний open-source перевершити Devin? Тестуємо AI-агента CrewAI (повний посібник із... Припиніть платити дорогі щомісячні підписки на API! У сьогоднішньому глибокому аналізі ми провели Crewai (32 000 зірок GitHub) через найкращий реальний бенчмарк можливостей розробників на DailyDev AI. 👉 Завантажте офіційний репозиторій GitHub: crewAIInc/crewAI ===================================================================== ⏳ ЧАСОВІ МІТКИ ТА РОЗДІЛИ (ПЕРЕГЛЯНЬТЕ ПЕРЕД РОЗГОРТАННЯМ): 00:00 Закрита пастка підписки на ШІ та щомісячні рахунки за API 00:48 Чому розробники переходять на Crewai 01:35 Архітектура кодової бази та огляд «під капотом» 02:20 Покрокове встановлення в «пісочниці» терміналу 03:45 Реальний бенчмарк можливостей та споживання пам’яті 04:50 Оцінка продукції, підводні камені та остаточна інженерія Вирок ========================================================================= 🔍 ЩО ТАКЕ CREWAI ТА ЯК ВОНО ПРАЦЮЄ? Фреймворк для управління рольовими іграми, автономними агентами на основі штучного інтелекту. Сприяти розвитку спільного інтелекту. ⚡ КЛЮЧОВІ ПЕРЕВАГИ РОЗРОБНИКА: • 100% безкоштовно та з відкритим вихідним кодом: повна прозорість кодової бази за відкритою ліцензією • Конфіденційність локального хоста: нульове відстеження даних, нульова телеметрія, повна підтримка офлайн • Написано на Python: виняткова продуктивність з мінімальними системними накладними витратами • Масове впровадження спільнотою: понад 32 000 розробників на GitHub 💻 ПОКРОКОВІ КОМАНДИ ВСТАНОВЛЕННЯ В ТЕРМІНАЛІ: git clone crewAIInc/crewAI cd CrewAI python -m venv .venv .venv\Scripts\activate # У Linux/macOS: source .venv/bin/activate pip install -e . ========================================================================== 🔔 ПІДПИСУЙТЕСЬ НА DAILYDEV AI: Ми тестуємо та аналізуємо два абсолютно нові трендові репозиторії з відкритим кодом для штучного інтелекту щодня у піковий час у США (11:00 за східним часом та 17:00 за східним часом). Підпишіться та натисніть на дзвіночок, щоб ніколи не пропустити наступний вірусний інструмент для штучного інтелекту з відкритим кодом! #OpenSourceAI #LocalLLM #AIAgents #Python #DeveloperTools #DailyDevAI

Cloudflare open-sourced the skill that turns your coding agent into a security auditor, with fresh verifiers trying to kill every finding. 🔗 cloudflare/security-audit-skill #securityauditskill #cloudflare #javascript

Genesis World is a Python simulation platform for robotics and embodied AI. It combines a multi-physics engine, the Nyx photo-realistic renderer and the Quadrants compiler. Parses URDF, MJCF, OBJ, GLB and USD assets. Genesis-Embodied-AI/genesis-world t.co

Based on > [Before writing this, Astra thought for 1,034 tokens. That thinking is hidden. The API returns only its 5 headings: Reconstructing the active map / Mapping maze corridors / Preparing exact maze map / Reconstructing row groupings / Checking channel patterns] This might just be an instance of "A working Nintendo in ~1GB of Qwen weights" from 3 days ago, human-made, than what everyone expects. news.ycombinator.com UPD. I just asked Astra (max) to attempt to do that for lostmsu/TurboGPT (a tiny transformer that trains in under 1min on RTX 5xxx series), and the produced weights were much much worse (bpb 4.47) than the trained ones (bpb 2.53). Reasoning bit: "I’ll ... encode more specific rules directly in the weights." -- exactly the approach from above. E.g. no recursive self-improvement here. Still impressive.

Free vs Paid Next.js SaaS Boilerplates (2026): What You Actually Get --- title: "Free vs Paid Next.js SaaS Boilerplates (2026): What You Actually Get" published: true description: "Free vs paid Next.js SaaS boilerplates in 2026 — what nextjs/saas-starter, create-t3-app, and ixartz give you versus paid kits like ShipEmber, with a fair comparison table." tags: nextjs, saas, webdev, opensource canonical_url: shipember.com --- By Jake Mcdonald, founder of ShipEmber · November 2, 2026 · About an 11-minute read · Free kits checked against their GitHub repos today I'm Jake Mcdonald. I sell a paid Next.js starter (ShipEmber), so this page has a conflict of interest. I'm still going to say this clearly: free open-source starters are often the right first move. The question is what "free" actually includes — and what you still have to wire yourself before the first paid customer. I verified the free options below against their public repos or sites on November 2, 2026. Paid prices match each vendor's live page the same day (or our own pricing for ShipEmber). Free vs paid at a glance | Kit | Price | Auth | Stripe subscriptions | Best for | | --- | --- | --- | --- | --- | | nextjs/saas-starter | Free (MIT) | Email/password + JWT cookies | Checkout + Customer Portal (basic) | Learning the shape of a SaaS | | create-t3-app | Free (MIT) | Auth.js optional | No — bring your own | Typesafe scaffold, not a SaaS kit | | ixartz/SaaS-Boilerplate | Free (MIT) | Clerk | Not the focus of the public README | Multi-tenant + i18n learning | | ShipEmber | $49 launch week, then $79 | Auth.js v5 (Google, GitHub, magic links) | Checkout, portal, signed idempotent webhooks | Minimal solo Free→Pro MVP | | ShipFast / Makerkit / etc. | ~$157–$1,499 | Varies | Usually yes | Broader indie or B2B surface | What "free" actually means Free usually means MIT code you can clone. It does not mean: - OAuth providers configured for production, - webhook idempotency and plan gating you can trust under retries, - marketing pages ready to rebrand, - or someone answering Discord questions when Stripe returns a weird event. You still pay with time. Sometimes that trade is correct. nextjs/saas-starter (Vercel / Next.js) Verified: nextjs/saas-starter — MIT, ~16k stars when I checked today. Demo linked from the README: next-saas-start.vercel.app. From the README, you get: - Next.js + Postgres + Drizzle + Stripe + shadcn/ui - Marketing landing page and a pricing page wired to Stripe Checkout - Dashboard CRUD, basic Owner/Member RBAC - Stripe Customer Portal for subscription management - Email/password auth with JWTs in cookies - Middleware to protect logged-in routes; activity logging Honest take: This is the best free reference I know for "what a clean Next.js + Stripe + Postgres app looks like." Gaps vs a commercial kit: no Google/GitHub OAuth out of the box, no polished one-file rebrand, and you will harden webhook/idempotency patterns yourself for production. Start here if you're learning. Graduate when the missing pieces cost more evenings than a cheap paid kit. create-t3-app Verified: create.t3.gg and the t3-oss/create-t3-app repo (MIT). Install with npm create t3-app@latest. Their own copy is clear: it is not an all-inclusive SaaS template. It scaffolds the pieces you opt into — Next.js, TypeScript, Tailwind, Prisma (or others), tRPC, and Auth.js (NextAuth) — with strong opinions about type safety. No Stripe. No pricing page. No customer portal. Honest take: Perfect when you want a typesafe app shell and you intend to own billing. Terrible if you expected "clone and charge cards tomorrow." Pair it with Stripe docs (or a kit) when you need subscriptions. ixartz/SaaS-Boilerplate Verified: ixartz/SaaS-Boilerplate — MIT, demo at react-saas.com. README lists Next.js, Tailwind, shadcn/ui, Clerk auth, multi-tenancy with teams/roles, Drizzle, i18n, landing, dashboard, tests, and CI. Stripe is not the headline feature of the public README. Honest take: Useful if you want to study multi-tenant patterns and you're fine with Clerk (their free tier has limits; paid Clerk is a separate bill). If your requirement is "Auth.js + Stripe subscriptions on Postgres with no third-party auth vendor," this is the wrong free kit. When free is the better pick - You're learning App Router, Drizzle/Prisma, or Stripe for the first time. - You have a weekend and a high tolerance for wiring env vars and webhook secrets yourself. - Your product is not ready to charge anyone — scaffolding beats buying. - You specifically want create-t3-app's typesafe stack and will add billing later. Related reading on that tradeoff: topic #12 in our internal notes became this page. Also see Best Next.js SaaS boilerplates in 2026. When a paid kit is the better pick - You've already burned a week on auth + webhooks and just want the boring path paved. - You need OAuth (Google/GitHub) + magic links + Stripe Checkout + portal + server-side Free/Pro gating together. - You want a small, opinionated codebase with docs aimed at shipping, not at teaching every option. - Your hourly rate makes $79–$249 cheaper than two more evenings of billing bugs. Paid kits are not equal. ShipFast, Makerkit, and supastarter buy you more surface area (and more learning). ShipEmber buys you the core loop only. I wrote separate comparisons: ShipFast, Makerkit, supastarter, Shipped.club. Why choose ShipEmber (if you buy anything) Here's the honest pitch — same points I'd tell a friend. 1. Paid for the gap free kits leave ShipEmber is Auth.js v5 + Stripe subscriptions (Checkout, customer portal, signature-verified idempotent webhooks) + Prisma/Postgres + a gated dashboard + marketing pages + one-file rebrand. That's the gap between "I cloned saas-starter" and "I can charge Pro tonight." 2. Price stays near free-kit territory Live price: $49 launch week, then $79 — see pricing. One-time. Instant zip download. 14-day refund if it doesn't work as described. Lifetime updates to v1. 3. Intentionally small No orgs, no i18n, no five payment providers. If you need those, buy Makerkit or supastarter — or start from nextjs/saas-starter and grow into them. If you want the paid core loop Get the zip, add your keys, and build the product part. Get ShipEmber, $49 Pricing details · What's inside · Auth.js + Stripe checklist Related: Full boilerplate comparison · Stripe subscriptions deep dive · Why I built ShipEmber Verification note: nextjs/saas-starter and ixartz/SaaS-Boilerplate READMEs and licenses checked on GitHub on November 2, 2026. create-t3.gg checked the same day. Vendor pages and READMEs change. — Jake Mcdonald, Springfield, IL

SOML – A Config Format for Humans soml-lang/soml (news.ycombinator.com)

This Free App Runs Any AI Tool on Your PC — in One Click Pinokio is a free, open-source app that installs and runs any AI tool on your own computer — in one click. 🖱️ One-click install for image, video, music & chat AI 🔒 Runs locally — your data stays private 💸 100% free, no subscriptions 🔔 Subscribe for a new AI tool every day. 💬 Comment "LINK" for the tool. More from me: 📚 Learn AI With Uzair → youtube.com 📰 Ai News → youtube.com 🔭 The Facts Orbit → youtube.com 🔗 Pinokio: pinokiocomputer/pinokio #ai #aitools #pinokio #localai #opensource #shorts

Skill to Create Product Videos | Discussion

LLVM Weekly - #670, November 2nd 2026 LLVM Weekly - #670, November 2nd 2026 ===================================== If you prefer, you can read a HTML version of this email at <llvmweekly.org>. Welcome to the six hundred and seventieth issue of LLVM Weekly, a weekly newsletter (published every Monday) covering developments in LLVM, Clang, and related projects. LLVM Weekly is brought to you by [Alex Bradbury](linkedin.com). Subscribe to future issues at <llvmweekly.org> and pass it on to anyone else you think may be interested. Please send any tips or feedback via email: <asb@asbradbury.org>, or Mastodon: [@llvmweekly@fosstodon.org](fosstodon.org) / [@asb@fosstodon.org](fosstodon.org), or Bluesky: [@llvmweekly.org](bsky.app) / [@asbradbury.org](bsky.app). ## News and articles from around the web and events Timm Baeder gave a [Clang bytecode interpreter update on the Red Hat blog](developers.redhat.com). Saleem Abdulrasool [wrote about ABIs](speakinginswift.substack.com) on the Browser Company Speaking in Swift blog. According to the [LLVM Calendar](calendar.google.com) in the coming week there will be the following: * Office hours with the following hosts: Quentin Colombet, Renato Golin. * Online sync-ups on the following topics: formal specification, MLIR C/C++ frontend working group, pointer authentication, lifetime safety, Clang static analysis, OpenMP, Clang C and C++ language working group, Flang, RISC-V, LLVM embedded toolchains, HLSL, MLGO, LLVM libc math. * For more details see the [LLVM calendar](calendar.google.com), getting involved documentation on [online sync ups](llvm.org) and [office hours](llvm.org). ## On the forums * Anton Korobeynikov noted that [the Graphite review tool will be disabled for the LLVM project](discourse.llvm.org) as they no longer offer discounted or free plans for open source organisations. * Notes are available from various round tables / workshops at last week's Dev Meeting: [debug info](discourse.llvm.org), [LLVM hearts ML](discourse.llvm.org), and the [RISC-V roundtable](discourse.llvm.org). * Michael Kruse provided an [update on the effort to improve Flang compilation speed by de-templatising](discourse.llvm.org) noting that a key PR will land soon. "Flang should not behave any differently, but builds up to 46% faster (gcc, without precompiled headers)". * Ralf Jung started an RFC discussion on [adding a freezing memcpy](discourse.llvm.org) which would be part of the story for exposing `freeze` to programmers in Rust. * Joshua Haberman posted an RFC on [`tail_chaincc`, a maximum efficiency tailcall convention](discourse.llvm.org). It combines the callee-cleanup mechanics of `tailcc` with the register optimisations of `preserve_none` and is intended to be used with `[[clang::musttail]]`. * paperchalice wrote a v2 RFC on [TableGen support for RegisterBankInfo](discourse.llvm.org), providing a way to define register bank mapping rules by matching `TypedOperand`s. * Federico Bruzzone posted an MLIR RFC on [unifying masking in the Vector dialect](discourse.llvm.org). * Konstantin Zhuravlyov started a discussion on [vendor-owned pre-merge testing for LLVM PRs](discourse.llvm.org). ## LLVM commits * LoopStrengthReduce learned to rewrite branches to eq/ne with an immediate for targets like RISC-V with the Zibi (immediate branch extension) enabled. [0b56c8e](github.com/llvm/llvm-project/commit/0b56c8e2a5b4). * llvm-dwarfutil now supports `--compress-debug-sections`. [cc6b3b5](github.com/llvm/llvm-project/commit/cc6b3b5a1d0f). * An X86 pass was added to insert `sfence` after non-temporal stores. [238ef21](github.com/llvm/llvm-project/commit/238ef21c3564). * A number of fixes were made to tail call support on AArch64 Windows. [3c956bd](github.com/llvm/llvm-project/commit/3c956bd6bc50). * The 'debugger-tuning' module flag was introduced. [738215b](github.com/llvm/llvm-project/commit/738215bc1122). * LLVM's AI contribution policy is now referenced on the 'how to submit a bug' page. [5661d4f](github.com/llvm/llvm-project/commit/5661d4fdb9c0). * `llvm.raw.sections` named metadata was added for embedding arbitrary binary data into named sections of the output object file. [39cd74f](github.com/llvm/llvm-project/commit/39cd74fb6ea2). * The `LiveVariables` analysis was removed, described as "12 years overdue" in the commit message! [93f05d7](github.com/llvm/llvm-project/commit/93f05d753ad3). * Malloc promotion was removed due to being buggy and rarely profitable. [e2089b0d](github.com/llvm/llvm-project/commit/e2089b0ddf1a). * VPlan now computes branch costs. [999b73d](github.com/llvm/llvm-project/commit/999b73deef74). ## Clang commits * `std::meta::is_type` support was implemented. [6006957](github.com/llvm/llvm-project/commit/6006957c522e). * Clang's DepScan gained a new API to find modulemaps without loading. [ff065cf](github.com/llvm/llvm-project/commit/ff065cf32589). ## Other project commits * Bolt's webpage styling was updated. [d35f657b](github.com/llvm/llvm-project/commit/d35f657bba4c). * LLVM's libc now has double precision sinh, cosh, and tanh correctly rounded for all rounding modes. [1866d4c](github.com/llvm/llvm-project/commit/1866d4cc5634), [075a6cb](github.com/llvm/llvm-project/commit/075a6cb14025), [ff9ad99](github.com/llvm/llvm-project/commit/ff9ad993c2b9). * LLVM libc's regex implementation is being fleshed out. [ad46922](github.com/llvm/llvm-project/commit/ad46922aac46), [adb8031](github.com/llvm/llvm-project/commit/adb80317aa28). github.com/llvm/llvm-project/commit/0b56c8e2a5b4: github.com/llvm/llvm-project/commit/0b56c8e2a5b4 github.com/llvm/llvm-project/commit/cc6b3b5a1d0f: github.com/llvm/llvm-project/commit/cc6b3b5a1d0f github.com/llvm/llvm-project/commit/238ef21c3564: github.com/llvm/llvm-project/commit/238ef21c3564 github.com/llvm/llvm-project/commit/3c956bd6bc50: github.com/llvm/llvm-project/commit/3c956bd6bc50 github.com/llvm/llvm-project/commit/738215bc1122: github.com/llvm/llvm-project/commit/738215bc1122 github.com/llvm/llvm-project/commit/5661d4fdb9c0: github.com/llvm/llvm-project/commit/5661d4fdb9c0 github.com/llvm/llvm-project/commit/39cd74fb6ea2: github.com/llvm/llvm-project/commit/39cd74fb6ea2 github.com/llvm/llvm-project/commit/93f05d753ad3: github.com/llvm/llvm-project/commit/93f05d753ad3 github.com/llvm/llvm-project/commit/e2089b0ddf1a: github.com/llvm/llvm-project/commit/e2089b0ddf1a github.com/llvm/llvm-project/commit/999b73deef74: github.com/llvm/llvm-project/commit/999b73deef74 github.com/llvm/llvm-project/commit/6006957c522e: github.com/llvm/llvm-project/commit/6006957c522e github.com/llvm/llvm-project/commit/ff065cf32589: github.com/llvm/llvm-project/commit/ff065cf32589 github.com/llvm/llvm-project/commit/d35f657bba4c: github.com/llvm/llvm-project/commit/d35f657bba4c github.com/llvm/llvm-project/commit/1866d4cc5634: github.com/llvm/llvm-project/commit/1866d4cc5634 github.com/llvm/llvm-project/commit/075a6cb14025: github.com/llvm/llvm-project/commit/075a6cb14025 github.com/llvm/llvm-project/commit/ff9ad993c2b9: github.com/llvm/llvm-project/commit/ff9ad993c2b9 github.com/llvm/llvm-project/commit/ad46922aac46: github.com/llvm/llvm-project/commit/ad46922aac46 github.com/llvm/llvm-project/commit/adb80317aa28: github.com/llvm/llvm-project/commit/adb80317aa28

How we cut pre-turn agent routing latency in Ollama (qwen3.5:9b) from 2.5s down to 378ms on a single GPU (Disclosure: I am the author of Herald Router and Ultimate Assistant, the open-source projects linked below.) Correction: an earlier version of this post called tev1 a "~400M" model that fits in under 500 MB of VRAM, and that's wrong. It is 4.3B at Q8_0 (~4.6 GB) (confirmed with ollama show). The latency and accuracy numbers were measured and haven't changed. I've fixed the size and the VRAM takeaway below. I also originally credited it to the wrong maker: it's Together AI's model (huggingface.co). Sorry for the confusion. When building a local voice/desktop assistant on top of Ollama (Ultimate Assistant v0.4.4 + Herald Router v0.4.2, running together on 127.0.0.1 with no cloud or Tailscale required), we noticed that the biggest source of sluggishness wasn't Ollama's main generation speed — it was the pre-turn routing checks that happen before the main response starts. On every turn, the assistant needs to know: 1. Does this prompt need live web search (need_web_search), and if so, deep research (need_deep_search)? 2. Does it reference past conversation memory (need_memory_lookup)? 3. Is it a coding/shell task or a deep reasoning query? Even when we tuned qwen3.5:9b in Ollama with num_predict=8 and think=false, a single binary check took ~2.53 seconds (and running 6 routing checks sequentially took ~15.1 seconds) before the main Ollama chat response even began. Benchmarking qwen3.5:9b (Ollama) vs a 4.3B System 1 Sidecar on the Same GPU We tested running a dedicated 4.3B (Q8_0) GGUF binary decision model (Together AI's Tev1-4B-experimental (tev1, an Apache-2.0 fine-tune of Qwen3.5-4B), which outputs a single yes/no token) alongside Ollama (qwen3.5:9b) on the same NVIDIA RTX 4070 Ti SUPER (16 GB VRAM) across a 24-prompt evaluation suite: | Setup | Mode | Avg Pre-Turn Routing Latency | P50 Latency | Routing Accuracy (24/24) | | :--- | :--- | :--- | :--- | :--- | | tev1 (4.3B Q8_0 sidecar) + Ollama (qwen3.5:9b) | Shared GPU (cuda) | 378.1 ms | 365.4 ms | 91.7% (22/24) | | tev1 (4.3B Q8_0 sidecar) + Ollama (qwen3.5:9b) | tev1 on CPU (-ngl 0), Ollama on GPU | 1,093.9 ms | 1,089.3 ms | 91.7% (22/24) | | Ollama qwen3.5:9b alone | Single-question check (num_predict=8, think=false) | 2,526.0 ms | 2,418.7 ms | 91.7% (22/24) | | Ollama qwen3.5:9b alone | 6-question sequential turn routing | 15,156.0 ms | 14,512.0 ms | 91.7% (22/24) | Key Takeaways for Local Ollama Builders 1. You can keep your main Ollama model hot in VRAM: tev1 at Q8_0 takes ~4.6 GB, so on a 16 GB card it sits alongside qwen3.5:9b without evicting it. On smaller cards you can run it on CPU instead (~1.09 s with -ngl 0) and leave the GPU to your chat model. 2. Keep local question batches small (5Q + 1Q): Unlike hosted decision APIs (Jev, pplx-decider-v1.2, Liquid d1.1) where we can fire 40 questions in parallel (turn_surmise) in ~613 ms, a local GPU server serializes large batches across fixed compute slots. Firing just 5 core binary questions + 1 conditional follow-up keeps local GPU latency at 378 ms. 3. Zero-config fallback to Ollama (llm provider): If you only want to run Ollama with zero extra processes, our llm decision provider automatically uses your configured Ollama model with think=false and short token caps. We just shipped this in our latest open-source releases: - Herald Router v0.4.2: github.com/KianJRoss/herald-release/releases/tag/… - Ultimate Assistant v0.4.4: github.com/KianJRoss/UltimateAssistant-release/re… How are you handling pre-turn tool/search routing with Ollama right now — native tool calling on every turn, a smaller Ollama model (qwen3.5:0.8b / smollm2), or an external classifier?

今日のGitHubトレンド hyprwm/Hyprland 見た目にこだわった独立した動的タイル型Waylandコンポジタの開発を目的としています。 最新のWayland機能の提供や高度なカスタマイズ性、視覚効果、強力なプラグイン、簡単なIPCなどの実装により、利便性と美しさを兼ね備えた環境を提供します。

Location: Colorado, USA Remote: Yes Willing to relocate: Yes Technologies: Golang (Go), C, Python, Java, SQL, git, Docker, Linux/POSIX, Internet & web dev, cloud IaaS, distributed, concurrency & threading, performance & scalability, some math & ML Résumé/CV: github.com/mkramlich/portfolio/raw/refs/heads/mas… Email: groglogic+hn2026nov@gmail.com programming for decades. solid fundamentals. troubleshooter. tech lead/arch. SRE-ish. solved legacy Heisenbugs & shipped, many times. author of perf cheatsheet writing book on HPC US citizen, native English ex Orbitz on core tech (JVM, GC, perf regress follow-up, ops, logs, instrum, caches, sessions, threads, db conns) research & due diligence for US State Dept on public defenses against foreign adversarial propaganda & disinfo (ie. natsec) game engine creator & toolmaker since kid. once built small sw biz recent client: sys prog R&D on mem alloc latency & SEGV resilience. C on Linux. delivered code, benchmarks, diagrams & report on how to upgrade perf & avail of their soft-RT (micros mattered), $-impacting backend LatLearn: FOSS Golang latency instrum & reporting lib

Making a few improvements on my mechanical file splitter for Rust, took the opportunity to put it on Github Wally869/file-splitter-rs

You don't need to rebuild your Agent to use Envar. Keep your existing setup. EnvarConnect handles the connection, task delivery and recovery. The infrastructure behind that is now public: EnvarAI/EnvarConnect