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 product. 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. The project is open source (Apache-2.0). harnessgym is available on the command line, and it can be self-hosted.
It is developed by patrick-toulme, and the product first shipped in 2026. The project is developed in the open on GitHub with 25 stars and 1 commits in the last 90 days. Across PulseGate's embedding index, harnessgym has few near neighbours, marking it as relatively distinct. Among its 6 catalogued features are agent benchmarking, codex integration, and MCP support.
Latest indexed changes and source events
Other apps tracked under the same category.
