Asymptote-Labs

你在 Claude Code 里纠正过一次错，换个 Codex 窗口，它又犯。 开源记忆层 Beacon 能记下这次纠正，按你定的规则存成共享记忆，另一个 Agent 也能读到。 开源仓库：Asymptote-Labs/agent-beacon 按项目介绍，支持 Claude Code、Codex、Cursor、OpenCode 等 20 多个 Agent 运行框架。 原帖作者的四步，可以直接照着跑： 1、给 Claude Code 一个编程任务，它改代码、跑测试，Beacon 在后台录下整个过程。 2、让 Jev（做判断的模型）评审这次运行。第一次返回“需要复核”，因为他还没给正确改法，他的应用按规则什么都没存。 3、他手动纠正 Agent，Agent 改完重跑测试。Jev 再评审，这次符合应用的存储规则。 4、把纠正和证据存成共享记忆。另开一个 Codex 会话，明确让它读这条记忆，Codex 直接想起来了，不用重新解释。 分工要看清楚：Beacon 负责记录，Jev 负责判断什么值得留，你的应用负责定规则、决定存不存。不是让模型自己乱记。 价值也不在“记忆”两个字，在跨工具。你在一个 Agent 里踩过的坑，能带到另一个 Agent。 同一支视频里还讲了：会话在 Agent 之间迁移、把经验做成可复用技能、从 Agent 的操作记录里发现安全风险。作者是 Asymptote Labs 联合创始人 Justin。

@asymptotelabs Repo here → Asymptote-Labs/agent-beacon huge credit to → @jqdsouza and @asymptotelabs for building Beacon and sharing it with everyone as open source 🙏 if you find it useful, show them some love with a GitHub star ⭐️

2,577 Stars 2 Din Mein: AI Coding Ki Agli Chhalaang OpenAI Se Nahi? 5 GitHub Launches #Shorts Top 5 trending GitHub repos, Hindi mein - har number aaj check kiya gaya hai. Is week ke top trending repos, 75k+ stars combined: 1. Asymptote-Labs/agent-beacon (3k stars) - The cross-harness, self-improving memory layer for AI agents. Join our community: discord.com 2. trycua/cua (31k stars) - Scale computer-use 2.0 with open-source drivers, cross-OS sandboxes, and benchmarks for training, evaluation, and data generation. 3. Fei2411/DeepSeek-Bot (3k stars) - A team of long-lived bots for DeepSeek Harness, with main bots, bot-to-bot messages and group chats. 4. noahdunnagan/fsearch (2k stars) - Whole-disk file search for macOS: fuzzy names, typo tolerance, indexed content grep. ~1 ms over 8M files. 5. utmapp/UTM (36k stars) - Virtual machines for iOS and macOS Repo links: Asymptote-Labs/agent-beacon trycua/cua Fei2411/DeepSeek-Bot noahdunnagan/fsearch utmapp/UTM Comment karo "VIEWS" - saare links DM mein bhej dunga. Kisi dev dost ko bhejo jise ye chahiye. Save karlo, baad mein kaam aayega. Naman AI - AI aur dev tools, Hindi mein. Har din naya repo, har number verified. #Shorts #GitHub #AI #OpenSource #TechHindi [github trending repos, best github repositories 2026, top 5 github repos, open source projects for beginners, ai coding agents, github stars] [coding in hindi, tech shorts hindi, programming for beginners, developer tools 2026, ai tools for developers, learn coding free] [bn] ২ দিনে ২,৫৭৭ স্টার: এআই কোডিংয়ের পরবর্তী ধাপ ওপেনএআই থেকে নয়? ৫টি গিটহাব লঞ্চ #Shorts হিন্দিতে শীর্ষ ৫টি ট্রেন্ডিং গিটহাব রিপো - আজ প্রতিটি নম্বর চেক করা হয়েছে। এই সপ্তাহের শীর্ষ ট্রেন্ডিং রিপো, সম্মিলিতভাবে ৭৫ হাজারেরও বেশি স্টার: ১. Asymptote-Labs/agent-beacon (৩ হাজার স্টার) - এআই এজেন্টদের জন্য ক্রস-হারনেস, স্ব-উন্নয়নশীল মেমরি লেয়ার। আমাদের কমিউনিটিতে যোগ দিন: discord.com ২. trycua/cua (৩১ হাজার স্টার) - ওপেন-সোর্স ড্রাইভার, ক্রস-ওএস স্যান্ডবক্স এবং প্রশিক্ষণ, মূল্যায়ন ও ডেটা তৈরির জন্য বেঞ্চমার্কের মাধ্যমে কম্পিউটার-ব্যবহার ২.০-কে স্কেল করুন। ৩. Fei2411/DeepSeek-Bot (৩ হাজার স্টার) - DeepSeek Harness-এর জন্য দীর্ঘস্থায়ী বটদের একটি দল, যেখানে রয়েছে মূল বট, বট-টু-বট মেসেজ এবং গ্রুপ চ্যাট। 4. noahdunnagan/fsearch (2k stars)- macOS-এর জন্য সম্পূর্ণ-ডিস্ক ফাইল অনুসন্ধান: অস্পষ্ট নাম, টাইপো সহনশীলতা, সূচীকৃত বিষয়বস্তু grep। 8M ফাইলের উপরে ~1 ms 5. utmapp/UTM (36k তারা) - iOS এবং macOS এর জন্য ভার্চুয়াল মেশিন রেপো লিঙ্ক: Asymptote-Labs/agent-beacon trycua/cua Fei2411/DeepSeek-Bot noahdunnagan/fsearch utmapp/UTM মন্তব্য করুন "দর্শন" - সারা লিঙ্ক ডিএম মে ভেজ দুঙ্গা। কিসি দেব দোস্ত কো ভেজো জিসে ইয়ে চাহিয়ে। করলো বাঁচাও, বাদ মে কাম আয়েগা। নমন এআই - এআই অর দেব টুল, হিন্দি মে। প্রতিদিন নতুন রিপো, প্রতিটি নম্বর ভেরিফাইড। #শর্টস #গিটহাব #এআই #ওপেনসোর্স #টেকহিন্দি [গিটহাব ট্রেন্ডিং রিপো, সেরা গিটহাব রিপোজিটরি ২০২৬, সেরা ৫টি গিটহাব রিপো, নতুনদের জন্য ওপেন সোর্স প্রজেক্ট, এআই কোডিং এজেন্ট, গিটহাব স্টারস] [হিন্দিতে কোডিং, হিন্দি টেক শর্টস, নতুনদের জন্য প্রোগ্রামিং, ডেভেলপার টুলস ২০২৬, ডেভেলপারদের জন্য এআই টুলস, বিনামূল্যে কোডিং শিখুন]

How to share memory between Claude Code, Codex and Cursor with Beacon You fix a mistake in Claude Code. Tomorrow you open Codex or Cursor and correct the exact same mistake again, because each harness keeps its own memory. Beacon by Asymptote Labs is an open-source, local-first memory layer that sits across the harness layer. It captures session history from Claude Code, Cursor, Codex, OpenCode, Cline and 20+ other harnesses into one OpenTelemetry-based trace format, then turns useful workflows, corrections and debugging patterns into reviewed knowledge that future agents can retrieve through MCP or Agent Skills. The README sums it up in one line: a problem solved by one agent should not need to be learned from scratch by another. This guide sets Beacon up in Local mode, shows how to check what it captured, and covers the two other jobs it does well: exact session replay and sending agent activity to a SIEM. Before you start: Local vs Beacon Cloud Interactive setup signs in through beacon.sh and preselects Beacon Cloud, with an explicit Local opt-out. Signing in forwards nothing. Confirming Beacon Cloud installs Beacon and starts forwarding your history to Asymptote Labs, and the confirm screen says so before you accept. Beacon records prompts, responses, commands and file edits. If you ever paste an API key into an agent, it can end up in a trace. If you want everything to stay on your machine, pick Local. You can disconnect a cloud endpoint any time with beacon endpoint disconnect. Install The fastest path is to let your coding agent do it. Paste this into Claude Code, Codex or Cursor: Read https://beacon.sh/start.md then set me up on Beacon Or install by hand on macOS: brew update brew trust asymptote-labs/tap brew tap asymptote-labs/tap brew install beacon beacon endpoint install On Linux (Debian, Ubuntu, Fedora, RHEL, Rocky, Alma) the installer picks the .deb or .rpm for your architecture and verifies it against the release checksums.txt: curl -fsSL https://github.com/asymptote-labs/agent-beacon/releases/latest/download/install.sh | bash If you prefer not to pipe a script into your shell, download it, read it with less install.sh, then run bash install.sh. On Windows, download the x64 MSI from the latest release and run msiexec /i BeaconEndpointAgent-<version>-x64.msi. When beacon endpoint install asks for a destination, choose Local. Install the Beacon Skills Whichever destination you pick, the wizard installs the Beacon Skills into ~/.agents/skills and ~/.claude/skills unless you turn them off. These are the Agent Skills that recall and distill project memory from your traces. To redo or undo that later: beacon skills install beacon skills uninstall In Claude Code you can also install the plugin from the repo's marketplace with /plugin marketplace add asymptote-labs/agent-beacon, or use the skills CLI with npx skills add asymptote-labs/agent-beacon. Use your agents normally That is the whole step. Open Claude Code, Cursor, Codex or any supported harness and work as usual. Beacon captures session history in the background. Check what Beacon captured beacon traces This opens a local terminal browser for traces, event timelines, token usage and retained content. Nothing is sent anywhere. For a local web view: beacon endpoint dashboard Or read the raw event stream directly at ~/.beacon/endpoint/logs/runtime.jsonl. It is plain JSONL, so you are never dependent on the UI. Recall memory from another agent Beacon's loop is: run agents, capture history, evaluate what worked, extract useful knowledge, review and approve, reuse across future agents. That review step matters. Expect to curate what Beacon extracts rather than get perfect memory on day one. To expose memory over MCP: - Locally: beacon mcp serve runs the local beacon MCP server, which never touches the network. - With Beacon Cloud: beacon mcp connect registers the beacon-managed MCP server in Claude Code, Codex CLI, Cursor, VS Code, Gemini CLI and OpenCode. Each harness signs in with OAuth the first time, no token is written, and beacon mcp disconnect removes exactly what it added. A good first test prompt, run in a second harness after a session in the first: Recall what Beacon learned about <project task> in this repo and tell me which past session it came from. Bonus 1: replay exactly what an agent did Each session becomes one trace with prompts, tool calls, commands, edits, approvals, MCP activity and tokens. In the dashboard, session pages show lenses, such as files changed with their diffs, an itemized token bill, a security review grouped by risk, or the approval timeline. The README warns to install only lenses you trust with your traces. Coverage differs by harness. In the support table, Codex CLI does not report file activity and Cursor does not report tokens, while Claude Code reports every column. Bonus 2: send agent activity to your SIEM Beacon writes local JSONL by default and can forward the same normalized history to Splunk HEC or CrowdStrike Falcon LogScale HEC during install or repair. Microsoft Sentinel, Sumo Logic, Wazuh and Rapid7 InsightIDR use Beacon content packs, Datadog and Elastic collect the local JSONL with their own agents, and S3 or GCS work through Vector. The per-SIEM steps live at docs.beacon.sh. Forwarding sends prompts and commands off the machine, so tell developers what is captured. Use cases with copy-paste prompts - Share memory between Claude Code, Codex and Cursor - Replay exactly what your coding agent did - Send coding agent activity to your SIEM --- Get one email every Monday with the week's hottest AI repos and exactly how to use them: subscribe free at dedupedai.com

深入理解 Go 与 SIMD：从底层硬件指令到编译器实现原理 主页 | Web版 | 订阅 | 归档 | Feed GopherDaily 20261023 每日一谚：Don't swallow errors; either log them or return them, but never both Go技术生态 深入理解 Go 与 SIMD：从底层硬件指令到编译器实现原理 长期以来在 Go 中使用 SIMD 只能依赖繁琐的手写汇编，而 Go 1.26/1.27 引入的实验性 simd 与 simd/archsimd 包彻底打破了这>一壁垒。本文深入剖析现代 CPU 向量寄存器与通道（Lanes）的物理机理，详解底层架构包与可移植包的设计权衡，揭秘编译器内建函数（Intrinsics）与 midway 多重编译的底层黑魔法，并通过广播、融合乘加（FMA）、掩码混合与尾部处理等核心操作，手把手构建跑出 9 倍性能飞跃的点积计 算实战，为 Go 开发者提供了一套完整的硬件向量化加速指南。 Go 紧急发布两个安全版本！一次 CA 证书信任危机，暴露 HTTPS 安全体系的薄弱环节 Go 因为一批中间 CA 证书的安全问题，紧急发布 Go 1.26.10 和 Go 1.27.3。本文深入解释这次安全修复的技术原理、证书链信任>机制与工程影响，并通过可运行的 Go 示例说明如何验证证书链、排查生产环境中的旧二进制，以及建立更可靠的 Go 安全更新流程。 (迟来的)生日快乐，Beads！ Beads是一个命令行工具`bd`，编码智能体用它来管理任务。Beads将任务作为问题存储在项目文件夹中的`.beads`目录中。你告诉你的编码智能体使用Beads来管理它的任务，瞧，你的编码智能体将开始能够完成更长的任务。 云原生技术 使用OpenTelemetry Collector过滤和减少AI智能体遥测数据 OpenTelemetry Collector可以帮助过滤和减少AI智能体的遥测数据，优化资源命名和服务属性配置，提高系统性能和监控效率。 软件运行缓慢是因为糟糕的设计，而不是慢速语言 对于经常使用慢速语言或CPU密集型工作负载的开发者来说，这个数字可能高得离谱；而对于不使用这些的开发者来说，可能又显得过低。根据我的经验，这个数字至少对于解释型语言来说是在合理范围内的。 PHP2Shell安全更新：对Docker客户的影响 简而言之，这些漏洞可能允许恶意行为者在PHP核心中执行远程代码。这些漏洞都与PHP管理请求内存的方式有关。当PHP在请求过程中内存不足并中止时，某些代码路径会保留未初始化的内存，导致潜在的安全风险。 单租户Titus：在多租户容器平台上的VM级隔离 持续改进共享内核隔离有助于平台上的每个工作负载，无需选择加入，我们仍在投资于此。其限制是结构性的，需要进一步优化。 我们如何为数百万个Netlify项目构建Git存储 在过去的十年里，Netlify已经从持续部署和托管发展成为一个更广泛的运行时平台。但开发本身仍然存在于用户自己的Git主机上，需要更好的集成方案。 代码与蛋糕 - Docker很奇怪 我决定为了好玩制作自己的容器运行时，即使我还在早期阶段，我已经了解到Docker很奇怪。以下是我了解到的一些关于Docker的奇怪之处。 AI 软件如何信任软件：MCP、A2A及智能体使用的注册表 安全专业人士日益担忧，开发者正在将连接AI智能体的协议（如模型上下文协议(MCP)和智能体到智能体(A2A)）当作安全标准使用，这可能带来风险。 没有人再思考了 每个人都在AI领域工作。有至少一半是由AI编写的规范，有80%是由AI编写的代码，有60%是由AI编写的战略文件。如果所有东西都是由AI编写的，那么其背后的思考就非常少了。 Gas City的高峰时段：优化智能体的工厂CI 在转向智能体工程之前，我是一名传统企业软件工程师。刚从大学毕业，我就从构建虚拟机监控程序开始，然后作为技术负责人和人员经理，在初创公司和大型公司开始了冒险之旅。 LLMs使大规模形式化软件验证变得可行 by Anthropic 大多数软件都充满了错误，而AI现在可以轻松地发现这些错误。大型语言模型(LLMs)正在使形式化软件验证在更大规模上变得可行。 给你的智能体更少的互联网 - exe.dev博客 为你的智能体提供更少的互联网访问，可以增强安全性和性能，同时仍然保持必要的连接和集成能力。 使用任何框架支持智能体开发生命周期，从ADK到LangChain及更多 - Google开发者博客 新的智能体CLI扩展系统的端到端演示，包含一个LangChain示例和自定义部署策略，为开发者提供更灵活的智能体开发选择。 流行工具与项目 CarterPerez-dev/Cybersecurity-Projects Building 70 Projects ranging from beginner to advanced so anyone can — learn from, build upon, use as a reference, or even copy directly. Gamified Cybersecurity learning 👇 alibaba/open-code-review Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in multi-language ruleset (NPE, microsoft/TypeScript TypeScript is a superset of JavaScript that compiles to clean JavaScript output. helm/helm The Kubernetes Package Manager Asymptote-Labs/agent-beacon The cross-harness, self-improving memory layer for AI agents. Join our community: discord.com tailscale/tailscale The easiest, most secure way to use WireGuard and 2FA. zitadel/zitadel ZITADEL - Identity infrastructure, simplified for you. open-telemetry/opentelemetry-collector-contrib Contrib repository for the OpenTelemetry Collector aquasecurity/trivy Find vulnerabilities, misconfigurations, secrets, SBOM in containers, Kubernetes, code repositories, clouds and more samber/cc-skills-golang 🧑‍🎨 A collection of Golang agentic skills that works 编辑:Tony Bai 编辑主页:tonybai.com GopherDaily项目:github.com/bigwhite/gopherdaily Copyright 2019-2024 GopherDaily CarterPerez-dev/Cybersecurity-Projects: CarterPerez-dev/Cybersecurity-Projects alibaba/open-code-review: alibaba/open-code-review microsoft/TypeScript: microsoft/TypeScript helm/helm: helm/helm Asymptote-Labs/agent-beacon: Asymptote-Labs/agent-beacon tailscale/tailscale: tailscale/tailscale zitadel/zitadel: zitadel/zitadel open-telemetry/opentelemetry-collector-contrib: open-telemetry/opentelemetry-collector-contrib aquasecurity/trivy: aquasecurity/trivy samber/cc-skills-golang: samber/cc-skills-golang github.com/bigwhite/gopherdaily: bigwhite/gopherdaily

3 Trending GitHub Repos: An AI Sales Agent, Cross-Agent Memory & a Safe Disk Cleaner Three repositories trending on GitHub, explained in plain language: what each one does, who should try it, how to get started, and what to watch out for. This time: Harvey, a sales agent that runs on your Claude or ChatGPT subscription instead of an API key; Agent Beacon, a memory layer that lets lessons from one coding agent reach the next; and MangoDisk, a cross-platform disk cleaner that keeps its idea of "safe" in readable rules. ⏱ Chapters 0:00 Intro & this week in dev tools 1:33 Harvey: AI sales agent on your subscription 4:27 Agent Beacon: memory across coding agents 7:45 MangoDisk: safety-first disk cleanup 10:52 Summary 📦 Repos 1. ethanplusai/harvey – Ethan+ (Python · MIT) ethanplusai/harvey Try it: clone the repo, run Claude Code inside it and say "set up Harvey for me" (see the README's Quick start) 2. Asymptote-Labs/agent-beacon – Asymptote Labs (Go · MIT) Asymptote-Labs/agent-beacon Install: docs.beacon.sh Memory docs: docs.beacon.sh Plans: docs.beacon.sh 3. harry0703/MangoDisk – Harry (Rust · GPL-3.0) harry0703/MangoDisk Download: mangodisk.app 📰 News mentioned • Replit makes OpenAI its default, drops Anthropic (Oct 16): techcrunch.com • JetBrains' Java and Kotlin extension for VS Code and Cursor reaches 1.0 (Oct 15): blog.jetbrains.com Star counts are as of 22 October 2026. Performance and cost claims are as reported in each project's README. Summaries are simplified; see the repos for full details. Images: • Repo page screenshots: github.com/ethanplusai/harvey, github.com/Asymptote-Labs/agent-beacon, github.com/harry0703/MangoDisk · screenshot • Harvey dashboard: github.com/ethanplusai/harvey/blob/main/docs/dash… · MIT • Beacon local dashboard: github.com/Asymptote-Labs/agent-beacon/blob/main/… · MIT If you found this useful, like and subscribe for the next round of trending repos. #GitHub #OpenSource #AIAgents #DeveloperTools #ClaudeCode

Bringing context from Claude Code or Cursor into Codex A correction you gave Claude Code can still be useful when you're working in Codex. Beacon lets you save it for that next session without copying over the whole chat. I'm one of the founders of Asymptote Labs, the team behind Beacon. It records your coding sessions, and you can ask an agent to draft a lesson from one of them. You review it before saving it. Codex can then look it up through Beacon's MCP server, along with the session it came from. To try it, install the Beacon CLI, configure session capture, and add the Codex plugin using the setup docs below. One setup detail: Cloud is preselected. Choose Local if you want to keep captured sessions on your machine. Repo and demo: Asymptote-Labs/agent-beacon

Open-source, cross-harness memory for AI agents Earlier this year, my co-founder and I found ourselves frequently switching between different coding agents (Claude Code, Codex, Cursor) anytime we ran out of shaky usage limits or a newer, better model came out. We became increasingly frustrated with having to re-explain our tasks, workflows, common mistake patterns, etc. anytime we switched agents. We found no good free alternatives out there, so we built our own and fully open-sourced it! Beacon hooks into 20+ different agent harnesses, captures session telemetry (prompts, tool calls, command executions, etc) in one normalized format, and distills it into common patterns and repeatable workflows with a human-approval step. This compounded knowledge is then accessible to any future agent via skills / MCP. We believe your agent data is yours to own and should not be locked behind any frontier lab's ecosystem or closed memory infrastructure. We built Beacon to make working across agents way more transparent and efficient. Try it out and tell us what you think: Asymptote-Labs/agent-beacon

It's been an honor watching @jqdsouza and @shakshukan build Beacon at @spc Check it out here! Asymptote-Labs/agent-beacon

📌 مستودع Beacon على GitHub (مجاني ومفتوح المصدر) مع طريقة التثبيت: Asymptote-Labs/agent-beacon