#coding-agents · IA & ML
Agents de code
Codex, Cursor, Gemini CLI, Aider et d’autres agents qui codent pour vous, avec leurs plugins et fichiers de consignes.
Ce mois-ci (9 oct. – 7 nov.), en tête : dsh-superagent-prototype (+20 707), dsh-Go (+14 026) et elephant-goldfish-model (+13 528). Les 1 225 projets classés ont gagné 521 314 étoiles.
Mis à jour le 7 nov., 16:39 UTC · classé toutes les heures à partir des étoiles quotidiennes de GitHub
Mis à jour il y a 37 min
Classement du mois
- 1deepseek-ai/dsh-superagent-prototype Towards a More Autonomous Agent SystemGagnées en 30 j +20,7 k Score 2 070,7 Total 20,7 k
- 2ccch1mneyyy/dsh-Go dsh-go — DeepSeek Harness 装进口袋:手机本机运行,也能遥控你的电脑。Gagnées en 30 j +14 k Score 1 402,6 Total 14 k
- 3google/elephant-goldfish-model Open-source plugin for designing and reviewing software with agentsGagnées en 30 j +13,5 k Score 1 352,8 Total 13,5 k
- 4microsoft/TokenEconomizer Experience-Driven Black-Box Cost Control for Coding AgentsGagnées en 30 j +4,9 k Score 493,4 Total 4,9 k
- 5Folkbench/folkbench AI API 中转站评测排行与切换工具:实测可用率、延迟与价格 · Open-source AI API relay benchmark, rankings & switcher for Claude Code / CodexGagnées en 30 j +3,7 k Score 372,2 Total 3,8 k
- 6JetBrains/thinkrail ThinkRail is the agentic IDE that gets better every time you use itGagnées en 30 j +7,4 k Score 327,2 Total 7,9 k
- 7yetone/magpie Every agent's model. One place. Codex on DeepSeek, Claude Code on Kimi, from the menu bar.Gagnées en 30 j +24,8 k Score 299,2 Total 31,7 k
- 8nightly-labs/openbot A local-first desktop workspace for persistent AI teammates. Run Codex, Claude, and Grok with dedicated workspaces, task queues, file sharing, browser control, and agent-to-agent collaboration.Gagnées en 30 j +5,7 k Score 264,4 Total 6,2 k
- 9benjitaylor/skills Skills for AI coding agents.Gagnées en 30 j +2,3 k Score 228,1 Total 2,3 k
- 10reason-machines/reason-network Reason Network: your team's coding agents, talking to each other. The engine behind `reason network`.Gagnées en 30 j +1,6 k Score 164,2 Total 1,6 k
- 11 Gagnées en 30 j +24,4 k Score 150,7 Total 50,8 k
- 12ranxianglei/billion-context A context-compression plugin for month-long single sessions (billions of tokens) ,small context windows (a 100K context is enough) and token savings (5x fewer tokens) .上下文压缩插件,月级长会话会话, 兼顾小窗口(100k上下文足矣)省token(省5倍token) . billion-context is all you needGagnées en 30 j +3,8 k Score 147,6 Total 4,5 k
- 13ZiChuanLan/agent-purge One persona, many coding agents. Replace or inject system prompts across codex, claude, opencode, grok, omp, hermes, pi, zcode - with a local web console.Gagnées en 30 j +1,4 k Score 139,2 Total 1,4 k
- 14leepokai/Codync Open source Grok Bot alternative, Bring your own agent and subscription: message Claude Code, Codex, Gemini CLI, Cursor, Copilot and 40+ AI agents as bots on your own computer, from iPhone, Mac, Windows, Linux or terminal. Agent-agnostic and free. Also a Muse and Dots alternative. Built in Rust.Gagnées en 30 j +1,8 k Score 136,6 Total 2 k
- 15liguobao/ds-harness-remote 基于 DeepSeek Harness 插件机制构建的远程访问方案,通过低延迟、端到端加密的 P2P 网络,支持使用 PC、移动端 和 Web 随时访问本地设备上的DSH 、CodeX、Cursor、Claude Code等工作区。 (Built on DeepSeek Harness plugins, this low-latency, end-to-end encrypted P2P solution lets PC, mobile, and web clients access local DSH, Codex, Cursor, and Claude Code workspaces.)Gagnées en 30 j +1,9 k Score 111,6 Total 2,1 k
- 16aicodeking/pandacode PandaCode: a calm desktop workspace for coding agentsGagnées en 30 j +1,1 k Score 111,1 Total 1,1 k
- 17emanuele-em/kanzo Self-hosted, sharable kanban for humans and agents. One 4.7 MB binary, 5 MB of RAM, 10 to 60 tokens per agent reply, starts in 3 ms, zero setup.Gagnées en 30 j +1,1 k Score 108,6 Total 1,1 k
- 18dagoSte/squadra Coordinate Claude, Codex and Cursor windows with shared tasks, acknowledgements, prechecks, parallel tests, source-bound proofs and independent review. Built-in skills recall lessons, simplify code and forecast work. Track progress, decisions and evidence in a bilingual local dashboard, with MCP…Gagnées en 30 j +1,1 k Score 108,2 Total 1,1 k
- 19stablyai/orca Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription. Available on desktop, mobile and remote runtime.Gagnées en 30 j +30,9 k Score 104,3 Total 118 k
- 20feimacode/open-design-agent-kit Make posters, social posts, slides and landing pages in the coding agent or chat you already use (Copilot, Claude, Codex, Cursor), with 198 design systems, checks and PDF/PNG/PowerPoint export.Gagnées en 30 j +1 k Score 104,2 Total 1 k
- 21feder-cr/git-ai Git designed for AI agents. Open-source, in the spirit of Anthropic's Scion and OpenAI's Pando. Not affiliated with either.Gagnées en 30 j +1 k Score 103,1 Total 1 k
- 22Harvil1/codeAgent CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and edits files, runs commands and tests, and iterates until the task is done — all with a transparent, extensible tool loop.Gagnées en 30 j +1 k Score 100,8 Total 1 k
- 23WhiteTowerAI/ohmygame The open-source studio for making games with AI. Your own one-person game studio. Everything you need to make games with AI, in one app. Game canvas. Bring your own key.Gagnées en 30 j +1,5 k Score 97,5 Total 1,7 k
- 24yzlin286-wq/Deepscient 让 AI 与人类一起攻克真正的科学难题 —— 12 阶段 55 门 · 36 工具 · 98 条技能 · 证据链与可复现Gagnées en 30 j +942 Score 94,2 Total 942
- 25shx2005/codex-account-switcher 你是否厌倦了 Codex 多个账号之间来回切换?本地账号管理、官方登录、额度查询、快速切换与跨设备导入导出。Local Codex account profiles, login, usage, switching, and export/import.Gagnées en 30 j +937 Score 93,7 Total 937
- 26kitlangton/scrawl Show an agent a problem: mark up, record, sendGagnées en 30 j +887 Score 88,7 Total 887
- 27YizhengWw/HachimoDock A desktop pet that reacts to your Claude Code sessions in real-time — thinking, typing, juggling, sleeping, and more.Gagnées en 30 j +867 Score 86,7 Total 933
- 28franzenzenhofer/big-arrow-on-the-screen Let your AI agents paint big arrows, boxes and text on your Mac screen. One CLI, click-through, gone by itself. Skill for Claude Code and Codex. MIT.Gagnées en 30 j +835 Score 83,5 Total 835
- 29sno-ai/sno-station-skills Sno Station Skills: 31 tested skills that turn Claude Code and Codex into one working team. Cross-vendor peer review, automatic handoff when an agent hits its quota, a one-page morning brief, work orders with proof, and a nightly loop that learns from your own sessions. Open source, installed with…Gagnées en 30 j +790 Score 79,0 Total 861
- 30richiemcilroy/Tov A TypeScript-shaped language built for coding agents. It compiles to small, fast native binaries.Gagnées en 30 j +782 Score 78,2 Total 783
- 31FinanceFlash/unvibecode Complex code hides connections, workflows, and business risks.Unvibe complex code. Trace business workflows.Gagnées en 30 j +1,1 k Score 77,2 Total 1,3 k
- 32davidondrej/cloudroom Cloud agents for any harness. Claude Code, Codex, Pi, and OpenCode run in isolated sandboxes, and live sessions move between your Mac and the cloud.Gagnées en 30 j +1,2 k Score 73,5 Total 1,5 k
- 33dominikmartn/harp Run many Claude Code and Codex agents side by side, in one sidebar that tells you which one needs you. An unofficial fork of Warp.Gagnées en 30 j +708 Score 70,8 Total 708
- 34NB-Corp/gpt-with-taste Better judgment. Better taste. Less ceremony. System instructions and source-aware steering for GPT in Codex.Gagnées en 30 j +667 Score 66,7 Total 667
- 35pullboard-dev/pullboard Autonomous development for real products. Governed agents build from specs you approve, follow the rules you set, and nothing merges until another agent proves it. Your decisions, judgement and taste are the bar that work must clear. Declare your vision and let agents build it.Gagnées en 30 j +666 Score 66,6 Total 734
- 36akitaonrails/ai-memory Solution for long term memory for agent coding CLIs and to facilitate handoff between different agent vendorsGagnées en 30 j +6,3 k Score 66,4 Total 15,3 k
- 37z91772524-ai/pojia-next 三个 AI 客户端的内置提示词一键替换:DSH / WorkBuddy / ZCode。双击即用、可自证、改前备份、一键还原。v8.29:卡片式界面、登录强制激活码、DSH 插件自动注入、官方群验证。免装 Python 单文件 exe,完全免费开源。Gagnées en 30 j +898 Score 65,5 Total 1,1 k
- 38SakanaAI/AI-Scientist-v3 The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)DiscoveryGagnées en 30 j +652 Score 65,2 Total 652
- 39ThinkWatchProject/ThinkWatch-Lite Local gateway for Claude Code, Codex and other AI clients on macOS, Windows and Linux: switch upstreams without touching clients, keep API keys from relays, cut off malicious tool calls, trace every request.Gagnées en 30 j +636 Score 63,6 Total 725
- 40shinshin86/mesh-avatar-studio Turn one illustration into an animated 2D mesh avatar with a coding agent and a local editorGagnées en 30 j +1,4 k Score 61,1 Total 1,9 k
- 41Lee-xeo/Claude-Cage Cage:Mac 上的独立 Claude 编码工作区,集成 Linux 终端、浏览器与项目编辑器。Gagnées en 30 j +567 Score 56,7 Total 567
- 42 Gagnées en 30 j +554 Score 55,4 Total 554
- 43sv3nbeast/agent-manager-lite macOS 上的 Codex、Claude Code CLI 与 Claude Desktop 多实例管理器,统一管理账号、供应商密钥、独立配置、会话与代理。 / A macOS manager for Codex, Claude Code CLI and Claude Desktop instances, accounts, provider keys, isolated configs, sessions and proxies.Gagnées en 30 j +545 Score 54,5 Total 545
- 44MiniMax-AI/mcode-stack The workflows and skills the MiniMax Code team uses to build MiniMax Code. Open source, install and use.Gagnées en 30 j +545 Score 54,5 Total 545
- 45HazAT/ultimate A local coding agent with a web UI that builds itself while it runs, on Pi DurableGagnées en 30 j +523 Score 52,3 Total 523
- 46N4darae/shrt A contract-driven gRPC regression harness for AI coding agents, with human-approved baselines. Snapshot the valid call chains of an API so an agent can look one up instead of tracing for it. gRPC today, OpenAPI nextGagnées en 30 j +1,6 k Score 51,9 Total 2,5 k
- 47Graphicle-AI/graphicle Code graph and memory for your coding agents, in one Rust program. For Claude Code, Codex, Cursor and any MCP client.Gagnées en 30 j +516 Score 51,6 Total 516
- 48cursor/plugins Cursor plugin specification and official pluginsGagnées en 30 j +5,2 k Score 51,4 Total 15,6 k
- 49soumatheusgomes/vibe-coding-toolkit A curated, battle-tested AI-coding toolkit: Claude Code plugins, subagent orchestration, quality gates, and ready-to-copy prompts, extracted from real production use.Gagnées en 30 j +1,5 k Score 51,1 Total 2,3 k
- 50opensec-git/Pi-Bolt ⚡ Pi, the coding agent, compiled ahead of time to one native executable. 10× faster to start, 7× less CPU and 4.5× less memory than Pi on Node. Linux, macOS, Windows, ARM64 and Android (Termux).Gagnées en 30 j +600 Score 50,0 Total 744
- 51mksglu/context-mode Free, local plugin that keeps tool output out of your coding agent's context window. Sandbox and SQLite FTS5 search, 99% fewer bytes in context. Works with Claude Code, Codex, Pi, OpenCode, Gemini CLI, Copilot CLI and 4 more agents. Zero telemetry.Gagnées en 30 j +8 k Score 49,7 Total 33,6 k
- 52devswha/ovis Ovis (formerly herdr web UI): free, open-source browser and phone client for herdr. Chat and live terminal for Claude Code, Codex and every agent pane, remote PCs over SSH, web push alertsGagnées en 30 j +1,3 k Score 48,8 Total 1,9 k
- 53herdrdev/herdr-core herdr-core: terminals for coding agentsGagnées en 30 j +468 Score 46,8 Total 468
- 54runloom/pier 几个 AI 终端开着,谁在等你一眼能看见。Claude Code、Codex 还在原来的终端里,旁边就能改文件、看 Git。macOS 本地工作台。Gagnées en 30 j +464 Score 46,4 Total 561
- 55Kai-Jungsthoefel/SOMA Desktop app for designing parametric 3D models in CadQuery together with the coding agent of your choiceGagnées en 30 j +463 Score 46,3 Total 463
- 56ccch1mneyyy/dsh-TUI DSH's officially top-recommended TUI plugin — high performance, low overhead, cute pixel whale, smooth mouse interaction. One-command install via npm. / DSH 官方首推的 TUI 插件,高性能低占用,可爱像素鲸鱼,流畅鼠标交互,npm 一键安装Gagnées en 30 j +3 k Score 46,2 Total 7,1 k
- 57AxiomCodeAI/axiomcodegraph Turn any codebase into a knowledge graph grounded in formal methods. Your AI agents get exact answers for any code-related task, ensure correctness, and optimize time and token usage.Gagnées en 30 j +450 Score 45,0 Total 516
- 58Alishahryar1/free-claude-code Use Claude Code, Codex, Antigravity, VSCode, Pi, and OpenCode (and 6 other harnesses) for free (1.3B+ free tokens) from your terminal, app, IDE, or phone, and now from the browser with native browser sessions (multi-harness + multi-model) like OpenClaw (voice supported + ToS friendly)Gagnées en 30 j +10,5 k Score 44,3 Total 67,1 k
- 59zgcagi/Harness-RSI Harness self-evolution: update targets, theory, evaluation, and reported evidence. Bilingual reading list and project website.Gagnées en 30 j +436 Score 43,6 Total 437
- 60Louis-CFM/coucou A tiny friend in your Mac's notch and on your iPhone that keeps an eye on your AI coding agents: Claude Code, Codex, Cursor, Gemini CLI, Antigravity and more. Approve from the notch or your Lock Screen.Gagnées en 30 j +2,8 k Score 43,3 Total 7 k
- 61solongate/agent-security Local-first, open-source security gateway for AI coding agents. Enforce tool-call policies, detect secrets, and audit actions on-device.Gagnées en 30 j +427 Score 42,7 Total 428
- 62anywhere-labs/Agents-Anywhere 跨设备的开源Agent工作台Gagnées en 30 j +1,6 k Score 41,0 Total 3,1 k
- 63wuyoscar/Internal-Safety-Collapse [NeurIPS 2026] Safety failures in coding agents and frontier LLMs. Reproducible workspaces for studying when AI agents generate unsafe data during task completion.Gagnées en 30 j +1,4 k Score 40,8 Total 2,6 k
- 64omnirush-ai/omnirush-gui A desktop coding agent with free access to frontier models.Gagnées en 30 j +2,1 k Score 40,7 Total 4,9 k
- 65higress-group/HiRoute Make Codex and Claude Code subscriptions go further: a local model router that gives routine agent work to economical models and keeps your strongest model for the hard parts.Gagnées en 30 j +393 Score 39,3 Total 422
- 66Charonyuu/whatsmyagentdoing See what every Claude Code and Codex agent on your machine is doing — live, in a little office.Gagnées en 30 j +386 Score 38,6 Total 386
- 67guregodevo/memdoor AI coding agent that makes a team of small models beat a frontier oneGagnées en 30 j +373 Score 37,3 Total 374
- 68Asymptote-Labs/agent-beacon The cross-harness, self-improving memory layer for AI agents. Join our community: https://discord.com/invite/zdNChS2fBuGagnées en 30 j +1,6 k Score 37,2 Total 3,4 k
- 69Muvon/octomind Open-source AI coding agent and agent runtime: one binary, any model, MCP-native. Runs in terminal, CI, or as a daemon.Gagnées en 30 j +449 Score 37,0 Total 596
- 70lokicorvus/crosspet 跨 AI 桌宠:跟着你用的 AI 换形象、跟着 AI 的工作状态做动作Gagnées en 30 j +368 Score 36,8 Total 428
- 71Innei/ryugi 流儀 — a skills collection for coding agents and the artifacts workbench they design in: live artboards, commentable documents, HTML test benches, TDD buildsGagnées en 30 j +366 Score 36,6 Total 366
- 72kyy-logs/code-review-skill Auditable code review skill for Claude Code and Codex: four independent probes, evidence-backed findings, and a JSON-derived merge gate.Gagnées en 30 j +357 Score 35,7 Total 357
- 73rlaope/oh-my-hermes ⚚ The coding harness with Hermes Agent wired into IDE.Gagnées en 30 j +2 k Score 35,5 Total 5,2 k
- 74Entelligence-AI/agentplay Replay your coding agent sessions as a map and a timelineGagnées en 30 j +355 Score 35,5 Total 355
- 75uniquechao/PandaDOS Your self-hosted control plane for Claude Code and Codex. Turn issues into queued, observable, approval-aware coding workflows—from any browser.Gagnées en 30 j +347 Score 34,7 Total 363
- 76Atoll92/agent-standup Your Claude Code, Codex and Mistral Vibe sessions as a live, animated team call: who is working, who waits on whom, who needs you. VS Code extension, terminal command, desktop app. Runs locally, zero tokens.Gagnées en 30 j +346 Score 34,6 Total 346
- 77addyosmani/agent-skills Production-grade engineering skills for AI coding agents.Gagnées en 30 j +10,8 k Score 33,5 Total 114 k
- 78nuphos/nuphos The agent workspace for your team — run, manage and collaborate on coding agents across people, machines and tools.Gagnées en 30 j +333 Score 33,3 Total 373
- 79didi/helixharness HelixHarness 提供完整的 AI Coding 工程化基础能力,还支持不同企业和团队结合自身的业务知识、工程规范和研发流程,持续构建和演进属于自己的专属 HarnessGagnées en 30 j +328 Score 32,8 Total 328
- 80mvschwarz/openrig Build your own network of agents from Claude Code, Codex and Pi: persistent teams with roles, shared context and owned work.Gagnées en 30 j +2,5 k Score 32,2 Total 8,7 k
- 81delta-box/deltabox-lite Lightweight, agent-native sandboxing with diff, commit and abortGagnées en 30 j +320 Score 32,0 Total 321
- 82devvmhq/devvm One VM for every project. An isolated sandbox with your project’s toolchain, ready for you or a coding agent to start codingGagnées en 30 j +319 Score 31,9 Total 319
- 83poco-ai/Agentero Unified research workspace for humans & agents — PDF Q&A with citations, Vault, writing. 为人与 Agent 协作的科研工作台;补齐 Zotero 时代的人机上下文断点。Gagnées en 30 j +948 Score 31,7 Total 1,8 k
- 84openqodex/openqodex Open source AI code review for coding agents. A separate reviewer checks every change your agent writes before you push, in Claude Code, Codex, Cursor and Cline. No account or key of its own.Gagnées en 30 j +650 Score 31,6 Total 1,1 k
- 85Wunsch2048/codex-bailong-desktop-pet Codex&GPT桌宠数据中心 | 你桌面的龙娘小助手Gagnées en 30 j +314 Score 31,4 Total 314
- 86savannahfeder/agentbox A desktop GUI for running dozens of Claude Code and Codex agents in parallel, each in its own git worktree. Answer them like email, or use the board view. Free, open source, on the plan you already pay for.Gagnées en 30 j +313 Score 31,3 Total 371
- 87rudderlabs/devbox Open source autonomous engineering harness in your cloud. One sandbox per task, no real secrets inside.Gagnées en 30 j +312 Score 31,2 Total 312
- 88Xpropel/Pi-Remote Remote control for your pi coding agent. Pi-Remote mirrors live pi terminal sessions to any browser, so you can watch runs, answer prompts, and send commands from your phone — end-to-end encrypted over a self-hosted relay.Gagnées en 30 j +311 Score 31,1 Total 311
- 89farion1231/cc-switch A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode,DeepSeek Harness and more. Only official website: ccswitch.ioGagnées en 30 j +11,7 k Score 31,1 Total 153 k
- 90tigerless-labs/cost-xray See what Claude Code and Codex actually send to the API — and what each part costs.Gagnées en 30 j +1,9 k Score 30,3 Total 5,8 k
- 91cluster1900/apexo-code Apexo: An open-source, general-purpose coding agent for terminal (TUI), web, and desktop with autonomous goals, workflows, persistent memory, command sandboxing, and first-class support for Gemini, Grok, and OpenAI-compatible models.Gagnées en 30 j +303 Score 30,3 Total 303
- 92seacen/meetcap Powerful, free, context-aware AI native meeting assistant that transcribes real-time and locally on your computer, writes the minutes, and lets your AI agent drive it.Gagnées en 30 j +303 Score 30,3 Total 303
- 93max-sixty/worktrunk Worktrunk is a CLI for Git worktree management, designed for parallel AI agent workflowsGagnées en 30 j +2,9 k Score 30,2 Total 11,9 k
- 94anomalyco/opencode The open source coding agent.Gagnées en 30 j +13,8 k Score 30,1 Total 225 k
- 95TannerMidd/pi-pocket A durable, multiplayer, mobile-first web app for Pi agents, built on Pi DurableGagnées en 30 j +507 Score 30,0 Total 793
- 96herdrdev/herdr the runtime your coding agents live onGagnées en 30 j +6,2 k Score 29,9 Total 49 k
- 97vercel-labs/durable-harness Durable coding-agent harnesses (Claude Code, Codex, OpenCode, Pi, fx) on a Workflow SDK WorldGagnées en 30 j +296 Score 29,6 Total 296
- 98lllleolin-max/VibeGit Local-first desktop safety net for AI-assisted coding. Create checkpoints, inspect changes, safely restore versions, and back up projects to GitHub—without destructive Git commands.Gagnées en 30 j +292 Score 29,2 Total 297
- 99YMuskrat/agentctx Lifecycle-managed, auditable project context for AI coding agentsGagnées en 30 j +289 Score 28,9 Total 291
- 100duyunzhoudyz/dyz-med-paper-skills 医学论文写作与科研助手:面向中国医生和医学研究生的 32 个 Agent Skills,适用于 Claude Code、Codex,覆盖选题、PubMed 文献检索、中英写作、选刊投稿与审稿修回。Medical writing & research skills.Gagnées en 30 j +285 Score 28,5 Total 285
- 101Get-Concord-AI/concord-mcp Live messaging for coding agentsGagnées en 30 j +576 Score 28,2 Total 993
- 102MicTx/spec-harness 面向 AI 编程智能体的任务包工作流工具,用可验证的范围、证据和 Git 门禁管理长期改动。(Task-package workflow for AI coding agents with verifiable scope, evidence, and Git gates.)Gagnées en 30 j +278 Score 27,8 Total 283
- 103eduwxyz/tucano Your team of AI agents, on your Mac, Windows or Linux. Agents that talk in channels, write code, review each other and use your tools, on the Claude Code, Codex, OpenCode or Pi you already have. Anything that touches the real world waits for your yes.Gagnées en 30 j +277 Score 27,7 Total 277
- 104artemchuikin/youtube-skills YouTube transcript skills for Claude Code, Cursor and Codex. Agent Skills to get transcripts, search YouTube, read channels and playlists, and bulk export.Gagnées en 30 j +273 Score 27,3 Total 273
- 105ericrisco/rsc-harness Your agent invents things because it has no memory, and can't touch your database because it has no arms. rsc is the meta-harness that gives it both, plus the trade to know the job and the reflexes to not break your repo. For Claude Code, Codex and 15 more.Gagnées en 30 j +359 Score 27,3 Total 532
- 106Romeroc751700/chatgpt-plus-pro-codex-cn-guide ChatGPT Pro100(10x,原5x)/Pro200(20x)国内购买与续费指南:Pro100 的 Work/Codex 套餐内用量翻倍、售价不变;本人账号、支付宝、自助或人工办理及30天订阅保障。含中文、English、Русский。Gagnées en 30 j +267 Score 26,7 Total 267
- 107ruvnet/ruflo 🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more IntegratedGagnées en 30 j +7,2 k Score 26,6 Total 81,1 k
- 108ZipengWu365/TOMC TOMC Memory: CPU context compression and task memory for Codex, Claude Code, Cursor, TRAE, WorkBuddy and other MCP clients.Gagnées en 30 j +264 Score 26,4 Total 264
- 109tony3liu/eido AI coding agent workspace for macOS, built on Zed and pi. Native code editing and review, browser use, computer use, and global agent access controls.Gagnées en 30 j +263 Score 26,3 Total 270
- 110lobehub/awesome-rsi A curated research map of Recursive Self-Improvement (RSI): models, agents, harnesses, embodied systems, automated AI R&D, benchmarks, and safety.Gagnées en 30 j +541 Score 26,3 Total 965
- 111ShuaiMXu/happyhands Open-source, AI-assisted UI design review for coding agents. Inspect screenshots, scope code changes and compare results in a local workbench. Alpha.Gagnées en 30 j +262 Score 26,2 Total 262
- 112sno-ai/sno-station When Claude Code hits its usage limit, Codex picks the task up from the same memory. Sno Station puts Codex, Claude Code, Cursor, Hermes Agent and OpenClaw on one squad: they hand work to each other and review each other's code. Open source, runs on your computer.Gagnées en 30 j +539 Score 25,5 Total 985
- 113dstrml/wu The fast, native code editor and agent workspace.Gagnées en 30 j +348 Score 25,4 Total 535
- 114Balanov/uncut The lossless, headless coding agent harness. One 7 MB static binary, four tools, plain stdin/stdout, no silent cuts.Gagnées en 30 j +254 Score 25,4 Total 254
- 115NewBeeM4n/codex-overload-fix A local retry shim that stops Codex's "Selected model is at capacity" error from interrupting your work.Gagnées en 30 j +252 Score 25,2 Total 252
- 116HarnessRouter/harnessrouter HarnessRouter Community Edition: the self-hosted, Apache-2.0 edition of the unified interface for agent harnesses. Run Codex, Claude Code, Hermes, PI, DSH, and more through one API, with sessions, streaming, files, cancellation, and failure handling. Implements the Unified Harness Protocol (UHP)…Gagnées en 30 j +1,4 k Score 25,1 Total 4,3 k
- 117Akillll-DuoHe/fy-code-animation 把中文文案、画风提示词和声音做成前后连贯的代码动画(Remotion / Canvas / HTML)的 DeepSeek Harness 技能。341 画风库检索、语义分镜、镜头转场、角色表演、四案音乐与音效、检查返修。Gagnées en 30 j +249 Score 24,9 Total 249
- 118lennney/stop-that-shit Stop That Shit(别再造史了)|面向 Codex/GPT 场景的多平台 Hook + Skill Guard:拦截 AI coding agent 无需求的哈希、校验和与任务范围膨胀。 A multi-platform Hook + Skill Guard for AI coding agents in Codex/GPT workflows: stop unrequested hashes, checksums, and task-scope creep.Gagnées en 30 j +1,2 k Score 24,5 Total 3,7 k
- 119alibaba/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, thread-safety, XSS, SQL injection), OpenAI & Anthropic compatible.Gagnées en 30 j +5,1 k Score 24,3 Total 49,6 k
- 120edenfunf/reelmimic Show it a video you love. Get a new video in the same style. An AI crew (Claude Code or Codex) plans, builds and reviews it with you.Gagnées en 30 j +764 Score 23,7 Total 1,8 k
- 121getpaseo/paseo Orchestrate multiple coding agents from desktop and mobileGagnées en 30 j +3,3 k Score 23,5 Total 23,4 k
- 122 Gagnées en 30 j +371 Score 23,5 Total 621
- 123SnowSky1/universal-imagegen-agent 把 Codex imagegen 的工作流与提示词库带到任意智能体;支持 npm/pnpm 一键安装、配套 skill、独立 API 与 Qwen-Image 兼容网关。Gagnées en 30 j +233 Score 23,3 Total 233
- 124alexsergivan/kwant Your own team of AI bots in one self-hosted binary: spaces, every account you have, handoffs, approvals and routines. Open-source, self-hosted alternative to Grok Bot, Claude Duet and OpenAI dots. Rust + React.Gagnées en 30 j +228 Score 22,8 Total 228
- 125wangmiaozero/pi-harness The operational superset of Pi Coding Agent — everything Pi, plus observability, governance, recovery, evaluation and multi-agent orchestration. Pi Coding Agent 的运维超集——完整继承 Pi 的核心能力,并进一步扩展可观测性、治理、故障恢复、评估和多 Agent 编排。Gagnées en 30 j +225 Score 22,5 Total 293
- 126klarluft/pitupitu Talk to Claude Code and Codex by voice, from your phone, on any of your machines. The open-source box agent for pitupitu.chat; your agents run in herdr.Gagnées en 30 j +223 Score 22,3 Total 223
- 127jiucai0915-sys/deepcode DeepSeek-native coding agent for your terminal | DeepSeek 原生终端编程 AgentGagnées en 30 j +222 Score 22,2 Total 231
- 128christos-antono/NPCTalk Make any NPC in any game talk back with Fish Audio: skills, a self-hosted voice server and tools for AI coding agents, with a full GTA V example.Gagnées en 30 j +221 Score 22,1 Total 221
- 129earendil-works/pi AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLIGagnées en 30 j +7,4 k Score 22,1 Total 121 k
- 130github/spec-kit 💫 Toolkit to help you get started with SDD or any other process!Gagnées en 30 j +8,2 k Score 22,0 Total 148 k
- 131aindeev/agent-chrome-relay Let your AI agents use your Chrome, signed in as you, in background tabs. By Alexey Indeev · blog: read.aindeev.com · X: @AlexeyIndeevGagnées en 30 j +219 Score 21,9 Total 219
- 132uucz/moyu 🐟 狠狠 PUA 你的 AI,然后自己准时下班。Make your AI grind, so you don't have to. Benchmarked: 66% less code.Gagnées en 30 j +217 Score 21,7 Total 296
- 133madebymustafa/design-taste 24 open-source agent skills that turn taste into instructions — ten genre identities, each proven by a same-brief before/after demoGagnées en 30 j +216 Score 21,6 Total 218
- 134aicodeking/deepseek-stack Agent skills that make DeepSeek models plan, verify and ship like frontier models. npx skills add aicodeking/deepseek-stackGagnées en 30 j +215 Score 21,5 Total 215
- 135tencentmusic/modus 从需求澄清到可信交付的 Agent 编程 Harness 工程框架Gagnées en 30 j +213 Score 21,3 Total 213
- 136eliasstravik/shepherdr Run many coding agents across machines from a phone, tablet or desktop. A herdr plugin.Gagnées en 30 j +510 Score 21,2 Total 1,1 k
- 137dragonked2/alphacode Free MIT AI coding agent — no API key needed. Built-in free model, or bring Claude, GPT, Gemini, DeepSeek, Ollama +50 more. Swarm mode, 40+ tools, browser & desktop automation, built in Rust.Gagnées en 30 j +328 Score 21,2 Total 568
- 138Gentleman-Programming/gentle-shell Gentle Shell is a Pi-native workspace for AI-assisted development, bringing parallel coding agents, live tasks, Git diffs, persistent memory, and permission controls into one terminal interface. Powered by Gentle AI and Organic Driven Development (ODD).Gagnées en 30 j +736 Score 20,9 Total 2 k
- 139KenKaiii/gg-framework The coding agent that gets more out of your AI subscription. Fastest and leanest of 20 agents tested, with unlimited local search of real open-source code.Gagnées en 30 j +207 Score 20,7 Total 235
- 140decodingai-magazine/building-a-coding-agent-from-scratch-course Learn harness engineering by building Claude Code from scratch. Free, open-source course: 8 articles, 6 videos, 1 codebase.Gagnées en 30 j +512 Score 20,6 Total 1,1 k
- 141Agenta-AI/awesome-ai-agent-platforms A curated list of open-source AI agent platforms: AI coworkers and teammates, agent builders and frameworks, workflow automation platforms, browser agents, and coding agents, with licenses.Gagnées en 30 j +296 Score 20,3 Total 508
- 1423241288994/AImanager 让你的 AI 发挥更多价值|ChatGPT 项目上下文接入,Codex / Claude Code 与 API 多模型协作、交叉审阅,统一账号额度与会话管理Gagnées en 30 j +203 Score 20,3 Total 212
- 143vybenetwork/solana-mcp-vybe Public Solana MCP registry metadata for Vybe Solana APIGagnées en 30 j +836 Score 20,2 Total 2,5 k
- 144witnesstodark/mr-mak-workspace A local desktop workspace for Codex and Claude Code, with project reports, creative skills and optional voice.Gagnées en 30 j +371 Score 20,1 Total 711
- 145Gaurav-Gosain/tuios A terminal window manager that knows what your agents are doing. Tiling panes, workspaces, sessions that survive restarts, and one Inbox for every coding agent. Official only at tuios.dev and this repo. tuios has no X/Twitter account.Gagnées en 30 j +1,4 k Score 19,7 Total 6,4 k
- 146can1357/oh-my-pi ⌥ Coding agent with the IDE wired in. Built by Stencil Labs.Gagnées en 30 j +3,6 k Score 19,4 Total 38,1 k
- 147marvkr/better-design 🎨 Open-source design MCP server + shadcn/ui registry — AI design systems for Claude Code, Cursor, Codex, GitHub Copilot & any MCP client. 31 brand-grade themes (Linear, Stripe, Vercel, Notion, Apple, Supabase, Figma…) + design tokens, UI principles & WCAG rules. Install any component with one…Gagnées en 30 j +305 Score 19,1 Total 559
- 148lemonadesaltbagel/sill Native Windows Bash for AI coding agents. Run Claude Code, Codex, opencode & Gemini CLI without Git Bash, MSYS2 or WSL. Built in Rust, with MCP support.Gagnées en 30 j +191 Score 19,1 Total 191
- 149lijiaqi-AI-Product-Manager/dsh-agent-compare 同一需求,两版真跑,体验后审查采用。Two live builds for one task in DeepSeek Harness.Gagnées en 30 j +191 Score 19,1 Total 191
- 150abcwyc/pi-agent-desktop Pi — A cross-platform AI coding agent, bringing the Claude Code experience to your desktop. No environment setup, no terminal commands. Download and start coding right away.Gagnées en 30 j +417 Score 18,9 Total 902
- 151GanyuanRan/Autoloom AI coding with Aegis governance built into execution: baseline-aware changes, evidence-backed delivery. Free desktop client, your choice of model. 将哲科思维融入 AI 开发执行,让变更有依据、交付有证据。用创意编织现实。Gagnées en 30 j +188 Score 18,8 Total 216
- 152blendbunjaku/optimaizr Spend fewer tokens on the same work. A local CLI that finds wasted tokens in Claude Code, Codex, opencode and your own API calls.Gagnées en 30 j +188 Score 18,8 Total 215
- 153Endokelp/Endoplexity Agentic browser control driven by your own Claude / Cursor subscriptionsGagnées en 30 j +242 Score 18,5 Total 413
- 154SLEEPYBQ/MemoSync Co-manage memory with your coding agent across sessions. A local workbench for Claude Code, Codex and Pi.Gagnées en 30 j +185 Score 18,5 Total 186
- 155pulseaiclub/phi A fast coding agent, rpc plugin, sub-agents, sloppy edits, and mcpGagnées en 30 j +414 Score 18,4 Total 922
- 156y5ez3g/facadecode The multi-agent orchestrator for VS Code. Run Claude Code, Codex, and other agent CLIs that start, message, and operate each other across windows and machines.Gagnées en 30 j +182 Score 18,2 Total 182
- 157The-PR-Agent/pr-agent 🚀 PR Agent: The Original Open-Source PR Reviewer. This project is not the Qodo free tier.Gagnées en 30 j +2,1 k Score 18,1 Total 15,4 k
- 158JialaoLiu/dsh-baton Pass the baton from Claude Code or Codex to a local DeepSeek Harness. An MCP server that hands off tasks and brings the result back.Gagnées en 30 j +180 Score 18,0 Total 180
- 159Javis603/token-monitor Local-first desktop widget for tracking token usage, costs, limits, and session activity across 52+ AI coding tools—including Claude Code, Codex, Cursor, OpenCode, OpenClaw, and more—with multi-device sync.Gagnées en 30 j +924 Score 17,9 Total 3,6 k
- 160YCC-Lover/research-starter-skills 面向科研新手的 Codex 科研协作技能集:选题、文献检索与阅读、论文写作、自然润色、审稿返修和可编辑学术汇报。结合 Research-Starter-Kit 原创教程,用 1 个总入口与 6 个专业模块推进研究。 Research training, writing & editable presentations for Codex.Gagnées en 30 j +179 Score 17,9 Total 185
- 161izzyfrm/roblox-ai A curated collection of Roblox UI references for Claude Code, Codex, and other AI coding assistants to study and use as design inspiration - over 12K References.Gagnées en 30 j +178 Score 17,8 Total 178
- 162dom96/KillSwitch An esoteric programming language built to break LLMs and coding agents.Gagnées en 30 j +177 Score 17,7 Total 190
- 163Clearailhc/clearai-dsh ClearAI:以本体为纲的原生 DSH 插件 —— 经证据核验的研究长成可浏览的领域本体。 · ClearAI: an ontology-first DSH agent preset — evidence-checked research that grows into a domain ontology.Gagnées en 30 j +333 Score 17,6 Total 689
- 164hardbeat920/monocode A GUI for your coding agentsGagnées en 30 j +925 Score 17,5 Total 3,7 k
- 165lgwrightlab/schematic-figure Skill for AI agents that draws publication-quality scientific schematic figures as vector codeGagnées en 30 j +173 Score 17,3 Total 173
- 166coco-research/coco Coco Super Intelligence: agent skills, slash commands and subagents for Claude Code, Cursor and Codex. One command installs them into the tool you already use.Gagnées en 30 j +308 Score 17,2 Total 628
- 167PinelliaChill/Operant Operant Beta:以多模型分工、按需通信、分层审批和经验复用为核心设计,在本机组织可追溯的 Agent 协作,并通过模块化架构扩展能力。Gagnées en 30 j +241 Score 17,0 Total 443
- 168miuuyy/codex-chatgpt-web Use ChatGPT Web (including Pro) as a native model in Codex — with context, tools, streaming and images, without using Codex quota.Gagnées en 30 j +2 k Score 16,9 Total 15,6 k
- 169open-mercato/cezar Open-source orchestrator and ADE for running Claude Code, Codex, OpenCode, Pi and other AI coding agents in parallel — locally or 24/7 on your own server.Gagnées en 30 j +398 Score 16,8 Total 959
- 170zero-lab-ai/skills Portable, evidence-bound security skills for authorized defensive assessment, red teaming, penetration testing, detection engineering, and engagement operations.Gagnées en 30 j +168 Score 16,8 Total 168
3 dépôts à la croissance inhabituelle ne sont pas affichés. Afficher le classement complet
Émergents en Agents de code Semaines passées : 26 oct.19 oct.
À propos de ce thème
Certains de ces agents travaillent dans un éditeur, d’autres dans un terminal, dont OpenCode, Cline, Roo Code et GitHub Copilot ; les projets construits autour comptent aussi des harnais qui pilotent un agent. Claude Code et ses ajouts ont leur propre thème. Agents IA couvre les agents de toute sorte, celui-ci s’en tient à ceux qui programment. Pour qui compare les agents, ou cherche des consignes et des extensions pour celui qu’il utilise déjà.