[NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention, which reduces inference latency by up to 10x for pre-filling on an A100 while mai
Projets IA open source
Une sélection de projets IA open source de GitHub à suivre : LLM, agents, RAG, déploiement local, image et voix… 1047 projets pour l’instant.
Vous cherchez des projets déployables gratuitement sur Cloudflare, Vercel, Netlify, etc. ? Voir Déploiement gratuit : sélection
Tout 1047🧠 Grands modèles de langage 26🤖 Agents IA 164🧩 Plateformes de développement d’applications 23📚 RAG et bases de connaissances 46💬 Interfaces de chat et clients 41🖥️ Inférence et déploiement en local 87👨💻 Programmation assistée par IA 99🛠️ Frameworks et SDK 47🔌 MCP et écosystème d’outils 34🎨 Génération d’images 25🎬 Génération de vidéo 17🎙️ Voix et audio 44👁️ Vision par ordinateur 28📄 Analyse de documents et scraping 24🗄️ Bases de données vectorielles 25🏋️ Entraînement, fine-tuning et MLOps 75🧪 Évaluation, observabilité et sécurité 81🚪 Passerelles et proxys d’API 12🔎 Recherche et deep research 15⚙️ Bibliothèques de deep learning 56🏷️ Données et annotation 31🔬 IA pour l’industrie et la science 34⚡ Outils de productivité 13
Readymade evaluators for your LLM apps
🥤 RAGLite is a Python toolkit for Retrieval-Augmented Generation (RAG) with DuckDB or PostgreSQL
Enterprise-grade landing zone for AI agent applications on Azure. Deploy the secure infrastructure, the agent app, or both — built on Microsoft Foundry and Microsoft Agent Framework, with Zero-Trust networking, observabi
NVTabular is a feature engineering and preprocessing library for tabular data designed to quickly and easily manipulate terabyte scale datasets used to train deep learning based recommender systems.
a self-hosted webui for 30+ generative ai
An autoML framework & toolkit for machine learning on graphs.
Weave is a toolkit for developing AI-powered applications, built by Weights & Biases.
Open-source autonomous AI penetration testing. 50 specialist agents across web, API, cloud, Active Directory, Kubernetes, CI/CD and AI/LLM (OWASP LLM Top 10). Runs on a local LLM behind a Privacy Gateway. Integrates with
The nnsight package enables interpreting and manipulating the internals of deep learned models.
Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments
A security scanner for your LLM agentic workflows
A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract.
Active learning for systematic reviews
RAFT contains fundamental widely-used algorithms and primitives for machine learning and information retrieval. The algorithms are CUDA-accelerated and form building blocks for more easily writing high performance applic
Kubernetes AI Toolchain Operator