Agent infrastructure
claude-code-local
nicedreamzapp/claude-code-local
A local inference setup that lets Claude Code run on Apple Silicon or a PC using MLX or llama.cpp. It serves an Anthropic-compatible API, picks a model for your hardware, and keeps code offline.
Topics
Related projects
mlx-serve2.4kNative LLM inference server for Apple Silicon with OpenAI- and Anthropic-compatible APIs, plus a macOS app offering chat, agent mode, multimodal interaction, and tool calling.
coucou7kA notch and menu-bar companion for AI coding agents that shows live Claude Code, Codex, and other sessions, and lets you approve permissions, answer questions, and chat from your Mac or phone.
ThinkWatch-Lite1kThinkWatch Lite is a local gateway for Claude Code, Codex, and other AI clients that switches upstreams, redacts secrets, blocks dangerous tool calls, and traces usage.
mlx-dspark736A native MLX speculative-decoding inference engine that speeds up local LLMs on Apple Silicon.
claude-status-bar731A tiny macOS menu bar app that shows Claude Code's live status—thinking, running tools, awaiting permission, and elapsed time—aggregating multiple sessions at a glance.
headroom-desktop635A desktop tray app that routes coding agents through a local proxy pipeline to compress prompts and cut token costs.