Your Mac's chip runs the AI · Claude Code works exactly like it always does · nothing leaves your computer
A real session, unedited. Claude Code reads and edits the file, and the AI answering is running on the laptop.
Claude Code just said "you've reached your usage limit" and the reset is hours away? Keep working: same Claude Code, same project, but the AI answering runs on your own Mac.
curl -fsSL https://raw.githubusercontent.com/nicedreamzapp/claude-code-local/main/install.sh | bashThat's it. It even works on a 16 GB MacBook, and gets better the more memory your Mac has.
Trinidad Head is the recommended terminal for running local models, on Mac and PC. It's built from scratch by the same person who made this project, and it makes long local-AI sessions nicer:
- 🪟 Glass windows with a soft neon glow, rounded and easy on the eyes
- 🌈 A different color for every window, so you can tell your local-model windows apart at a glance
- 🔠 Bigger, easy-to-read text
- 💬 Your own prompts stand out in a soft bubble, so you can find what you asked when you scroll back
- 🖱️ Copy and paste just work, even under Claude Code's calm focus view
👉 Get Trinidad Head · project page
When Claude runs out, type exit in Claude Code, then keep going. You get a short menu,
and the same conversation carries on with whichever model you pick:
- ☁️ Free cloud models from OpenRouter (add a free key, see below)
- 💻 Models on your Mac from the lineup below, sized to fit your memory
setup.sh installs it for you. To add it by hand, or to turn on the free cloud models:
echo 'source "$HOME/claude-code-local/scripts/keepgoing-shell.sh"' >> ~/.zshrc # the "keep going" command
mkdir -p ~/.config/claude-code-local
echo 'OPENROUTER_API_KEY=your-free-key' >> ~/.config/claude-code-local/keepgoing.env # optionalWant a reminder at the bottom of every Claude window? Point your status line at
scripts/statusline-keepgoing.sh. It says "💡 Out of Claude credits? Type exit, then keep going to
carry on with a free or local model."
💡 Free cloud models can get busy later in the day. The models on your Mac are always there.
Your Mac has a powerful graphics chip built in. This project uses it to run big AI models right on your computer and plugs them into Claude Code, so the whole coding experience works offline: editing files, managing projects, even driving your browser or talking out loud.
The trick: Claude Code speaks one language (Anthropic's), and local AI servers usually speak another (OpenAI's). Most setups put a slow translator in between. This project's server speaks Claude Code's language directly, so there's nothing in the middle, and that's what makes it fast.
📝 You ──▶ 🤖 Claude Code ──▶ ⚡ this server (on your Mac) ──▶ 🧠 local model ──▶ 🖥️ your Mac's chip
- 🍎 A Mac with Apple Silicon (M1 or newer)
- 🐍 Python 3.12 (setup installs it for you)
- 🤖 Claude Code:
npm install -g @anthropic-ai/claude-code
Setup looks at your Mac's memory and picks a model that fits:
| Your Mac's memory | The model you get |
|---|---|
| 16 GB (MacBook Air, base models) | 🟡 Hermes 4 14B — yes, this works |
| 32–48 GB (Pro) | 🟢 Gemma 4 12B |
| 64–95 GB (Max) | 🟢 Gemma 4 31B |
| 96 GB and up (Max, Ultra) | 🔵 Qwen 3.5 122B, plus room for 🟠 Llama 3.3 70B and more |
One command:
curl -fsSL https://raw.githubusercontent.com/nicedreamzapp/claude-code-local/main/install.sh | bashOr read the script first:
git clone https://github.com/nicedreamzapp/claude-code-local
cd claude-code-local
bash setup.shSetup picks your model, downloads it, installs the server, and puts Claude Local.command on
your Desktop. Double-click it and you're coding locally. 🎉
🐛 Asked to sign in to a Claude account? Your
claudeis too old. Update it:npm install -g @anthropic-ai/claude-code
🛠️ Prefer to do it by hand?
# 1. Set up the MLX environment
python3.12 -m venv ~/.local/mlx-server
~/.local/mlx-server/bin/pip install mlx-lm
# 2. Pick a model and download it (one time)
bash scripts/download-and-import.sh gemma # or 'llama' or 'qwen'
# 3. Start the server
MLX_MODEL=divinetribe/gemma-4-31b-it-abliterated-4bit-mlx \
bash scripts/start-mlx-server.sh
# 4. Launch Claude Code against it
ANTHROPIC_BASE_URL=http://localhost:4000 \
ANTHROPIC_API_KEY=sk-local \
claude --model claude-sonnet-4-6setup.sh installs the server as a symlink back to proxy/server.py in this repo, so if you edit
it, just restart the server.
Same server, same Claude Code. Swap one setting and you swap the brain. Our own ready-to-use builds live at huggingface.co/divinetribe.
| Model | Nickname | Good for | |
|---|---|---|---|
| 🟡 | Hermes 4 14B | The one that runs on your laptop | Everyday edits on a regular MacBook |
| 🟢 | Gemma 4 31B | The quick one | Daily coding |
| ✨ | Muse-Glimmer 30B | The fresh agent | Tool use, and it can see images |
| 🟣 | Qwen 3.8 27B | The full-precision sprinter | Careful coding plus vision |
| 🟠 | Llama 3.3 70B | The wise one | The hardest thinking |
| 🔵 | Qwen 3.5 122B | The beast | Fastest answers on big Macs |
| 🐳 | DeepSeek V4 Flash | The long-memory whale | Huge projects, via ds4 |
Which one should I run? We test them on real agent tasks in the open: the Agent-12 leaderboard. Honest note: those scores come from Agent-12's own lean test harness (Anvil), not from inside Claude Code. Claude Code sends the model a lot more per turn, so the same model can score and time differently here.
Sizes, speeds and memory needs for every model are in the full guide.
⚠️ "Abliterated" models have their built-in refusals turned down. That's not a general upgrade, and each model's own license still applies. Please use them responsibly.
Each one is a double-click launcher in launchers/.
| Mode | What it does | |
|---|---|---|
| 🤖 | Code | Claude Code with a local model: Claude Local, Gemma 4 Code, Llama 70B |
| ⚡ | Native Engine | Our own lightweight agent for the fastest replies: the (Native Engine) launchers |
| 🌐 | Browser | The local AI drives your real browser: Browser Agent (guide) |
| 🎤 | Hands-free voice | Talk to it and hear it answer in your own voice: Narrative Gemma (guide) |
| 📱 | Phone | Text your Mac from your iPhone and get answers back (guide) |
Your code never leaves your Mac. No cloud model, no tracking, no "anonymous analytics".
The launchers switch off Claude Code's own background internet traffic with Anthropic's documented settings (thanks @tadrianonet, PR #32):
CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1
DISABLE_AUTOUPDATER=1
CLAUDE_CODE_DISABLE_OFFICIAL_MARKETPLACE_AUTOINSTALL=1
CLAUDE_CODE_DISABLE_BACKGROUND_TASKS=1Check it yourself: during a session, lsof -p $(pgrep -f claude) shows only localhost:4000.
🧹 We removed LiteLLM after supply-chain concerns and re-checked every dependency. Anything with unexplained network calls didn't ship. The full audit is in the full guide.
☁️ The one exception is your own choice: picking a free cloud model in
keep goingsends that conversation to OpenRouter.
| 📖 Full technical guide | Every model table, benchmark, tuning setting and design note |
| 📊 Benchmarks · 🔧 Tool-call reliability | The numbers and how they were measured |
| 🎤 Voice mode · 🌐 Browser agent · 📱 Phone control · 🔌 MCP servers | Everything the launchers can do |
| 📁 What's in this repo · 🙏 Credits | The tour and the thank-yous |
Each one works on its own. Together they take Claude Code off the keyboard and off the screen.
| Project | What it does | |
|---|---|---|
| 🌊 | Trinidad Head | The terminal to run it all in, on Mac and PC |
| 🎤 | NarrateClaude | Talk to Claude and hear it answer in your cloned voice |
| 🌐 | browser-agent | Drives your real browser |
| 🚦 | browser-broker | Gives each AI agent its own browser tab so nobody fights |
| 📱 | claude-screen-to-phone | Control Claude Code from your iPhone |
| 🛟 | claude-failover | Keep cloud Claude first, flip to local with one command |
Ideas, bug reports, a launcher for a model we don't run: open an issue or a PR, every one gets read. We especially love hearing from people on older or smaller Macs about which models really fit.
Thank you, contributors: @0xshugo · @asdmoment · @kulveersingh · @tripathiprateek · @tadrianonet · @kevbarns · @KaoCSC. What each of them fixed is in the full guide.
Built by Matt Macosko in Arcata, California: one person, no team, no investors. Open to work on local AI and Apple Silicon: matt@ineedhemp.com
Nice Dreamz software · YouTube demos · Discord
📜 MIT License, use it however you want. ⭐ Star the repo if it helped you!