ai-agents

Dépôts en tendance : Agents IA

IA & ML

Frameworks et runtimes pour des agents LLM qui planifient, appellent des outils et agissent.

Mis à jour il y a 15 min

Dépôts classés cette semaine
670
Activité par rapport à la semaine dernière
+65 %

Dépôts classés en Agents IA

90 sur 670 classés · étoiles gagnées cette semaine, rapportées à la taille · min. 20

Comment la santé est calculée
Rang 1

Reverse engineer anything with agents, from app behavior down to native binaries.

TypeScript305 kétoiles au total Santé : En bonne santéTypeScriptClaude Code
+231 k étoiles cette semaine
+1 autres de morluto
Rang 2

Let an AI model use a real iPhone with a $7 ESP32: AirPlay eyes, USB HID hands, any OpenAI-compatible vision model. No Mac, no developer account, no jailbreak.

C3 kétoiles au total EmbarquéC & C++
+3 k étoiles cette semaine
Rang 4

Sandboxed Platform for Agentic Code Execution: pluggable-runtime sandboxes for running agent and user code in isolation.

Rust1,3 kétoiles au total Rust
+1,3 k étoiles cette semaine
Rang 5

ARTEX,AI 自主渗透测试系统。百度 agent+ 攻防挑战赛冠军项目。

Go1,2 kétoiles au total GoSécurité
+1,2 k étoiles cette semaine
Rang 7

Autonomous AI sales agent powered by Claude Code or Codex. Finds prospects, writes cold emails, sends campaigns, handles replies, books meetings. No API keys needed — runs on your Claude or Codex subscriptions.

Python1,2 kétoiles au total Santé : En bonne santéClaude CodePython
+1,1 k étoiles cette semaine
Rang 8

A team of long-lived bots for DeepSeek Harness, with main bots, bot-to-bot messages and group chats.

JavaScript2,4 kétoiles au total JavaScriptAgents de code
+2 k étoiles cette semaine
Rang 9

Scout: the open-source browser agent, by Outcrawl. Mirrored automatically from Outcrawl's own repository.

TypeScript933étoiles au total Tests & QALLM
+933 étoiles cette semaine
Rang 10

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。

JavaScript1 kétoiles au total Applis de bureauJavaScript
+898 étoiles cette semaine
Rang 11

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。

TypeScript1 kétoiles au total ObservabilitéMCP
+927 étoiles cette semaine
Rang 12

Intent compiler for AI agents — converges vague requests into typed IntentSpec contracts (probe, ask, or halt before routing), the input layer for routers and typed-decision models like Jev & Laya

Python763étoiles au total Skills d’agentsClaude Code
+692 étoiles cette semaine
Rang 13

Agent-first reverse engineering for macOS, Windows and Linux: any ACP agent reads, renames and patches binaries, Android apps and GPU kernels next to you.

TypeScript666étoiles au total AndroidRétro-ingénierie
+666 étoiles cette semaine
Rang 14

Ears for coding agents: let AI hear, review and make sound. CPU-only, open source.

Python638étoiles au total AudioMCP
+638 étoiles cette semaine
Rang 15

Local-first AI teammate workspace. Bring your own models and keep project conversations, tool approvals, and results together.

TypeScript620étoiles au total Santé : En bonne santéLocal-firstMCP
+618 étoiles cette semaine
Rang 18

A macOS menu bar app that safely keeps your MacBook awake with the lid closed, for timed agent sessions.

Swift1,5 kétoiles au total SwiftiOS
+1,1 k étoiles cette semaine
Rang 19

Sprix AI at 屿智同行 × 保研岛 — an open-source benchmark for AI agents in Baoyan advising and application planning.

Python504étoiles au total Python
+504 étoiles cette semaine
Rang 20

Scenario for Blender: AI images, video, 3D and PBR materials in the viewport, plus a local MCP server for agents. Blender 5.0+ extension, GPL-3.0-or-later.

Python501étoiles au total Vision par ordinateurMCP
+485 étoiles cette semaine
Rang 21

麦当劳省钱点餐助手(麦门精算师)|麦当劳优惠券组合优化 Skill:拉取麦当劳菜单与全部可用优惠券,算出最省的点餐组合,巨无霸套餐 ¥47 → ¥21.9(省 53%)。McDonalds MCP(麦当劳 MCP)coupon optimizer · McDonalds China MCP Server · Agent Skill for WorkBuddy · 麦当劳程序员创意开发大赛参赛作品

Python516étoiles au total Skills d’agentsMCP
+484 étoiles cette semaine
Rang 22

What The Function: your AI agent decompiles games you own into C that compiles to the exact same bytes. Runs locally.

Python484étoiles au total Santé : ArchivéÉmulationRétro-informatique
+484 étoiles cette semaine
Rang 23

Your personal AI agent in your own Cloudflare account. Chat, memory, tasks, notes and scheduled reminders, deployed with one command: npx create-talorys@latest. Free-tier friendly, single-user, no telemetry.

TypeScript1,3 kétoiles au total Auto-hébergéFrameworks web
+909 étoiles cette semaine
Rang 24

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.

Python865étoiles au total TerminalOutils CLI
+647 étoiles cette semaine
Rang 25

For You Agent——AI 时代的个人随身数字人格。把你的模型、AI 账号、技能、提示词和工作方式,带到每一个 AI 工具里。

Rust933étoiles au total Santé : En bonne santéSkills d’agentsApplis de bureau
+684 étoiles cette semaine
Rang 26

Animated, explorable diagrams for Claude and other coding agents, from a short JSON spec.

JavaScript628étoiles au total DatavizJavaScript
+481 étoiles cette semaine
Rang 27

Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.

Python29,1 kétoiles au total Santé : En bonne santéOutils CLIPython
+5,9 k étoiles cette semaine
Rang 28

An agent skill that finds where a photo was taken — OpenStreetMap geometry, elevation skylines, satellite imagery and street view — and shows its work. Works with Claude Code, Codex, Cursor, Gemini CLI, OpenCode and GitHub Copilot.

Python3,2 kétoiles au total SécuritéVision par ordinateur
+1,5 k étoiles cette semaine
Rang 31

Newsletters where you pay for the emails you send, not for dormant subscribers, at a fraction of the price of beehiiv and the like. Open source: self-host it, or use mailcheap.ai.

JavaScript1,2 kétoiles au total Bases de donnéesAuto-hébergé
+751 étoiles cette semaine
Rang 32

Better judgment. Better taste. Less ceremony. System instructions and source-aware steering for GPT in Codex.

JavaScript351étoiles au total JavaScriptAgents de code
+351 étoiles cette semaine
Rang 33

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

Go30,9 kétoiles au total Santé : En bonne santéSécuritéGo
+5,5 k étoiles cette semaine
Rang 34

Agentic Android launcher: build your own apps and widgets with AI agents, Omarchy themes, Arch Linux without root

Kotlin349étoiles au total KotlinAndroid
+344 étoiles cette semaine
Rang 35

Context is yours. Agents are replaceable.

Python908étoiles au total Santé : En bonne santéPython
+596 étoiles cette semaine
Rang 37

An agent that moves into your Android phone and becomes its soul — not an assistant, not a tool. Any app, no integrations, on-device, one APK.

Kotlin331étoiles au total KotlinAndroid
+317 étoiles cette semaine
Rang 39

☤ The official plugins for Hermes Agent, built and maintained by Nous Research: Home Assistant, Spotify, Claude Subscription DirectSDK and more, one install away from the Hermes plugin catalog.

Python314étoiles au total DomotiqueLLM
+310 étoiles cette semaine
Rang 40

Best headless browser for AI agents. Lite, Fast, High-Compatibility. Built in Rust

Rust19,2 kétoiles au total Santé : En bonne santéTests & QARust
+3,7 k étoiles cette semaine
Rang 41

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.

JavaScript3,4 kétoiles au total Vision par ordinateurJavaScript
+1,3 k étoiles cette semaine
Rang 42

Token 超支?快给史密斯打电话! Better Call Smith. Adaptive model routing, a glassy Codex usage monitor, and reproducible benchmarks with receipts.

Python318étoiles au total Local-firstiOS
+278 étoiles cette semaine
Rang 44

Find the cheapest API for any model and connect it from your AI agent: Grandet Skill and an anonymous MCP server, backed by listed prices from 1,800+ official, inference and relay providers on grandet.ai.

JavaScript276étoiles au total MCPSkills d’agents
+270 étoiles cette semaine
Rang 45

A local multi-agent harness that works with your existing Claude Code, Codex subscriptions, allows you to run an office of agents

TypeScript582étoiles au total Claude CodeTypeScript
+376 étoiles cette semaine
Rang 46

Claude Code skill for short films with no video model: 51 film styles, each a style prompt plus a demo film made entirely in code by Claude Opus 5.5 (incl. OPUSCAR 98 and the new Evidence Films). By Lemomo. · Opus5.5 x 51 种影片风格:风格提示词 + 纯代码样片 + 导演与技术指南(新增「实证影像」)

JavaScript2,9 kétoiles au total Skills d’agentsJavaScript
+1,1 k étoiles cette semaine
Rang 47

An auto-evolution framework that optimizes anything — your 7×24 team of algorithm engineers.

Python1,2 kétoiles au total Python
+621 étoiles cette semaine
Rang 48

Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation

Python244étoiles au total Vision par ordinateurPython
+244 étoiles cette semaine
Rang 49

All your machines, one app. For you and your AI agents: agent sessions, desktops, files, logs and GitHub across your Macs, Linux and Windows machines, with an MCP server.

Rust239étoiles au total RéseauMCP
+239 étoiles cette semaine
Rang 50

Build AI agents that run 100% on-device. Sub-100ms latency on Qualcomm NPU. Zero cloud dependency.

C++1,1 kétoiles au total Santé : Signaux mitigésEmbarquéC & C++
+549 étoiles cette semaine
Rang 51

Claude Code, Codex, Copilot, Pi, OpenCode, Gemini, and Prime Agent versions of Poteto's pstack. Rigorous agent workflows with Cursor primitives translated for other harnesses.

JavaScript2,7 kétoiles au total Santé : En bonne santéSkills d’agentsJavaScript
+973 étoiles cette semaine
Rang 52

Claude Code plugin to see, review and iterate on your agent's work without leaving the terminal: show images, play videos, and run visual QA with Playwright recordings and before/after comparisons inside the Claude Code terminal. Works in any terminal that supports the kitty graphics protocol, fully cross-platform on macOS, Linux and Windows.

TypeScript229étoiles au total TerminalTests & QA
+228 étoiles cette semaine
Rang 53

nanoMuse: an open-source personal agent for every device you own. One agent with a name and a look of its own that does things, keeps working while the app is closed, remembers you, and asks before anything you cannot undo. On Android, iPhone and iPad, Windows / macOS / Linux and in the browser; your phone's screen and your computer as its hands.

Swift1,4 kétoiles au total SwiftiOS
+621 étoiles cette semaine
Rang 54

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.

JavaScript1 kétoiles au total JavaScriptAgents de code
+500 étoiles cette semaine
Rang 55

Local-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-the-loop decisions.

JavaScript1 kétoiles au total Santé : En bonne santéLLM en localLocal-first
+493 étoiles cette semaine
Rang 56

🛡️ Free open-source AI-powered security terminal & vulnerability scanner (CVE, SBOM). Supports SSH, SFTP, RDP, VNC, Serial, and 12+ autonomous AI agents (DeepSeek, OpenAI) for automated security workflows, CTF & DevSecOps. Cross-platform & Web UI.

HTML830étoiles au total TerminalSécurité
+424 étoiles cette semaine
Rang 57

Frametell: turn your ideas and material into vivid explainer videos with an AI director agent. Local-first, any model.

TypeScript208étoiles au total Vision par ordinateurLocal-first
+208 étoiles cette semaine
Rang 59

Orca is the place for working with a fleet of agents (e.g. Grok Bot, Codex). Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.

TypeScript95,2 kétoiles au total Santé : En bonne santéTerminalAgents de code
+6,1 k étoiles cette semaine
Rang 60

Monid - OpenRouter for agent tools. Join our community at https://discord.gg/rQzztcgJV8

TypeScript4,7 kétoiles au total TypeScript
+1,2 k étoiles cette semaine
Rang 62

The job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.

Python50 kétoiles au total Santé : En bonne santéClaude CodePython
+4,3 k étoiles cette semaine
Rang 65

ARTEX 한국어판 · AI 자율 침투 테스트 프레임워크(upstream: Autumn-27/ARTEX, AGPL-3.0)

Go1,6 kétoiles au total SécuritéGo
+615 étoiles cette semaine
Rang 66

A comprehensive logo-design skill for Claude, Gemini CLI, Codex and other AI agents: principles, process, SVG craft, testing tools and a 1,400+ logo reference library.

HTML3,6 kétoiles au total Skills d’agentsAgents de code
+954 étoiles cette semaine
Rang 68

A curated, battle-tested AI-coding toolkit: Claude Code plugins, subagent orchestration, quality gates, and ready-to-copy prompts, extracted from real production use.

JavaScript1,3 kétoiles au total Santé : Signaux mitigésJavaScriptAgents de code
+510 étoiles cette semaine
Rang 69

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.

Python52,1 kétoiles au total Santé : En bonne santéBases de donnéesSkills d’agents
+3,9 k étoiles cette semaine
Rang 70

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.

HTML235étoiles au total Éditeurs & IDEObservabilité
+167 étoiles cette semaine
Rang 71

Autonomous GitHub Project build → QA → review loop for Claude Code. One-line install.

HTML357étoiles au total Santé : Signaux mitigésTests & QAAgents de code
+205 étoiles cette semaine
Rang 72

Harness self-evolution: update targets, theory, evaluation, and reported evidence. Bilingual reading list and project website.

TeX168étoiles au total Skills d’agentsAgents de code
+166 étoiles cette semaine
Rang 73

Android automation from code. Test your apps on real phones, script the tasks you repeat, run a shelf of phones, or let an AI agent use one, from Python, Node.js, the CLI, HTTP or Appium clients. No ADB, no USB cable, no root.

Go179étoiles au total Tests & QAGo
+165 étoiles cette semaine
Rang 77

Answer me with HTML — an agent skill that answers hard questions with a one-page HTML you can actually read. 让 AI Agent 用一页 HTML 回答复杂问题。

JavaScript3,6 kétoiles au total Outils CLISkills d’agents
+840 étoiles cette semaine
Rang 78

A virtual camera films an AI agent's screen while a tracker locks onto every glyph. Two fframes passes, one SkSL shader, all sound synthesized.

Rust455étoiles au total Rust
+234 étoiles cette semaine
Rang 79

DSH x Blender direct realtime plugin v2.0 — an AI drives Blender over a direct TCP channel (no MCP): 16 tools, 28 families / 186 ops (viewport frames, click-to-pick, render profiling, headless offload) + a right-sidebar panel (live only) with click-to-context & @-mentions. Addon: DSH Blender Bridge. skill: sixtysevenlf/dsh-skill-blender-modeling

Python430étoiles au total Agents de codePython
+223 étoiles cette semaine
Rang 81

Clone any viral video with AI agents. Not just a script, the whole workflow: swap the face, the words, the B-roll, ship 100 variants in one command, and get your 100M views.

TypeScript23 kétoiles au total Santé : En bonne santéVision par ordinateurTypeScript
+2,2 k étoiles cette semaine
Rang 83

JiuwenSwarm is an intelligent AI Agent built on openJiuwen. It extends the powerful capabilities of large language models directly to your fingertips through various communication apps you use daily.

Python7,1 kétoiles au total Santé : En bonne santéLLMPython
+1,2 k étoiles cette semaine
Rang 84

ARTEX 한국어판 ·AI 기반 침해사고 대응 기능 추가 (upstream: Autumn-27/ARTEX, AGPL-3.0)

Go193étoiles au total SécuritéGo
+150 étoiles cette semaine
Rang 85

AI turns documents or topics into real, native PowerPoint decks—with native shapes, transitions and animations, data-backed charts and tables on demand, audio narration from speaker notes, and support for your own .pptx templates. · by Hugo He

Python63,1 kétoiles au total Santé : En bonne santéPython
+3,6 k étoiles cette semaine
Rang 86

中国 A 股数据基础设施。55个日更数据集:股票行情、基本面、期货数据、资金面、公告事件、指数行业、宏观与风险。行级溯源、PIT 语义、复权与历史成分内置,MCP 原生。自托管,零注册、零 API Token

Python628étoiles au total Santé : En bonne santéBases de donnéesMCP
+277 étoiles cette semaine
Rang 87

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

JavaScript166 kétoiles au total Santé : En bonne santéSkills d’agentsJavaScript
+5,8 k étoiles cette semaine
Rang 88

full guide to help you integrate AI in your workflow, for both beginners and experienced users

388étoiles au total Agents de code
+199 étoiles cette semaine
Rang 89

BINNY: an open source agent harness for reverse engineering. Plug in any model, or a local one.

Go141étoiles au total LLM en localSécurité
+141 étoiles cette semaine
Rang 90

Claude Code skill for Dribbble-level product launch videos from code. One shape that never cuts, springs, a cursor that drives every change, beat-synced SFX, 60 fps motion blur. v2: use with Claude Opus 5.5.

JavaScript301étoiles au total Santé : Signaux mitigésTests & QAVision par ordinateur
+164 étoiles cette semaine