leanlab is an open-source CLI tool designed for evolving and evaluating AI agent experiments and coding tasks. It supports experiment evolution against fixed metrics and automates the spec-to-merge workflow with locked acceptance tests, helping AI researchers and developers improve agent reliability and performance.
leanlab is a LLM eval & observability project. It focuses on automating the evolution and evaluation of AI agent experiments and coding tasks for improved performance and reliability. It is built as an open-source project for AI researchers and developers. leanlab is open source under the MIT license. It runs on the command line.
It is developed by bacharSalleh, and it first shipped in 2026. Development happens publicly on GitHub with 42 commits in the last 90 days. Among its 5 catalogued features are experiment evolution, agent evaluation, and acceptance tests.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do