google-metrax
A centralized JAX metrics library.
Decision gist · record as of 2026-08-14
Yes. Metrax is actively maintained, has low install friction, carries a permissive Apache 2.0 license, and addresses a real gap in the JAX ecosystem. It's backed by Google and used in production. Install it if you're building JAX-based ML models and need standard evaluation metrics without implementing them yourself.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires JAX and its dependencies (jax, numpy, flax) to be installed; JAX itself has platform-specific requirements.
- Low install friction with a pure Python wheel.
- Actively maintained with recent commits and used by Google products.
License · maintenance · safety
permissive license (permissive) — Licensed under Apache License 2.0 (permissive). You may use, modify, and distribute the package freely in commercial and private projects, provided you include the license and attribute the original work.
last release 2025-11-13 (274 days) · last repo commit 2026-08-11 · 64 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 75,599 downloads/mo, #14,697 on PyPI
Alternatives
Verify before relying
pip install google-metrax
import metrax
# Use predefined metrics for model evaluation
# (specific metric usage depends on your model type)- Which specific metrics are included for each model type (classification, regression, recommendation, language modeling).
- Whether metrax integrates with common JAX training loops or requires custom integration.
- Performance characteristics when used with large-scale distributed training.
What it is and what it does
Metrax is a JAX metrics library that fills a gap in the JAX ecosystem by providing standard evaluation metrics commonly found in TensorFlow and PyTorch. It builds on CLU (CommonLoopUtils) to ensure compatibility with distributed and scaled training environments. The library includes predefined metrics for classification, regression, recommendation, and language modeling tasks, allowing developers to evaluate JAX models without writing custom metric implementations.
The package is developed on GitHub and used by several Google core products, indicating production-level maturity. It depends on core JAX libraries (jax, numpy, flax) plus clu for distributed training support and tensorboardx for visualization integration. Installation is straightforward via pip, and the library is actively maintained with recent development activity.
Use it for
- Evaluate classification models in JAX by computing standard metrics like accuracy, precision, recall, and F1-score.
- Measure regression model performance using built-in loss and error metrics compatible with JAX workflows.
- Assess recommendation system quality with metrics designed for ranking and recommendation tasks.
- Monitor language model evaluation metrics during training with tensorboardx integration for visualization.
- Build distributed training pipelines with metrics that scale across multiple devices via CLU integration.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes.
Metrax is actively maintained, has low install friction, carries a permissive Apache 2.0 license, and addresses a real gap in the JAX ecosystem. It's backed by Google and used in production. Install it if you're building JAX-based ML models and need standard evaluation metrics without implementing them yourself.
Install
google-metrax on PyPI
Before you install
Low install friction with a pure Python wheel. Actively maintained with recent commits and used by Google products. Depends on JAX ecosystem libraries (jax, flax, clu, numpy) and tensorboardx, which are standard in JAX-based ML workflows.
Requires JAX and its dependencies (jax, numpy, flax) to be installed; JAX itself has platform-specific requirements.
License in practice
Licensed under Apache License 2.0 (permissive). You may use, modify, and distribute the package freely in commercial and private projects, provided you include the license and attribute the original work.
Quickstart
pip install google-metrax
import metrax
# Use predefined metrics for model evaluation
# (specific metric usage depends on your model type)Verify before relying
- Which specific metrics are included for each model type (classification, regression, recommendation, language modeling).
- Whether metrax integrates with common JAX training loops or requires custom integration.
- Performance characteristics when used with large-scale distributed training.
Package facts
| License | permissive license permissive |
| Python support | Supports the current Python release >=3.8 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 5 packagescluflaxjaxnumpytensorboardx |
| Maintenance | Actively maintained 274 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 75,599 / month, #14,697 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Operating System :: OS IndependentProgramming Language :: Python :: 3 |
Evidence: google_metrax-0.2.4-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “jax metrics library”
- google-metraxMetrax provides standard evaluation metrics for machine learning…
- raxRax provides ranking losses and metrics for learning-to-rank problems…
- cluCLU provides utilities and abstractions for writing machine learning…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also rax · jax · jaxlib · tokamax · google-tunix · clu · arize-phoenix-evals · torchmetrics · jax-cuda12-plugin