public evidence dossier
io.github.RudrenduPaul/agent-eval
Statistical regression testing for LLM agents: p-value, effect size, and CI on behavior change.
Latest visible observation: 2026-08-30T22:30:41.080Z
Identity
namespacegithub · observed 2026-08-10T20:36:26.103189Z
registry statusactive · observed 2026-08-10T20:36:26.103189Z
origin systemsadoption, github, registry · observed 2026-08-30T22:30:41.080Z
Distribution
repositoryhttps://github.com/RudrenduPaul/agent-eval · observed 2026-08-11 14:33:02
npm packageUnknown · observed 2026-08-11 14:33:02
PyPI packageUnknown
hosted endpointUnknown
Maintenance and public findings
repository pushedUnknown
repository archivedUnknown · observed 2026-08-11 14:33:02
npm deprecatedUnknown · observed 2026-08-11 14:33:02
OSV package advisoryUnknown · observed 2026-08-11 14:33:02
Hosted liveness
last endpoint observationUnknown
reported MCP revisionUnknown
Limits
This dossier reports public evidence. It is not a safety, code, permission, scope, runtime, or penetration-test verdict. Missing evidence remains unknown.