Skip to content
  1. Rank 81. Open-SoraApache-2.0 research stack for training and running video diffusion on 24 GB cards.GitHub stars: 29.8k
  2. Rank 82. OpenShotBeginner-friendly open-source video editor with animated titles.GitHub stars: 6.5k
  3. Rank 83. Node-REDThe veteran flow-based automation editor — drag nodes, wire events, deploy.GitHub stars: 23.6k
  4. Rank 84. text-generation-webuiGradio UI for local models with loaders, LoRA, and extensions.GitHub stars: 47.7k
  5. Rank 85. PocketPal AIRun small GGUF chat models fully offline on iOS and Android.GitHub stars: 8.3k
  6. Rank 86. XinferenceServe LLMs, embeddings, and media models from one Apache-2.0 platform.GitHub stars: 9.6k
  7. Rank 87. llamafileSingle-file LLM runtime from Mozilla. Download, chmod, run.GitHub stars: 26k
  8. Rank 88. PlandexTerminal agent that sandboxes and versions every change for big, long coding tasks.GitHub stars: 15.6k
  9. Rank 89. TensorRT-LLMNVIDIA’s kernel-level serving stack for maximum GPU inference throughput.GitHub stars: 14.6k
  10. Rank 90. CSMSesame’s 1B conversational speech model behind the viral Maya voice demo.GitHub stars: 14.7k
  11. Rank 91. MLC-LLMCompile-and-serve LLMs on Metal, Vulkan, WebGPU, and phones — no CUDA required.GitHub stars: 23.1k
  12. Rank 92. stable-diffusion.cppPure C/C++ inference for SD, Flux, and Qwen-Image weights — CPU included.GitHub stars: 7k
  13. Rank 93. OliveModern open-source NLE aimed at professional timeline work.GitHub stars: 9.1k
  14. Rank 94. Stable Diffusion web UIThe AUTOMATIC1111 Gradio UI that made local SD mainstream.GitHub stars: 164.9k
  15. Rank 95. kokoro-onnxKokoro 82M voices as ONNX — real-time TTS on CPU with zero GPU.GitHub stars: 2.7k
  16. Rank 96. shell_gptCLI that runs an LLM as a shell command for scripts, refactors, and answers.GitHub stars: 12.3k
  17. Rank 97. HuginnAgent-based self-hosted automation for watches, scrapes, and events.GitHub stars: 49.9k
  18. Rank 98. SwarmUIMIT diffusion UI that swarms ComfyUI backends across all your GPUs.GitHub stars: 4.6k
  19. Rank 99. txtaiAll-in-one Python framework for embeddings, vector search, and RAG workflows.GitHub stars: 12.9k
  20. Rank 100. MochiGenmo’s Apache-2.0 10B video model — permissive weights, heavy hardware.GitHub stars: 3.7k

Listed 105Updated Sep 11, 2026GitHub Sep 12, 2026