Skip to content
Fossfits
Index

Apache 2.0.

Common for infra and model tooling. Attribution and NOTICE file still matter.

Apache-2.040 listedCatalog Sep 1, 2026

  1. Rank 1. OpenAI Codex CLIOpen-source terminal coding agent from OpenAI that plans, edits, and tests repos in a sandbox.GitHub stars: 123k
  2. Rank 2. Gemini CLIGoogle’s Apache-2.0 terminal coding agent with MCP tools and a large free tier.GitHub stars: 107k
  3. Rank 3. PrivateGPTApache-2.0 local RAG API layer for chatting with private documents offline.GitHub stars: 58k
  4. Rank 4. DeepSpeedMicrosoft’s Apache-2.0 ZeRO optimizer for multi-GPU, multi-node LLM training.GitHub stars: 43k
  5. Rank 5. SGLangFast model serving with KV-cache reuse for agent and reasoning workloads.GitHub stars: 36k
  6. Rank 6. KestraApache-2.0 event-driven orchestration with YAML flows and a clean UI.GitHub stars: 28k
  7. Rank 7. PEFTHugging Face’s LoRA/QLoRA library that makes big-model tuning fit one GPU.GitHub stars: 22k
  8. Rank 8. TRLHugging Face’s Apache-2.0 trainers for SFT, DPO, PPO, and reward modeling.GitHub stars: 19k
  9. Rank 9. Trigger.devApache-2.0 durable workflow engine for AI agents and background jobs in TypeScript.GitHub stars: 16k
  10. Rank 10. txtaiAll-in-one Python framework for embeddings, vector search, and RAG workflows.GitHub stars: 13k
  11. Rank 11. LanceDBEmbedded serverless vector database — SQLite-style, multimodal, no server to run.GitHub stars: 11k
  12. Rank 12. XinferenceServe LLMs, embeddings, and media models from one Apache-2.0 platform.GitHub stars: 9.6k
  13. Rank 13. Node-REDThe veteran flow-based automation editor — drag nodes, wire events, deploy.GitHub stars: 24k
  14. Rank 14. vLLMHigh-throughput model server for GPU inference.GitHub stars: 58k
  15. Rank 15. MilvusCloud-native vector database built for large-scale ANN search.GitHub stars: 38k
  16. Rank 16. QdrantRust vector database with filters, payloads, and a REST API.GitHub stars: 26k
  17. Rank 17. RAGFlowOpen-source RAG engine with deep document understanding.GitHub stars: 65k
  18. Rank 18. ClineVS Code agent that can use the editor, the terminal, and the browser.GitHub stars: 53k
  19. Rank 19. UnslothFaster LoRA fine-tuning with lower VRAM on consumer GPUs.GitHub stars: 45k
  20. Rank 20. ContinueOpen-source autocomplete and chat inside VS Code and JetBrains.GitHub stars: 29k
  21. Rank 21. LLaMA-FactoryWeb UI and YAML recipes for fine-tuning many open LLMs.GitHub stars: 58k
  22. Rank 22. AiderTerminal pair programmer that edits a git repo and commits the result.GitHub stars: 37k
  23. Rank 23. ChromaDeveloper-friendly embedding database for local RAG prototypes.GitHub stars: 23k
  24. Rank 24. AxolotlYAML-driven fine-tuning toolkit for serious training runs.GitHub stars: 11k
  25. Rank 25. GooseBlock’s local-first agent runtime with a desktop and CLI.GitHub stars: 24k
  26. Rank 26. MarqoDocker-deployed search engine combining vector and keyword search for discovery apps.GitHub stars: 5k
  27. Rank 27. FlowiseLow-code node UI on top of LangChain-style flows.GitHub stars: 44k
  28. Rank 28. Wan2.1Alibaba’s open text-to-video and image-to-video stack.GitHub stars: 14k
  29. Rank 29. InvokeAIPolished local creative tool around diffusion, with a studio UI.GitHub stars: 26k
  30. Rank 30. LTX-VideoLightricks open video model aimed at faster local clips.GitHub stars: 8k
  31. Rank 31. exoLink everyday devices into one cluster and run models too big for any single machine.GitHub stars: 47k
  32. Rank 32. TabbySelf-hosted coding assistant with a local inference server.GitHub stars: 32k
  33. Rank 33. FramePackLong local image-to-video with a low VRAM floor.GitHub stars: 18k
  34. Rank 34. MLC-LLMCompile-and-serve LLMs on Metal, Vulkan, WebGPU, and phones — no CUDA required.GitHub stars: 23k
  35. Rank 35. CogVideoXTHUDM open video diffusion with strong prompt following.GitHub stars: 13k
  36. Rank 36. llamafileSingle-file LLM runtime from Mozilla. Download, chmod, run.GitHub stars: 23k
  37. Rank 37. kotaemonApache-2.0 document chat with visible citations and RAG evaluation built in.GitHub stars: 26k
  38. Rank 38. Open-SoraApache-2.0 research stack for training and running video diffusion on 24 GB cards.GitHub stars: 30k
  39. Rank 39. MochiGenmo’s Apache-2.0 10B video model — permissive weights, heavy hardware.GitHub stars: 3.7k
  40. Rank 40. CSMSesame’s 1B conversational speech model behind the viral Maya voice demo.GitHub stars: 15k