GitHub Open Source Insight
Computed at Sep 10, 2026GitHub repo leaderboard by stars, growth rate and activity.
janhq
Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.
TypeScript44,391 starslast pushed 21 hours agokhoj-ai
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.
Python37,233 starslast pushed 1 month agollmware-ai
Unified framework for building enterprise RAG pipelines with small, specialized models
Python14,848 starslast pushed 4 months agogetumbrel
A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support!
TypeScript10,938 starslast pushed 2 years agoRunanywhereAI
Production ready toolkit to run AI locally
C++10,284 starslast pushed 2 days agoxorbitsai
Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.
Python9,562 starslast pushed 2 days agoreorproject
Private & local AI personal knowledge management app for high entropy people.
JavaScript8,560 starslast pushed 1 year agocactus-compute
Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots.
C++5,994 starslast pushed 2 days agomostlygeek
Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc
Go5,629 starslast pushed 22 hours agogptme
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!
Python4,411 starslast pushed Yesterday
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | janhq Jan is an open source alternative to ChatGPT that runs 100% offline on your computer. | TypeScript | 44,391 | last pushed 21 hours ago | |
| 2 | khoj-ai Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free. | Python | 37,233 | last pushed 1 month ago | |
| 3 | llmware-ai Unified framework for building enterprise RAG pipelines with small, specialized models | Python | 14,848 | last pushed 4 months ago | |
| 4 | getumbrel A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support! | TypeScript | 10,938 | last pushed 2 years ago | |
| 5 | RunanywhereAI Production ready toolkit to run AI locally | C++ | 10,284 | last pushed 2 days ago | |
| 6 | xorbitsai Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API. | Python | 9,562 | last pushed 2 days ago | |
| 7 | reorproject Private & local AI personal knowledge management app for high entropy people. | JavaScript | 8,560 | last pushed 1 year ago | |
| 8 | cactus-compute Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots. | C++ | 5,994 | last pushed 2 days ago | |
| 9 | mostlygeek Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc | Go | 5,629 | last pushed 22 hours ago | |
| 10 | gptme 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! | Python | 4,411 | last pushed Yesterday |
All · 11,474