# Evaluate — card for AI agents

HuggingFace library for evaluating machine learning models with standardized metrics.

Category: Prompts, structured output and evals · PyPI package `evaluate` · latest version 0.4.6 (checked 2026-11-01)
Install: `pip install evaluate`
License: Apache-2.0 (permissive)

In your own product (generator, app, hosted service): **yes**. Permissive license: ship it inside your own product, closed or open source, and keep its license and copyright notice.

## Agent Skills for it
- evaluate from Q00/ouroboros: `npx skills add Q00/ouroboros --skill evaluate`
- evaluate-presets from mikeyobrien/ralph-orchestrator: `npx skills add mikeyobrien/ralph-orchestrator --skill evaluate-presets`
- evaluate-rag from ai-evals-course/evals-skills: `npx skills add ai-evals-course/evals-skills --skill evaluate-rag`

## Numbers (AgentGid data)
- Gid Score: 48.4 (#2041 of all tools, 32 of 78 in its category)
- Used in 4 public projects set up for AI coding agents (0.1%)
- Downloads last week: 1,084,056 (as of 2026-11-17), +8.0% over 4 weeks
- GitHub stars: 2,497 (as of 2026-11-17)
- Last push: 2026-11-16

## Often used with
Hugging Face Datasets 88.9%, NumPy 81.0%, pandas 81.0%, Accelerate 79.4%, OpenAI Python Library 73.0%, Hugging Face Transformers 68.3%

## Checked alternatives (same job)
- Ragas: https://agentgid.com/tools/ragas/agent.md

## Links
- AgentGid page: https://agentgid.com/tools/evaluate/
- Homepage: https://github.com/huggingface/evaluate
- Repository: https://github.com/huggingface/evaluate

---
AgentGid's catalog is curated: every entry was checked against the maker's official pages (registry, repository, license and pricing pages) on the date shown; a license value shows the quote it stands on wherever AgentGid has one. Usage numbers come from AgentGid's own scan of public repositories set up for AI coding agents. Claims by makers are reported, not tested by AgentGid.
