Open source inference engine that tunes its kernels to your hardware to run open models faster on Apple Silicon, NVIDIA, AMD, or CPU.
nicedreamzapp/claude-code-local
Runs Claude Code against open AI models on your Apple Silicon Mac via an MLX-based Anthropic API server, with no cloud model or API key.
Open source альтернатива:Claude Code
- Звёзды
- 3,369
- Форки
- 0
- Открытые issues
- 0
- Последний коммит
- 4 дня назад
Ключевые возможности
- 01Serves the Anthropic Messages API with streaming on top of MLX models on Apple Silicon.
- 02Converts model-specific tool-call formats into Claude Code tool calls and repairs malformed tool JSON.
- 03Reuses the prompt cache between turns to speed up long sessions.
- 04Setup script picks a model based on the Mac's available memory.
- 05Launchers switch off Claude Code's background network traffic.
Сценарии использования
- Continuing coding work on a Mac when Claude usage limits have been reached.
- Using Claude Code offline or on an air-gapped machine.
- Working on confidential code or documents that must stay on the local machine.
Темы
Частые вопросы
- Что такое claude-code-local?
- Runs Claude Code against open AI models on your Apple Silicon Mac via an MLX-based Anthropic API server, with no cloud model or API key.
- claude-code-local можно использовать бесплатно? Какая у него лицензия?
- claude-code-local распространяется с открытым исходным кодом под лицензией MIT. Перед использованием в коммерческих продуктах проверьте условия лицензии.
- claude-code-local всё ещё поддерживается?
- Активно поддерживается. Последний коммит в claude-code-local — 15 окт. 2026 г..
- Для чего можно использовать claude-code-local?
- Continuing coding work on a Mac when Claude usage limits have been reached. Using Claude Code offline or on an air-gapped machine. Working on confidential code or documents that must stay on the local machine.
- Где скачать claude-code-local?
- Исходный код и инструкции по установке — на GitHub: https://github.com/nicedreamzapp/claude-code-local
Описание создано ИИ на основе README проекта. Статистика GitHub обновляется ежедневно.
Похожие проекты
Swift and Metal runtime that runs the 26B Gemma 4 26B-A4B model on Apple Silicon Macs with about 2 GB of RAM by streaming experts from SSD.
Uses an iPhone connected over USB-C to speed up prefill and extend context for a 27B Qwen model running locally on a Mac.
A small educational project for running vision-language model inference on Apple Silicon with MLX, scoring candidate answers about one image.
A local-first browser automation engine and Agent Skill that runs Qwen3.5 models on-device to pick browser actions from visible page elements.
A macOS and iOS document chat app that answers questions about your files using Apple Foundation Models, running entirely on-device.