GitHub repo leaderboard by stars, growth rate and activity.
MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.
Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.
Stride (formerly Xenko), a free and open-source cross-platform C# game engine.
Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk
The high-speed OpenGL, OpenCL, OpenAL, OpenXR, GLFW, SDL, Vulkan, Assimp, WebGPU, and DirectX bindings library your mother warned you about.
Turn an old Android phone into a GPU-accelerated Linux desktop (XFCE4 / KDE Plasma / LXQt / MATE) or a Home Assistant smart home server — using Termux. No root, no PC, no cloud.
An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency.
Low-Latency Accelerated Web Remote Desktop Streaming Platform for Self-Hosting, Containers, Kubernetes, or Cloud/HPC
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | A cross-platform, safe, pure-Rust graphics API. | Rust | 17,967 | last pushed Yesterday | |
| 2 | MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI. | C++ | 16,053 | last pushed 2 days ago | |
| 3 | Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability. | Rust | 15,889 | last pushed Yesterday | |
| 4 | Stride (formerly Xenko), a free and open-source cross-platform C# game engine. | C# | 7,813 | last pushed 2 days ago | |
| 5 | Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk | C++ | 5,674 | last pushed Yesterday | |
| 6 | The high-speed OpenGL, OpenCL, OpenAL, OpenXR, GLFW, SDL, Vulkan, Assimp, WebGPU, and DirectX bindings library your mother warned you about. | C# | 5,196 | last pushed 3 days ago | |
| 7 | Turn an old Android phone into a GPU-accelerated Linux desktop (XFCE4 / KDE Plasma / LXQt / MATE) or a Home Assistant smart home server — using Termux. No root, no PC, no cloud. | Shell | 3,355 | last pushed 2 weeks ago | |
| 8 | An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python dependency. | C++ | 2,404 | last pushed 24 hours ago | |
| 9 | Vulkan Quake port based on QuakeSpasm | C | 2,272 | last pushed 2 days ago | |
| 10 | Low-Latency Accelerated Web Remote Desktop Streaming Platform for Self-Hosting, Containers, Kubernetes, or Cloud/HPC | Python | 2,128 | — | last pushed 24 hours ago |
All · 11,474