GitHub · Python
cryptopoly/ChaosEngineAI
Local AI workstation: chat by voice or text, transcribe, generate images and video (with sound on Apple Silicon), benchmark and serve open-weight models. MLX, llama.cpp, vLLM and MTPLX backends, DFlash/DDTree speculative decoding, TurboQuant and TriAttention cache compression.
- Stars
- 26
- Forks
- 5
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: ai, llama-cpp, llm, local-ai, mlx, stable-diffusion, tauri, apple-silicon, cache-compression, dflash
Latest data point: Nov 21, 2026 · 26 stars · 5 forks