Stars
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
MiniCPM5: SOTA on-device LLMs, small yet powerful.
The easiest way to use Agentic RAG in any enterprise
RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
Open source AI terminal for cloud and infrastructure management, enabling you to deploy, troubleshoot, and automate services using natural language and intelligent agents.
PromptX · 领先的AI 智能体上下文平台 | PromptX · Leading AI Agent Context Platform
FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…
Rules and Knowledge to work better with agents such as Claude Code or Cursor
Experimental toolkit for auto-generating codebase documentation using LLMs
Pocket Flow: Codebase to Tutorial
Pocket Flow: 100-line LLM framework. Let Agents build Agents!
Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Train a Language Model with GRPO to create a schedule from a list of events and priorities
An Open-Source Framework for Prompt-Learning.
Context7 Platform -- Up-to-date docs for AI agents
Code AI platform with Code Search & Cody
A framework helps you quickly build AI Native IDE products. MCP Client, supports Model Context Protocol (MCP) tools via MCP server.
🙌 OpenHands: AI-Driven Development
High Accuracy and efficiency multi-task fine-tuning framework for Code LLMs. This work has been accepted by KDD 2024.
An intelligent assistant serving the entire software development lifecycle, powered by a Multi-Agent Framework, working with DevOps Toolkits, Code&Doc Repo RAG, etc.
Model Context Protocol Reference Servers
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
No fortress, purely open ground. OpenManus is Coming.
A high-throughput and memory-efficient inference and serving engine for LLMs
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations