Open source Artificial Intelligence
Open-source AI models, agents, runtimes, gateways, and retrieval tooling.
- openclaw/openclaw β Open-source AI assistant that lives on your own hardware and in your chat apps
- n8n-io/n8n β Fair-code workflow automation with a visual canvas, custom code and 1500+ integrations
- langgenius/dify β Visual platform for building LLM apps with RAG pipelines, agents and model integrations
- open-webui/open-webui β Self-hosted web UI for chatting with Ollama and OpenAI-compatible models offline
- langchain-ai/langchain β Python framework for building agents and LLM applications from composable components
- paperclipai/paperclip β Manage a team of AI agents with goals, budgets and task tracking
- debpalash/VoiceStudio β Local voice studio for cloning, dubbing, dictation and narration in 646 languages
- google-gemini/gemini-cli β Terminal AI agent for Gemini Code Assist enterprise licenses
- vllm-project/vllm β High-throughput inference and serving engine for LLMs with an OpenAI-compatible API
- infiniflow/ragflow β RAG engine that turns PDFs and office documents into a citable context layer for LLMs
- OpenHands/OpenHands β Self-hosted control center for coding agents and scheduled automations
- modelcontextprotocol/servers β Reference MCP servers for files, Git, fetch, memory, time, and thinking
- cheaper-inference/OmniRoute β Self-hosted AI gateway that routes one endpoint across 375 providers
- diegosouzapw/OmniRoute β Never stop coding.
- heygen-com/hyperframes β Render HTML, CSS and seekable animations into deterministic MP4 video
- BerriAI/litellm β Self-hosted AI gateway and Python SDK for 100+ LLM providers
- vectorize-io/hindsight β Agent memory system built so agents learn from experience, not just recall
- crewAIInc/crewAI β Python framework for role-based multi-agent crews and event-driven flows
- pingdotgg/t3code β One interface for coding agents, with desktop, web and phone clients
- CherryHQ/cherry-studio β Desktop AI workspace for models, agents, knowledge bases and images
- HKUDS/nanobot β Lightweight self-hosted personal AI agent in Python, in chat or browser
- JustVugg/colibri β Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine β pure C, zero deps, experts streamed from disk.
- AlexsJones/llmfit β Terminal tool that matches open LLMs to your CPU, RAM and GPU before you download them
- github/github-mcp-server β GitHub's official MCP server for repositories, issues, PRs, and Actions