Scores GUI agents and compiled workflows on benchmarks such as Windows Agent Arena, using each benchmark's own checker.
Latest release v0.98.0 · 17 Oct 2026
1 file for Claude Code: openadapt-evals CLAUDE.md — 10,026 tokens loaded in every session.
CLAUDE.md C 10,026 tok These files are OpenAdaptAI/openadapt-evals's own configuration — they tell Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.