agent-eval
Public
Pull mirror status: ok
#218
repo website down
maxffarrell
#216
Saved transcripts of registered custom agents are not parsed
RaphaelFakhri
#190
Codex session-file transcript may not match the schema the o11y parser expects
gaojude
#189
runtime: 'node20' fails sandbox creation on the Vercel backend (HTTP 400)
gaojude
#168
Housekeeping deletes nested fixture results as incomplete
kasperpeulen
#136
Better container rate limiting with Docker
jonahsnider
#134
Support limiting max turns for agents in evals
jonahsnider
#129
Support for eval dirs more than one level deep
unjust
#102
feat(results): ExperimentTrendAnalyzer — cross-run pass rate regression detection across timestamp directories
nanookclaw
#90
Add Mistral Vibe as a supported agent harness
benjamincanac