#llama.cpp

React Native binding of llama.cpp

Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level

Run any local LLM engine, auto-tuned to your GPU — polished web UI + OpenAI/Anthropic-compatible API. Point Claude Code at your own machine in one command. No Electron, no Python, offline-first.

ローカルLLM（mlx / mlx-vlm / llama.cpp / router）を OpenAI 互換 API として起動・管理する軽量サーバー

A private reasoner for your terminal. Direct conversation or grounded multi-agent research, GPU-native and fully local. No API keys, no inference servers.