RAG et systèmes de connaissances
siyuan
siyuan-note/siyuan
A knowledge workspace emphasizing local data, privacy and human–AI collaboration.
★ 46,2K⑂ 3KTypeScript
ToolAI.io · Chaîne GitHub
Projets d’IA populaires sur GitHub
Suivez les dépôts AI open source actifs dans les domaines des LLM, des agents, de MCP, de RAG et du code, avec leur nombre d’étoiles et des informations vérifiées sur les projets.
Données du dépôt public
Index du projet
RAG et systèmes de connaissances
FastGPT
labring/FastGPT
A visual knowledge-workflow platform with document ingestion, hybrid retrieval, reranking, and application publishing.
★ 29,6K⑂ 7,3KTypeScript
AI Applications & Automation
open-webui
open-webui/open-webui
A self-hosted AI chat interface supporting Ollama and OpenAI-compatible APIs.
★ 151K⑂ 22,1KPython
Inférence, déploiement et exécution
LocalAI
mudler/LocalAI
A local inference engine for self-hosting models and AI services.
★ 48,9K⑂ 4,4KGo
MCP et appels d’outils
context7
upstash/context7
A documentation service supplying library references and examples to LLMs and AI editors.
★ 61,6K⑂ 3KTypeScript
Programmation AI et outils pour développeurs
ECC
affaan-m/ECC
A collection of skills, memory patterns and development workflows for AI coding assistants.
★ 248,8K⑂ 37,5KJavaScript
Agents et multi-agents
nanobot
HKUDS/nanobot
A lightweight self-hosted personal AI agent with tools, memory and messaging integrations.
★ 47,7K⑂ 8,4KPython
Agents et multi-agents
CowAgent
zhayujie/CowAgent
An extensible AI assistant framework supporting models, tools, memory and messaging channels.
★ 46,8K⑂ 10,3KPython
AI Applications & Automation
TrendRadar
sansan0/TrendRadar
A news and trend monitor combining multi-source aggregation, AI analysis and notifications.
★ 62K⑂ 24,9KPython
Agents et multi-agents
Agent-Reach
Panniantong/Agent-Reach
A toolkit giving AI agents access to reading and search workflows across websites.
★ 78,1K⑂ 6,7KPython
MCP et appels d’outils
litellm
berriai/litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
★ 56,8K⑂ 10,8KPython
MCP et appels d’outils
Rapid-MLX
raullenchai/rapid-mlx
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
★ 3,5K⑂ 401Python
Page 1 / 4 · 45 projets