# onnx/onnxmltools

ONNXMLTools enables conversion of models to ONNX

Repository: https://github.com/onnx/onnxmltools
Canonical: https://ross.abutalabs.com/products/onnxmltools
Homepage: https://onnx.ai
Language: Python
License: Apache-2.0
License Family: permissive
Topics: machine-learning, python-library, onnx, scikit-learn, keras
Last push: 2026-08-01T14:59:40+00:00

## Health v2 (maintenance only)
Score: 78/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 95, release rhythm 44, longevity 100
- inputs: {"age_days": 3120, "days_push": 32, "days_rel": 215, "gap_med": 175, "n_releases_24m": 4}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1170, forks 218 (observed 2026-08-28T04:03:51.272255+00:00)

## What it is
ONNXMLTools is a Python library that converts machine learning models from various toolkits (Keras/TensorFlow, scikit-learn, Core ML, XGBoost, LightGBM, Spark ML, H2O, CatBoost, libsvm) into the ONNX format. It acts as a wrapper around specialized converters to enable model interoperability across frameworks and inference runtimes.

## Use cases
- convert a keras model to onnx
- export xgboost model to onnx format
- convert scikit-learn model for onnx runtime inference
- deploy lightgbm model with onnx
- make machine learning models framework-agnostic
- convert core ml models to onnx
- run catboost models on onnx runtime

## When to choose
- you need to deploy models trained in one framework using an ONNX runtime
- you want hardware-optimized inference via ONNX-compatible runtimes
- you need a single converter entry point for multiple ML toolkits

## When to avoid
- you use PyTorch, which has a built-in ONNX exporter
- you need conversion for a toolkit not in the supported list
- you only work within a single framework end to end

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, serialization, compiler
- domain: machine-learning, deep-learning, developer-tools
- platform: python, cross-platform
- tags: onnx, model-conversion, scikit-learn, keras, xgboost, lightgbm, interoperability

## Member repositories
- onnx/onnxmltools (main) score 78

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:51.272255+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:28:38.337473+00:00, confidence not recorded.
  - readme: https://github.com/onnx/onnxmltools (fetched 2026-08-28T04:03:51.272255+00:00, sha 764dafa5b0c0)
  - homepage: https://onnx.ai (fetched 2026-08-29T12:34:30.461706+00:00, sha d1e78f2c07f3)
  - site_page: https://onnx.ai/about.html (fetched 2026-08-29T12:34:30.471042+00:00, sha 2928d89a5b86)
  - registry_pypi: https://pypi.org/pypi/onnxmltools/json (fetched 2026-08-29T12:34:30.473172+00:00, sha e68ea4fd5e13)
- Data as of 2026-08-30T08:39:29.467469+00:00.