{"data":{"slug":"scouzi1966-maclocal-api","name":"maclocal-api","tagline":"macOS-based CLI and aggregator for utilizing Apple's ML models with OpenAI-compatible API","github_url":"https://github.com/scouzi1966/maclocal-api","owner":"scouzi1966","repo":"maclocal-api","owner_avatar_url":"https://avatars.githubusercontent.com/u/58265937?v=4","primary_language":"Swift","stars":342,"forks":17,"topics":["ai","apple-foundation-models","apple-intelligence","apple-llm","apple-llm-integration","apple-silicon","finetuning-llms","local-llm","localai","lora","macos-app","macos-swift","mlx","mlx-swift","openai-api","openclaw","opencode","opencode-ai","oss"],"archived":false,"github_pushed_at":"2026-09-20T03:55:01+00:00","maintenance_label":"Very active","stars_delta_30d":16,"url":"https://www.graphcanon.com/tools/scouzi1966-maclocal-api","markdown_url":"https://www.graphcanon.com/tools/scouzi1966-maclocal-api.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/scouzi1966-maclocal-api","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=scouzi1966-maclocal-api","description":"'afm' command cli: macOS server and single prompt mode that exposes Apple's Foundation and MLX Models and other APIs running on your Mac through a single aggregated OpenAI-compatible API endpoint. Supports Apple Vision and single command (non-server) inference with piping as well . Now with Web Browser and  local AI API aggregator","homepage_url":null,"license":"MIT","open_issues":23,"watchers":4,"ai_summary":"maclocal-api exposes Apple Foundation and MLX Models through an aggregated OpenAI-compatible endpoint in both server and single-command modes, supporting local inference.","readme_excerpt":"# AFM — local AI infrastructure for Apple Silicon\n\n\n\n\n\n\n[Website](https://maclocal.ai) · [Documentation](https://maclocal.ai/docs) · [GitHub releases](https://github.com/scouzi1966/maclocal-api/releases)\n\n> [!IMPORTANT]\n> **AFM is moving to a two-layer architecture built on AFMKit.**\n>\n> [AFMKit](https://github.com/scouzi1966/AFMKit) is the reusable Swift foundation\n> for building native AI apps and agents on Apple platforms. It owns the shared\n> model contracts and provider runtimes for Apple Foundation Models, MLX, and\n> DwarfStar, including generation, streaming, tool calling, structured output,\n> and multimodal services.\n>\n> **maclocal-api remains the complete AFM product**: the `afm` CLI, local\n> OpenAI-compatible server, WebUI, packaging, and operational tooling. It now\n> consumes one exact-versioned AFMKit dependency instead of carrying parallel\n> provider implementations. This separation lets apps and agents embed AFMKit\n> directly while server users continue to install and run AFM as before.\n>\n> The migration is being delivered incrementally. Existing AFM commands and API\n> compatibility remain the product contract while provider ownership moves into\n> AFMKit and maclocal-api becomes a focused application layer on top of it.\n\n---\n\n## Install\n\n> [!NOTE]\n> **Stable v0.9.19 is the recommended release.** It expands model support,\n> OpenAI Responses and Anthropic Messages compatibility, image endpoints,\n> native checkpoint conversion, and runtime reliability. Install `afm-next`\n> only to preview changes made after v0.9.19.\n>\n> Use this stable release unless a newer nightly explicitly lists a\n> post-v0.9.19 change you need.\n\n|  | Stable (v0.9.19) | Nightly (afm-next) |\n|---|---|---|\n| **Homebrew** | `brew install scouzi1966/afm/afm` | `brew install scouzi1966/afm/afm-next` |\n| **pip** | `pip install macafm` | `pip install --extra-index-url https://maclocal-ai.pages.dev/afm/wheels/simple/ macafm-next` |\n| **Release notes** | [v0.9.19](https://github.com/scouzi1966/maclocal-api/releases/tag/v0.9.19) | [Latest nightly](https://github.com/scouzi1966/maclocal-api/releases) |\n\n---\n\n### Install a previous version\n\nOlder stable releases are kept as pinned formulae in the Homebrew tap and as version-pinned wheels on PyPI. This is useful for reproducing an issue against a specific build or rolling back without waiting for a new release.\n\n**Homebrew (pinned stable formulae):** `afm@<version>` — available for `0.9.0`, `0.9.1`, and `0.9.3`–`0.9.10`.\n\n```bash\nbrew install scouzi1966/afm/afm@0.9.10\nbrew uninstall afm\nbrew link afm@0.9.10\nafm --version\n```\n\n**Homebrew (pinned nightly formulae):** `afm-next@<full-version>` — for example, `afm-next@0.9.15-next.20260808.e70cc52`. See the [Homebrew tap](https://github.com/scouzi1966/homebrew-afm) for available pinned nightlies.\n\n```bash\nbrew install scouzi1966/afm/afm-next@0.9.15-next.20260808.e70cc52\n```\n\n**pip (version-pinned wheels):** install any published release by version.\n\n```bash\npip install macafm==0.9.10\npip install --extra-index-url https://maclocal-ai.pages.dev/afm/wheels/simple/ \\\n  macafm-next==0.9.15.dev20260808\n```\n\n---\n\n## Requirements\n\n- Apple Silicon Mac\n- macOS 26 or newer for the complete feature set\n- Xcode 27 for development builds\n- Disk and unified memory appropriate for the model you choose\n\nSmall 0.6B–4B quantized models are the easiest way to confirm a setup. Large 30B-class models need substantially more unified memory.","github_created_at":"2025-08-08T01:20:14+00:00","created_at":"2026-07-15T10:59:53.659588+00:00","updated_at":"2026-09-20T05:03:44.61193+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","name":"ai"},{"slug":"apple-foundation-models","name":"apple-foundation-models"},{"slug":"apple-intelligence","name":"apple-intelligence"},{"slug":"apple-llm","name":"apple-llm"},{"slug":"apple-silicon","name":"apple-silicon"},{"slug":"finetuning-llms","name":"finetuning-llms"},{"slug":"local-llm","name":"local-llm"},{"slug":"macos-app","name":"macos-app"}],"trust":{"provenance":{"is_fork":false,"github_id":1034175804,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-20T05:03:42.781Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":30,"days_since_push":0,"last_release_at":"2026-09-20T03:55:00Z","stars_delta_30d":16,"open_issues_delta_30d":6},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-15T10:59:54.850Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-20T05:03:43.817Z"},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-09-20T05:03:43.817Z"},"languages":{"value":["swift","python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-20T05:03:43.817Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-20T05:03:43.817Z"}},"decision_facts":{"hosting":{"model":"self_hosted","summary":"Enables users to run their own models locally without needing external cloud services."},"pricing":{"model":"freemium","summary":"Being under MIT license, the core software is free. Any potential additional features or support might be charged for separately."},"requirements":null,"constraints":{"hosting_model":"self_hosted","pricing_model":"freemium"},"when_to_use":["You need to integrate Apple's MLX or Foundation Models locally on a Mac in a manner that conforms to the OpenAI API standard.","Your workflow requires utilizing Apple-specific hardware features like Apple Silicon, and you want to operate with local AI without internet dependency."],"when_not_to_use":["You are working on non-Mac platforms as maclocal-api is macOS-dependent and does not support cross-platform operations.","If you require cloud-based services or integration with broader cloud ecosystems that do not align with the OpenAI-compatible API offered by maclocal-api."],"source":"enrich:decision_facts","observed_at":"2026-07-17T07:07:25.694Z"},"constraint_facets":{"hosting_model":"self_hosted","pricing_model":"freemium"},"decision_summary":[{"label":"Hosting","value":"self hosted - Enables users to run their own models locally without needing external cloud services."},{"label":"Pricing","value":"freemium - Being under MIT license, the core software is free. Any potential additional features or support might be charged for separately."},{"label":"Adopt for","value":"maclocal-api is a macOS-specific tool that aggregates Apple's ML models into an OpenAI-compatible API endpoint, offering server and single-command modes for local inference with support for Apple Vision."},{"label":"License detail","value":"MIT License allows for free use, modification, and distribution as long as the license terms are included in any redistribution of the software."}]}}