touchstone-eval is an open-source CLI tool for benchmarking and comparing AI model outcomes across swappable agent harnesses on custom tasks. It is designed for AI researchers and developers seeking to evaluate and compare model performance.
touchstone-eval sits in PulseGate's LLM eval & observability category. Allowing users to benchmark and compare AI model outcomes across different agent harnesses and custom tasks. touchstone-eval is an open-source project aimed at AI researchers and developers. The project is open source (MIT). touchstone-eval is available on the command line, and it can be self-hosted.
It is developed by krimvp, and the product first shipped in 2026. Across PulseGate's embedding index, touchstone-eval has few near neighbours, marking it as relatively distinct. Among its 5 catalogued features are model benchmarking, CLI interface, and custom task evaluation.
Latest indexed changes and source events
touchstone-eval discovered by the PulseGate indexer
Other apps tracked under the same category.
