GitHub Open Source Insight
Computed at Sep 11, 2026GitHub repo leaderboard by stars, growth rate and activity.
jamiepine
The open-source AI voice studio. Clone, dictate, create.
TypeScript52,947 starslast pushed 5 weeks agoAlexsJones
Hundreds of models & providers. One command to find what runs on your hardware.
Rust35,806 starslast pushed 16 hours agojundot
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
Python21,611 starslast pushed 2 hours agoosaurus-ai
Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.
Swift7,831 starslast pushed 2 hours agoraullenchai
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
Python3,725 starslast pushed 5 hours agochadhurley25075-png
Heterogeneous prefill/decode for DeepSeek-V4-Flash: CUDA prefill (DGX Spark, vLLM) -> Metal decode (Mac Studio, oMLX) over plain 10GbE
Python108 starslast pushed 2 days agoiamwavecut
NVIDIA DLSS 5 neural rendering and DLSS frame generation on Apple Silicon (MLX/Metal, Core ML) and PyTorch; weights extracted from your own DLSS libraries
Swift61 starslast pushed 7 hours ago
| # | Repo | Language | Stars | 30-day trend | Last updated |
|---|---|---|---|---|---|
| 1 | jamiepine The open-source AI voice studio. Clone, dictate, create. | TypeScript | 52,947 | last pushed 5 weeks ago | |
| 2 | AlexsJones Hundreds of models & providers. One command to find what runs on your hardware. | Rust | 35,806 | last pushed 16 hours ago | |
| 3 | jundot LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar | Python | 21,611 | last pushed 2 hours ago | |
| 4 | osaurus-ai Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source. | Swift | 7,831 | last pushed 2 hours ago | |
| 5 | raullenchai The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider. | Python | 3,725 | last pushed 5 hours ago | |
| 6 | chadhurley25075-png Heterogeneous prefill/decode for DeepSeek-V4-Flash: CUDA prefill (DGX Spark, vLLM) -> Metal decode (Mac Studio, oMLX) over plain 10GbE | Python | 108 | last pushed 2 days ago | |
| 7 | iamwavecut NVIDIA DLSS 5 neural rendering and DLSS frame generation on Apple Silicon (MLX/Metal, Core ML) and PyTorch; weights extracted from your own DLSS libraries | Swift | 61 | last pushed 7 hours ago |
All · 11,658