{"data":{"slug":"mcourtyard-m-courtyard","name":"m-courtyard","tagline":"Local AI Model Fine-tuning Assistant for Apple Silicon","github_url":"https://github.com/Mcourtyard/m-courtyard","owner":"Mcourtyard","repo":"m-courtyard","owner_avatar_url":"https://avatars.githubusercontent.com/u/261539834?v=4","primary_language":"TypeScript","stars":172,"forks":14,"topics":["ai-assistant","apple-silicon","desktop-app","fine-tuning","llm","lm-studio","local-llm","lora","macos","mlx","ollama","react","rust","tauri"],"archived":false,"github_pushed_at":"2026-07-11T01:09:27+00:00","maintenance_label":"Steady","stars_delta_30d":11,"url":"https://www.graphcanon.com/tools/mcourtyard-m-courtyard","markdown_url":"https://www.graphcanon.com/tools/mcourtyard-m-courtyard.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/mcourtyard-m-courtyard","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=mcourtyard-m-courtyard","description":"M-Courtyard: Local AI Model Fine-tuning Assistant for Apple Silicon. Zero-code, zero-cloud, privacy-first desktop app powered by Tauri + React + mlx-lm.","homepage_url":null,"license":"Other","open_issues":1,"watchers":1,"ai_summary":"A zero-code, privacy-first desktop app for local model fine-tuning on Apple Silicon devices.","readme_excerpt":"## Requirements\n\n- **OS**: macOS 14+ (Sonoma or later)\n- **Chip**: Apple Silicon (M1 / M2 / M3 / M4 series)\n- **RAM**: 16 GB+ recommended (for 7B/8B models); 8 GB works for small models (1.5B/3B)\n- **Core Runtime**: M-Courtyard guides the local `uv` / Python / `mlx-lm` setup inside the app\n- **Optional Local Runtime**: [Ollama](https://ollama.com) installed and running if you want Ollama-based AI dataset generation or Ollama export\n- **Optional Local Runtime**: [LM Studio](https://lmstudio.ai) if you want LM Studio-based AI dataset generation or to load exported MLX models there\n- **No extra runtime required**: the built-in rules path can generate datasets without Ollama or LM Studio\n\n---\n\n## License\n\nM-Courtyard is open-source software licensed under the [AGPL-3.0 License](LICENSE).\nFor brand name and logo usage, see [Brand and Logo Usage Notice](BRANDING.md).\nFor commercial use or different licensing terms, please contact: `tuwenbo0112@gmail.com`","github_created_at":"2026-02-12T05:34:28+00:00","created_at":"2026-07-15T11:01:27.267237+00:00","updated_at":"2026-09-20T05:07:48.022502+00:00","categories":[{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"ai-assistant","name":"ai-assistant"},{"slug":"apple-silicon","name":"apple-silicon"},{"slug":"desktop-app","name":"desktop-app"},{"slug":"fine-tuning","name":"fine-tuning"},{"slug":"llm","name":"llm"},{"slug":"lm-studio","name":"lm-studio"},{"slug":"local-llm","name":"local-llm"},{"slug":"lora","name":"lora"}],"trust":{"provenance":{"is_fork":false,"github_id":1155972032,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T05:07:45.737Z","maintenance":{"label":"Steady","score":60,"methodology":"github_public_v1","releases_90d":3,"days_since_push":71,"last_release_at":"2026-07-11T01:13:35Z","stars_delta_30d":11,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-15T11:01:28.527Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T05:07:46.779Z"},"languages":{"value":["typescript"],"source":"github.language","observed_at":"2026-09-20T05:07:46.779Z"},"license_spdx":{"value":"Other","source":"github.license","observed_at":"2026-09-20T05:07:46.779Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Specific system requirements for the hardware and OS are not provided but considering its tagline, it is intended for Apple Silicon devices such as newer Macs."],"min_ram_gb":null},"constraints":{"min_ram_gb":null},"when_to_use":["Use M-Courtyard when you need to fine-tune AI models locally without cloud dependencies, especially if your workflow is entirely on Apple Silicon hardware like Macs.","Consider it for projects prioritizing data privacy where sensitive model training processes should remain untouched by external servers."],"when_not_to_use":["Avoid using M-Courtyard if you are working with devices that do not run on Apple Silicon as it is designed specifically for these hardware configurations.","Do not use this tool if your project requires cloud integration or relies heavily on collaborative features since M-Courtyard operates strictly in a zero-cloud environment."],"source":"enrich:decision_facts","observed_at":"2026-07-17T11:43:11.692Z"},"constraint_facets":{"min_ram_gb":null},"decision_summary":[{"label":"Requirements","value":"Specific system requirements for the hardware and OS are not provided but considering its tagline, it is intended for Apple Silicon devices such as newer Macs."},{"label":"Adopt for","value":"M-Courtyard is a specialized tool for local AI model fine-tuning on Apple Silicon devices that emphasizes privacy and offers a zero-code interface."}]}}