npm · Agent evaluation and testing

Validates OpenHarness features by running real multi-turn agent loops with live LLM calls against an unfamiliar codebase, checking actual tool execution.

HKUDS/OpenHarness

Benchmarks how much CodeGraph helps a coding agent on a real repository, comparing runs with and without it for a chosen local or published version.

colbymchenry/codegraph

Runs Darwin Mode on an agent harness: mutates one policy file per generation in a sandbox, scores each variant against your tests, and archives only variants that measurably improve.

ruvnet/RuView