harnessgym is an open-source CLI framework for benchmarking, testing, and improving agent harnesses for AI code agents such as Codex. It supports iterative improvement, MCP, and is designed for AI researchers and developers.
harnessgym is a LLM eval & observability project. It focuses on providing a framework for benchmarking and improving agent harnesses for AI code agents like Codex. harnessgym is an open-source project aimed at AI researchers and developers. harnessgym is open source under the Apache-2.0 license. harnessgym is available on the command line, and it can be self-hosted.
patrick-toulme builds and maintains harnessgym, and it first shipped in 2026. Development happens publicly on GitHub with 25 stars and 1 commit in the last 90 days. Among its 6 catalogued features are agent benchmarking, codex integration, and MCP support.
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