apfel

{
  "aliases": [],
  "alternatives": [
    "ollama",
    "llama.cpp",
    "LM Studio"
  ],
  "build_dependencies": [],
  "categories": [
    "language-runtime",
    "http-server"
  ],
  "caveats": null,
  "conflicts_with": [],
  "dependencies": [],
  "deprecated": 0,
  "deprecation_reason": null,
  "desc": "Apple Intelligence from the command-line, with OpenAi-compatible API server",
  "disable_reason": null,
  "disabled": 0,
  "enrichment_fetched_at": "2026-06-20T23:35:26+00:00",
  "first_seen": "2026-06-20T23:34:18+00:00",
  "full_name": "apfel",
  "github_default_branch": null,
  "github_last_commit_at": null,
  "github_readme_excerpt": null,
  "github_repo": null,
  "github_stars": null,
  "github_topics": [],
  "homepage": "https://apfel.franzai.com",
  "homepage_og_description": "Your Mac already has AI. Apple ships a language model with macOS -apfel unlocks it with one brew install. No downloads, no API keys, no config. The fastest path to local AI.",
  "homepage_og_image": "https://apfel.franzai.com/og.png",
  "homepage_title": "apfel - Your Mac Already Has AI",
  "installs_30d": 2584,
  "installs_365d": 4830,
  "installs_90d": 4830,
  "keg_only": 0,
  "keg_only_reason": null,
  "last_seen": "2026-06-20T23:34:18+00:00",
  "license": "MIT",
  "llm_generated_at": "2026-06-20T23:47:34+00:00",
  "llm_model": "claude-haiku-4-5",
  "name": "apfel",
  "oldnames": [],
  "one_liner": "Command-line interface to macOS built-in language models with OpenAI-compatible API server.",
  "optional_dependencies": [],
  "rank_30d": 859,
  "rank_365d": 1961,
  "rank_90d": 1103,
  "raw_hash": "4d18af419f38fcc9",
  "recommended_dependencies": [],
  "revision": 0,
  "ruby_source_path": "Formula/a/apfel.rb",
  "tap": "homebrew/core",
  "test_dependencies": [],
  "uses_from_macos": [],
  "version_head": "HEAD",
  "version_stable": "1.6.0",
  "versioned_formulae": [],
  "why_use_this": "Leverages Apple Intelligence models already shipped with macOS without requiring external API keys, downloads, or configuration\u2014making it the fastest path to local LLM inference on Apple Silicon Macs. Exposes an OpenAI-compatible API, so you can swap it into existing tooling designed for ChatGPT/OpenAI without rewriting."
}