#89 · Primary category： Inference & Local Deploy
claude-code-local
Run Claude Code fully on-device with local AI on Apple Silicon via an MLX-native Anthropic-API server, offering private, offline, airgap-ready inference.
Project last updated：08/22/26
GitHub Stars
3.2K
Forks
621
Contributors
10
License
MIT
Why we included this project
Claude Code's usage limits and policies that forbid sending source code to a cloud API are the two reasons most people look for a local alternative. This project runs a small MLX-native server on Apple Silicon that speaks the Anthropic API, so the Claude Code CLI you already use can point at a local model instead of the cloud, with no proxy or API key and no network connection required. The repo ships six models sized for different hardware, from a 14B build that fits a 16 GB MacBook to a DeepSeek variant with a 1M-token context for longer sessions, and voice and browser modes sit alongside the core coding workflow. The airgap-ready design suits teams under NDA, legal, or healthcare constraints, while solo developers get a way to keep coding through rate limits. It's a practical, well-documented bridge between the Claude Code experience and fully on-device inference.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
ollama
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
llama.cpp
LLM inference in C/C++
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
gpt4all
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
LocalAI
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.