kimi

A coding agent for low-cost models

✨ AI Coding, Vim Style

Run Kimi K3, a 2.8T-parameter Mixture-of-Experts LLM, on a single Apple Silicon Mac. Streams MXFP4 experts on demand over HTTP into a local disk cache — fused NEON kernels, Metal/MPS compute, exact reproducible decoding, and an OpenAI-compatible API server for local chat and coding agents.

Argus is a local, open-source visual UI testing app.