Test legal AI agents
Harvey Labs is a benchmarking tool designed to measure and improve the capabilities of artificial intelligence agents that support tasks in the legal field. This study, prepared in Python language, aims to evaluate the performance of software that develops legal technologies with standard tests.
Updates
- October 22, 2026: Stars 1,401 → 1,504, latest release v1.3.0 (October 21, 2026).
- October 1, 2026: Stars 1,370 → 1,401, latest release v1.2.0 (October 1, 2026).
- September 19, 2026: Stars 881 → 1,370, latest release v1.1.0 (September 18, 2026).
What you get
- Measures AI performance in legal tasks
- Provides realistic business scenarios and documentation
- Standardizes agents' legal competence
Getting started
To get started, check out the docs/tutorial.md file among the documentation on the GitHub page. This guide walks you through how to manage an M&A data room mission end-to-end, from setup to report review.
Related dictionary terms
Links
TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-08-10: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.