{"data":{"slug":"nicedreamzapp-claude-code-local","name":"claude-code-local","tagline":"Run Claude Code on-device using local AI models for privacy-sensitive workflows.","github_url":"https://github.com/nicedreamzapp/claude-code-local","owner":"nicedreamzapp","repo":"claude-code-local","owner_avatar_url":"https://avatars.githubusercontent.com/u/207429969?v=4","primary_language":"Python","stars":3321,"forks":627,"topics":["abliterated","ai-privacy","airgap","ambient-computing","anthropic","apple-silicon","browser-agent","claude-code","gemma","llama","local-ai","local-llm","macos","mlx","mlx-lm","offline-ai","on-device-ai","private-ai","qwen","voice-ai"],"archived":false,"github_pushed_at":"2026-09-19T10:47:57+00:00","maintenance_label":"Very active","stars_delta_30d":128,"url":"https://www.graphcanon.com/tools/nicedreamzapp-claude-code-local","markdown_url":"https://www.graphcanon.com/tools/nicedreamzapp-claude-code-local.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/nicedreamzapp-claude-code-local","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=nicedreamzapp-claude-code-local","description":"Run Claude Code 100% on-device with local AI on Apple Silicon. MLX-native Anthropic-API server. 6 fighters incl. Muse-Glimmer 30B (now multimodal — reads images, abliterated), Gemma 4 31B, Qwen 3.5 122B (65 tok/s), DeepSeek V4 Flash (1M ctx). Private, offline, airgap-ready. Built for NDA / legal / healthcare workflows.","homepage_url":"https://www.youtube.com/@nicedreamzapps","license":"MIT","open_issues":2,"watchers":30,"ai_summary":"A Python-based repository providing an MLX-native Anthropic-API server and support for running various large language models locally on Apple Silicon devices.","readme_excerpt":"<div align=\"center\">\n\n# 🧠⚡ Claude Code Local\n\n### Claude Code, running on your own Mac. No cloud. No API key. No waiting.\n\n**Your Mac's chip runs the AI · Claude Code works exactly like it always does · nothing leaves your computer**\n\n<a href=\"https://github.com/nicedreamzapp/claude-code-local/stargazers\"><img src=\"https://img.shields.io/github/stars/nicedreamzapp/claude-code-local?style=for-the-badge&logo=github&color=f5c542&labelColor=1f2328\" alt=\"GitHub stars\"></a>\n<a href=\"#-what-you-need\"><img src=\"https://img.shields.io/badge/Mac-Apple_Silicon-111111?style=for-the-badge&logo=apple&logoColor=white\" alt=\"Apple Silicon\"></a>\n<a href=\"#-your-code-stays-home\"><img src=\"https://img.shields.io/badge/🔒_Privacy-100%25_Local-success?style=for-the-badge\" alt=\"100% Local\"></a>\n<a href=\"#-use-it-with-trinidad-head\"><img src=\"https://img.shields.io/badge/🌊_Best_with-Trinidad_Head-a855f7?style=for-the-badge\" alt=\"Best with Trinidad Head\"></a>\n<a href=\"LICENSE\"><img src=\"https://img.shields.io/badge/📜_License-MIT-yellow?style=for-the-badge\" alt=\"MIT\"></a>\n<a href=\"https://discord.gg/ZdSqgAxUW\"><img src=\"https://img.shields.io/discord/1497121921580404818?label=Discord&logo=discord&color=5865F2&style=for-the-badge\" alt=\"Discord\"></a>\n\n</div>\n\n<p align=\"center\">\n  <img src=\"assets/demo.gif\" width=\"860\" alt=\"Claude Code editing a file with Gemma 4 31B running locally on a Mac, no cloud\">\n  <br><em>A real session, unedited. Claude Code reads and edits the file, and the AI answering is running on the laptop.</em>\n</p>\n\n---\n\n## 🛑 Hit your Claude usage limit?\n\nClaude Code just said **\"you've reached your usage limit\"** and the reset is hours away? Keep working:\nsame Claude Code, same project, but the AI answering runs on your own Mac.\n\n```bash\ncurl -fsSL https://raw.githubusercontent.com/nicedreamzapp/claude-code-local/main/install.sh | bash\n```\n\nThat's it. It even works on a **16 GB MacBook**, and gets better the more memory your Mac has.\n\n---\n\n## 🌊 Use it with Trinidad Head\n\n**Trinidad Head is the recommended terminal for running local models, on Mac and PC.** It's built\nfrom scratch by the same person who made this project, and it makes long local-AI sessions nicer:\n\n- 🪟 **Glass windows with a soft neon glow**, rounded and easy on the eyes\n- 🌈 **A different color for every window**, so you can tell your local-model windows apart at a glance\n- 🔠 **Bigger, easy-to-read text**\n- 💬 **Your own prompts stand out** in a soft bubble, so you can find what you asked when you scroll back\n- 🖱️ **Copy and paste just work**, even under Claude Code's calm focus view\n\n<p align=\"center\">\n  <img src=\"https://raw.githubusercontent.com/nicedreamzapp/trinidad-head/main/docs/images/colors.jpg\" width=\"860\" alt=\"Three Trinidad Head windows, each glowing a different color\">\n</p>\n\n👉 **[Get Trinidad Head](https://github.com/nicedreamzapp/trinidad-head)** · [project page](https://nicedreamzwholesale.com/software/trinidad-head/)\n\n---\n\n## 🔋 Out of Claude credits? Keep going.\n\nWhen Claude runs out, type **`exit`** in Claude Code, then **`keep going`**. You get a short menu,\nand **the same conversation carries on** with whichever model you pick:\n\n- ☁️ **Free cloud models** from OpenRouter (add a free key, see below)\n- 💻 **Models on your Mac** from the lineup below, sized to fit your memory\n\n<p align=\"center\">\n  <img src=\"https://raw.githubusercontent.com/nicedreamzapp/trinidad-head/main/docs/images/keep-going.jpg\" width=\"860\" alt=\"The keep going menu: free cloud and local models to continue a Claude conversation\">\n</p>\n\n`setup.sh` installs it for you. To add it by hand, or to turn on the free cloud models:\n\n```bash\necho 'source \"$HOME/claude-code-local/scripts/keepgoing-shell.sh\"' >> ~/.zshrc   # the \"keep going\" command\nmkdir -p ~/.config/claude-code-local\necho 'OPENROUTER_API_KEY=your-free-key' >> ~/.config/claude-code-local/keepgoing.env   # optional\n```\n\nWant a reminder at the bottom of every Claude window? Point your status line at\n`scripts/statusline-ke","github_created_at":"2026-03-26T06:43:30+00:00","created_at":"2026-07-15T10:58:18.478766+00:00","updated_at":"2026-09-20T04:59:33.727873+00:00","categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"ai-privacy","name":"ai-privacy"},{"slug":"airgap","name":"airgap"},{"slug":"anthropic-api","name":"anthropic-api"},{"slug":"apple-silicon","name":"apple-silicon"},{"slug":"local-ai","name":"local-ai"},{"slug":"offline-ai","name":"offline-ai"},{"slug":"on-device-ai","name":"on-device-ai"},{"slug":"private-ai","name":"private-ai"}],"trust":{"provenance":{"is_fork":false,"github_id":1192378543,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T04:59:30.993Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":2,"days_since_push":0,"last_release_at":"2026-08-22T22:36:42Z","stars_delta_30d":128,"open_issues_delta_30d":1},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-15T10:58:19.655Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T04:59:32.285Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-20T04:59:32.285Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-20T04:59:32.285Z"}},"decision_facts":{"hosting":null,"pricing":{"model":"freemium","summary":"Free to use under the MIT license; premium support or features may incur costs not detailed in the repository."},"requirements":{"notes":["- Needs Apple Silicon hardware.","- Compatible with Python."],"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"pricing_model":"freemium","requires_docker":false},"when_to_use":["- You need to conduct NDA, legal or healthcare projects that require strict data privacy and airgapping.","- Your workflow involves heavy use of voice AI capabilities on Mac machines."],"when_not_to_use":["- If you are not working within the Apple ecosystem as it primarily supports devices running Apple Silicon.","- For workflows where real-time collaboration and cloud-sharing features are integral to your operations, as claude-code-local focuses on local execution."],"source":"enrich:decision_facts","observed_at":"2026-07-17T10:09:35.699Z"},"constraint_facets":{"min_ram_gb":null,"pricing_model":"freemium","requires_docker":false},"decision_summary":[{"label":"Pricing","value":"freemium - Free to use under the MIT license; premium support or features may incur costs not detailed in the repository."},{"label":"Requirements","value":"- Needs Apple Silicon hardware.; - Compatible with Python."},{"label":"Adopt for","value":"claude-code-local offers an MLX-native Anthropic-API server and support for running large models locally on Apple Silicon with high token throughput and privacy guarantees."}]}}