Open-source observability for AI agents. Find where your agents fail, dispatch your coding agent to fix it, and verify the fix against real traces.
Projets IA open source
Une sélection de projets IA open source de GitHub à suivre : LLM, agents, RAG, déploiement local, image et voix… 1056 projets pour l’instant.
Vous cherchez des projets déployables gratuitement sur Cloudflare, Vercel, Netlify, etc. ? Voir Déploiement gratuit : sélection
Tout 1056🧠 Grands modèles de langage 26🤖 Agents IA 166🧩 Plateformes de développement d’applications 23📚 RAG et bases de connaissances 46💬 Interfaces de chat et clients 42🖥️ Inférence et déploiement en local 87👨💻 Programmation assistée par IA 99🛠️ Frameworks et SDK 48🔌 MCP et écosystème d’outils 35🎨 Génération d’images 25🎬 Génération de vidéo 17🎙️ Voix et audio 43👁️ Vision par ordinateur 28📄 Analyse de documents et scraping 25🗄️ Bases de données vectorielles 25🏋️ Entraînement, fine-tuning et MLOps 76🧪 Évaluation, observabilité et sécurité 82🚪 Passerelles et proxys d’API 12🔎 Recherche et deep research 15⚙️ Bibliothèques de deep learning 57🏷️ Données et annotation 32🔬 IA pour l’industrie et la science 35⚡ Outils de productivité 12
Webots Robot Simulator
Fast inference engine for Transformer models
模块化的图像生成 Web 界面，强调易用与性能。
Structured multi-perspective deliberation for hard decisions. Run full councils, focused triads, or duo debates across Claude Code, Codex, Gemini CLI, and OpenCode.
MCP 与 A2A 网关与注册中心，统一管理多个服务器。
Notion 官方 MCP 服务器，让 AI 读写你的工作区。
The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems.
TNN: developed by Tencent Youtu Lab and Guangying Lab, a uniform deep learning inference framework for mobile、desktop and server. TNN is distinguished by several outstanding features, including its cross-platform capabil
Prompt Engineering | Prompt Versioning | Use GPT or other prompt based models to get structured output. Join our discord for Prompt-Engineering, LLMs and other latest research
A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.
Reliable Multi-Agent Orchestration Framework
Agent framework for the JVM. Pronounced Em-BAY-bel /ɛmˈbeɪbəl/
The Ruby AI framework.
大型多模态模型的评测套件。
Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web. Make your own persistent autonomous agent on top!
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
Set of tools to assess and improve LLM security.
ADHD — a skill for coding agents. Tree-of-thought with pruning, built on the Claude & Codex Agent SDK. Fans out parallel divergent thoughts under different cognitive frames, scores, prunes traps, deepens the survivors. T
Pre-trained Deep Learning models and demos (high quality and extremely fast)
An open source extension that connects AI agents to computational notebooks in JupyterLab.
Cloudflare 官方 MCP 服务器，用自然语言管理 Workers、KV、R2 等资源。
小巧快速的向量搜索引擎。
LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.