DeepEval (Confident AI)

Open-source unit tests for LLMs.

Visit site GitHub
Open source Self-hostable free
LicenseApache-2.0
Starting priceSelf-host free
Model supportmulti
Languagespython
GitHub stars16.5k
Last activity2026-06-25
VerifiedThu Jun 25 2026 00:00:00 GMT+0000 (Coordinated Universal Time)
Verified byseed

A pytest-style framework for writing and running LLM evaluations, paired with the Confident AI platform for reporting.

Strengths

  • Pytest-style DX, fits existing test suites
  • Open source metric library

Tradeoffs

  • Confident AI cloud is proprietary
  • Setup for custom metrics takes work