Claude Skill

scouzi1966/maclocal-api

maclocal-api is a Swift CLI that exposes Apple Foundation & MLX models via an OpenAI-compatible endpoint on macOS. Supports server & single-prompt modes, Apple Vision, piping, web browser, and loca...

Overview

Stars299
Forks15
LanguageSwift
Last pushed2026-06-14
Last synced2026-06-17
View on GitHub

Repository

Ownerscouzi1966
Repositorymaclocal-api
Full namescouzi1966/maclocal-api
Repo ID1,034,175,804

Install this Skill

git clone https://github.com/scouzi1966/maclocal-api.git

Registry

Typeopenclaw_skill
Quality score75/100
Verificationreadme_parsed
Last verified2026-06-16
Platforms
ClaudeOpenClawCodexCursor
Capabilities
browsercode-reviewpdfmemorysearchimagevideoterminalaiapple-foundation-models
Detected files
README.mddocspyproject.toml
Install methods
  • git clone https://github.com/scouzi1966/maclocal-api.git
  • pip install macafm==0.9.10 # previous stable
  • pip install --extra-index-url https://maclocal-ai.pages.dev/afm/wheels/simple/ \
  • pip install macafm

Summary

maclocal-api is a Swift-based CLI tool that exposes Apple's Foundation and MLX models, along with other local AI APIs, through a single OpenAI-compatible endpoint on macOS. It supports both server mode and single-prompt (non-server) inference with piping, and now includes a web browser and local AI API aggregator.

Chinese description

'afm' 命令 CLI:macOS 服务器与单提示模式,通过单一聚合的 OpenAI 兼容 API 端点,在 Mac 上暴露 Apple 的 Foundation 和 MLX 模型及其他 API。支持 Apple Vision 及通过管道进行单命令(非服务器)推理。现已集成网页浏览器和本地 AI API 聚合器。

Key features

  • OpenAI-compatible aggregated API endpoint for Apple Foundation & MLX models
  • Dual mode: macOS server and single-prompt (non-server) inference with piping
  • Apple Vision support for image-based AI tasks
  • Web browser integration for interactive usage
  • Local AI API aggregator combining multiple local endpoints

Use cases

  • Run local LLM inference on Apple Silicon without cloud dependency
  • Aggregate multiple local AI APIs into one OpenAI-compatible endpoint for apps
  • Perform image analysis using Apple Vision models via CLI or server
  • Prototype and test Apple Foundation & MLX models with piping and scripting
  • Build privacy-focused AI workflows entirely on macOS

README excerpt

If you find this useful, please ⭐ the repo!   Also check out [Vesta AI Explorer](https://kruks.ai/)! — my full-featured native macOS AI app. ## Install | | Stable (v0.9.12) | Nightly (afm-next) | |---|---|---| | **Homebrew** | `brew install scouzi1966/afm/afm` | `brew install scouzi1966/afm/afm-next` | | **pip** | `pip install macafm` | `pip install --extra-index-url https://maclocal-ai.pages.dev/afm/wheels/simple/ macafm-next` | | **Release notes** | [v0.9.12](https://github.com/scouzi1966/maclocal-api/releases/tag/v0.9.12) | [v0.9.13-next](https://github.com/scouzi1966/maclocal-api/releases/tag/nightly-20260614-a92a0fe) | ### 🔨 Build from source — one command Clone and build everything (submodules, patches, WebUI, release binary) with a single script. It checks your toolchain, auto-installs what it can (Node via Homebrew), and tells you what to install manually (Xcode Command Line Tools) — no AI agent or project knowledge required. The script initializes submodules for you, so a plain `git clone` is all you need. ```bash git clone https://github.com/scouzi1966/maclocal-api.git cd maclocal-api ./build.sh ``` That's it. The `afm` binary lands in `.build/release/afm`. Add `--install` to also install it to `/usr/local/bin` (on your `PATH` by default; uses `sudo` if needed): ```bash ./build.sh --install ``` Run `./build.sh --help` for all options (`--debug`, `--skip-webui`, `--yes` for non-interactive/CI). > [!TIP] > **Switching between stable and nightly:** > ```bash > brew unlink afm && brew install scouzi1966/afm/afm-next # switch to nightly > brew unlink afm-next && brew link afm # switch back to stable > ASSUMES you did a brew install scouzi1966/afm/afm previously > ``` ### Install a previous version Older stable releases are ke

Topics

Explore more

Data from GitHub. Synced on 2026-06-17