Swama

{
  "alternatives": [],
  "artifacts": [
    {
      "app": [
        "Swama.app"
      ],
      "target": "/Applications/Swama.app"
    },
    {
      "zap": [
        {
          "trash": "~/Library/Preferences/trans-n.ai.Swama.plist"
        }
      ]
    }
  ],
  "auto_updates": null,
  "categories": [],
  "deprecated": 0,
  "deprecation_reason": null,
  "desc": "Machine-learning runtime",
  "disable_reason": null,
  "disabled": 0,
  "display_name": "Swama",
  "enrichment_fetched_at": "2026-06-20T22:49:59+00:00",
  "first_seen": "2026-06-20T00:47:34+00:00",
  "full_token": "swama",
  "github_default_branch": "main",
  "github_last_commit_at": "2026-06-08T00:59:35Z",
  "github_readme_excerpt": "# Swama\n\n[![Swift](https://img.shields.io/badge/Swift-6.2-orange.svg)](https://swift.org)\n[![macOS](https://img.shields.io/badge/macOS-15.0+-blue.svg)](https://www.apple.com/macos/)\n[![MLX](https://img.shields.io/badge/MLX-Swift-green.svg)](https://github.com/ml-explore/mlx-swift)\n[![License](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)\n\n\u003e English | [\u4e2d\u6587](README_CN.md) | [\u65e5\u672c\u8a9e](README_JA.md)\n\n**Swama** is a high-performance machine learning runtime written in pure Swift, designed specifically for macOS and built on Apple\u0027s MLX framework. It provides a powerful and easy-to-use solution for local LLM (Large Language Model) and VLM (Vision Language Model) inference.\n\n## \u2728 Features\n\n- \ud83d\ude80 **High Performance**: Built on Apple MLX framework, optimized for Apple Silicon\n- \ud83d\udd0c **OpenAI Compatible API**: Standard `/v1/chat/completions`, `/v1/embeddings`, `/v1/audio/transcriptions`, and `/v1/audio/speech` (experimental) endpoint support with tool calling\n- \ud83d\udcf1 **Menu Bar App**: Elegant macOS native menu bar integration\n- \ud83d\udcbb **Command Line Tools**: Complete CLI support for model management and inference\n- \ud83d\uddbc\ufe0f **Multimodal Support**: Support for both text and image inputs\n- \ud83c\udfa4 **Local Audio Transcription**: Built-in speech recognition powered by Qwen3-ASR and other MLX ASR models (no cloud required)\n- \ud83d\udd0d **Text Embeddings**: Built-in embedding generation for semantic search and RAG applications\n- \ud83d\udce6 **Smart Model Management**: Automatic downloading, caching, and version management\n- \ud83d\udd04 **Streaming Responses**: Real-time streaming text generation support\n- \ud83c\udf0d **HuggingFace Integration**: Direct model downloads from HuggingFace Hub\n\n## \ud83c\udfd7\ufe0f Architecture\n\nSwama features a modular architecture design:\n\n- **SwamaKit**: Core framework library containing all business logic\n- **Swama CLI**: Command-line tool providing complete model management and inference functionality\n- **Swama.app**: macOS menu bar application with graphical interface and background services\n\n## \ud83d\udccb System Requireme",
  "github_repo": "Trans-N-ai/swama",
  "github_stars": 567,
  "github_topics": [],
  "homepage": "https://github.com/Trans-N-ai/swama",
  "homepage_og_description": null,
  "homepage_og_image": null,
  "homepage_title": null,
  "installs_30d": 29,
  "installs_365d": 582,
  "installs_90d": 156,
  "last_seen": "2026-06-20T00:47:34+00:00",
  "llm_generated_at": null,
  "llm_model": null,
  "names": [
    "Swama"
  ],
  "one_liner": null,
  "rank_30d": 2604,
  "rank_365d": 1969,
  "rank_90d": 1990,
  "raw_hash": "9910c727a603d0e7",
  "ruby_source_path": "Casks/s/swama.rb",
  "tap": "homebrew/cask",
  "token": "swama",
  "version": "2.2.0",
  "why_use_this": null
}