🍺 BREW Explorer

← all formulae

onnx

brew install onnx v1.21.0_2 Apache-2.0

C++ library implementing the Open Neural Network Exchange (ONNX) format for ML model serialization and inference.

Why you might care

ONNX is the standard interchange format for deep learning models across frameworks (PyTorch, TensorFlow, etc.), letting you train in one framework and deploy in another. Use this when building ML pipelines, inference servers, or model conversion tools that need to parse, validate, or execute ONNX graphs without framework lock-in.

Categories

Alternatives

CoreML TensorFlow PyTorch
11.7k
30-day installs · #325
37.0k
90-day · #335
104.3k
365-day · #404

Runtime dependencies

Build dependencies

Links

Blurb generated by claude-haiku-4-5 on 2mo ago.

Raw metadata
{
  "aliases": [],
  "alternatives": [
    "CoreML",
    "TensorFlow",
    "PyTorch"
  ],
  "build_dependencies": [
    "cmake"
  ],
  "categories": [
    "library",
    "ml",
    "data-science"
  ],
  "caveats": null,
  "conflicts_with": [],
  "dependencies": [
    "abseil",
    "protobuf"
  ],
  "deprecated": 0,
  "deprecation_reason": null,
  "desc": "Open standard for machine learning interoperability",
  "disable_reason": null,
  "disabled": 0,
  "enrichment_fetched_at": "2026-06-20T23:40:48+00:00",
  "first_seen": "2026-06-20T23:34:18+00:00",
  "full_name": "onnx",
  "github_default_branch": null,
  "github_last_commit_at": null,
  "github_readme_excerpt": null,
  "github_repo": null,
  "github_stars": null,
  "github_topics": [],
  "homepage": "https://onnx.ai/",
  "homepage_og_description": null,
  "homepage_og_image": null,
  "homepage_title": "ONNX | Home",
  "installs_30d": 11745,
  "installs_365d": 104264,
  "installs_90d": 36986,
  "keg_only": 0,
  "keg_only_reason": null,
  "last_seen": "2026-06-20T23:34:18+00:00",
  "license": "Apache-2.0",
  "llm_generated_at": "2026-06-20T23:44:10+00:00",
  "llm_model": "claude-haiku-4-5",
  "name": "onnx",
  "oldnames": [],
  "one_liner": "C++ library implementing the Open Neural Network Exchange (ONNX) format for ML model serialization and inference.",
  "optional_dependencies": [],
  "rank_30d": 325,
  "rank_365d": 404,
  "rank_90d": 335,
  "raw_hash": "f98207f6a5cd9f94",
  "recommended_dependencies": [],
  "revision": 2,
  "ruby_source_path": "Formula/o/onnx.rb",
  "tap": "homebrew/core",
  "test_dependencies": [
    "cmake"
  ],
  "uses_from_macos": [
    {
      "python": "build"
    }
  ],
  "version_head": null,
  "version_stable": "1.21.0",
  "versioned_formulae": [],
  "why_use_this": "ONNX is the standard interchange format for deep learning models across frameworks (PyTorch, TensorFlow, etc.), letting you train in one framework and deploy in another. Use this when building ML pipelines, inference servers, or model conversion tools that need to parse, validate, or execute ONNX graphs without framework lock-in."
}