Claude Code Local: hit your limit? Keep going.

Claude Code, running on your own computer when your Claude usage runs out. Same tools, same project, no API key.

curl -fsSL https://raw.githubusercontent.com/nicedreamzapp/claude-code-local/main/install.sh | bash

Mac and Linux. Windows is one PowerShell line. On a Mac, Linux or Windows, type exit in Claude Code, then keep going, and the same conversation carries on.

How-to guides and docs: nicedreamzapp.github.io/claude-code-local

⭐ 3,708 GitHub stars (github.com/nicedreamzapp) · ⬇️ 46,543 all-time downloads (huggingface.co/divinetribe) Models on Hugging Face: 18 MLX builds at huggingface.co/divinetribe (⬇️ 42,774 all-time downloads) · this repo ⭐ 3,499 stars

🆕 Qwen 4 watch: Alibaba says Qwen 4 is coming. The day the weights land we test it inside Claude Code and add it here, with real speed and scores. ⭐ Star or watch the repo to catch it. The plan

Agent-12 score for the model setup picks on a 96 GB Mac, Qwen 3.8 27B: 12/12 easy, 7/8 hard. Scored in Agent-12's own harness, not inside Claude Code. How the models compare

🧠⚡ Claude Code Local

Claude Code, running on your own Mac. No cloud. No API key. No waiting.

Your Mac's chip runs the AI · Claude Code works exactly like it always does · nothing leaves your computer

Now on Linux and Windows too, same Claude Code, same privacy, your own machine doing the work. Phones are next.

In one sentence: a small Python server (proxy/server.py) runs open AI models on your Mac's chip with Apple's MLX and answers Claude Code in Anthropic's own API format, so Claude Code works with no cloud model and no API key.

Ran out of Claude usage or hit a rate limit mid-task? Start here, it takes one command to keep working on a local model.

Other things I built that go with it are in the local-first family.

Matt Macosko wrote the glue that makes local models usable inside Claude Code. The pieces in this repo:

• ⚡ proxy/server.py: the MLX server. Speaks the Anthropic Messages API with streaming, turns each model's own tool-call format (Gemma 4, Qwen, Llama JSON) into Claude Code tool calls, repairs garbled tool JSON, and reuses the prompt cache between turns so long sessions don't re-read everything.
• 🧪 scripts/test_parse_tool_calls.py and scripts/test_mlx_server.py: tests for the tool-call parser (no model needed) and for multi-step tool calls against a running server.
• 🏎️ agent/agent.py: the Native Engine, a one-file terminal coding agent with a short fixed system prompt so the cache survives every turn. bench/agent_bench.py reproduces its cache numbers.
• 🔋 bin/keepgoing + bin/keepgoing.py: finds your last Claude Code conversation in this folder and resumes it on a free cloud or local model. On Linux and Windows (bin/keepgoing.cmd) it resumes on the llama.cpp model through portable/ccl.py keepgoing.
• 🚀 install.sh, setup.sh and scripts/doctor.sh: check the Mac, pick a model that fits its memory, install everything and make a Desktop launcher.
• 🩺 Doctor: checks the core (Claude Code, model server, model files, Python, llama.cpp) and every add-on you installed. Mac or Linux: . Windows: . Add / to restart your own service that is down or recreate a missing symlink (it never deletes anything), and / for a privacy-safe block to paste into a bug report.

Upstream, not mine: Claude Code (Anthropic), MLX and mlx-lm (Apple), and the models themselves (Google, Qwen, Nous Research and the others credited below). Contributors who fixed things are named at the bottom.

🛑 Hit your Claude Code usage limit?

Claude Code just said "5-hour limit reached", "You've reached your weekly limit", or your API key came back with "credit balance is too low", and the reset is hours away? You ran out of Claude usage, not out of work. Keep going on your own machine: same Claude Code, same project, but the AI answering runs on your Mac (or your Linux or Windows PC), with no API key and no usage limit.

1. Install it once (Mac or Linux; Windows is below):

   curl -fsSL https://raw.githubusercontent.com/nicedreamzapp/claude-code-local/main/install.sh | bash
   

2. Switch to local. Type exit in Claude Code, then keep going (Mac, Linux or Windows), and the same conversation carries on with a local model. Or double-click Claude Local on your Desktop for a fresh session (claude-local on Linux).

3. Switch back when your limit resets. Plain claude is never changed by the install, so it still uses your Claude plan.

This is the beginning of the README. Read the rest at the original. Read the full README ↗