Skip to content
Fossfits
Index

MIT.

Short permissive license. Easy for product teams to accept.

MIT30 listedCatalog Sep 1, 2026

  1. Rank 1. LlamaIndexThe MIT Python framework for building document ingestion and RAG pipelines.GitHub stars: 52k
  2. Rank 2. FaissFacebook’s MIT ANN library for billion-scale embedding search on CPU or GPU.GitHub stars: 41k
  3. Rank 3. MLXApple’s framework for running and training models on Mac unified memory.GitHub stars: 28k
  4. Rank 4. stable-diffusion.cppPure C/C++ inference for SD, Flux, and Qwen-Image weights — CPU included.GitHub stars: 7k
  5. Rank 5. SwarmUIMIT diffusion UI that swarms ComfyUI backends across all your GPUs.GitHub stars: 4.5k
  6. Rank 6. gptmeMIT terminal agent toolkit with code, shell, and web tools — local-model friendly.GitHub stars: 4k
  7. Rank 7. PocketPal AIRun small GGUF chat models fully offline on iOS and Android.GitHub stars: 8k
  8. Rank 8. GraphRAGMicrosoft’s MIT library for graph-based RAG over whole document corpora.GitHub stars: 36k
  9. Rank 9. llama.cppC/C++ runtime that made local GGUF models practical.GitHub stars: 87k
  10. Rank 10. OpenCodeOpen-source coding agent with a terminal UI, built to run against local or hosted models.GitHub stars: 42k
  11. Rank 11. OllamaLocal model runner with a one-line CLI and a REST API.GitHub stars: 152k
  12. Rank 12. LiteLLMProxy that translates many model APIs into one OpenAI-shaped client.GitHub stars: 30k
  13. Rank 13. ActivepiecesOpen-source automation with pieces, AI, and a TypeScript SDK.GitHub stars: 18k
  14. Rank 14. whisper.cppC/C++ port of Whisper for fast local transcription.GitHub stars: 45k
  15. Rank 15. LangfuseTraces, prompts, and evals for LLM apps.GitHub stars: 16k
  16. Rank 16. OpenHandsSoftware agent that uses a sandbox to edit code, run tests, and open PRs.GitHub stars: 62k
  17. Rank 17. AnythingLLMDesktop and server chat with documents, agents, and many backends.GitHub stars: 49k
  18. Rank 18. LocalAIOpenAI-compatible API that can sit in front of several local backends.GitHub stars: 35k
  19. Rank 19. kokoro-onnxKokoro 82M voices as ONNX — real-time TTS on CPU with zero GPU.GitHub stars: 2.7k
  20. Rank 20. Faster-WhisperWhisper reimplementation on CTranslate2 for faster local ASR.GitHub stars: 19k
  21. Rank 21. GPT-SoVITSFew-shot voice cloning and cross-lingual TTS with a full training WebUI.GitHub stars: 62k
  22. Rank 22. GPT4AllNomic’s local chat app and model catalog for laptops without a GPU.GitHub stars: 76k
  23. Rank 23. F5-TTSMIT flow-matching TTS with expressive multilingual voices at consumer-GPU speed.GitHub stars: 15k
  24. Rank 24. HuginnAgent-based self-hosted automation for watches, scrapes, and events.GitHub stars: 47k
  25. Rank 25. shell_gptCLI that runs an LLM as a shell command for scripts, refactors, and answers.GitHub stars: 12k
  26. Rank 26. WhisperOpenAI’s speech-to-text model you can run locally.GitHub stars: 90k
  27. Rank 27. PiperFast local neural text-to-speech that runs on CPU.GitHub stars: 11k
  28. Rank 28. nanoGPTKarpathy’s ~300-line GPT trainer — the cleanest way to learn LLM training.GitHub stars: 63k
  29. Rank 29. PlandexTerminal agent that sandboxes and versions every change for big, long coding tasks.GitHub stars: 16k
  30. Rank 30. ShortGPTMIT framework that automates short-form video from script to rendered clip.GitHub stars: 7.9k