Skip to content

Independent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds.

Commits on main

37a2d24
fix(gemini): treat rejected API keys as fatal auth errors (#338)
Rudy Mizrahi Celekli committed 29 days ago
5d62e0c
e868102
8d87b24
fix(b26): identify each per-tool rate-limit probe (#330)
Rudy Mizrahi Celekli committed 29 days ago
dfa4443
ff7edf0
649bc49
fix: accept UTF-8 BOM in dotenv files (#321)
べろしてぃ committed 29 days ago
8dfe0a9
4ced30d
feat: V11 inspection (#356)
stefyi-4355 committed 1 month ago
744796b
chore: bump version (#322)
stefyi-4355 committed 1 month ago
1559983
docs: fold design notes into the guides (#318)
n-papaioannou committed 1 month ago
ebec294
eb4cb4d
fix: preserve all Gemini system message frames (#285)
Rudy Mizrahi Celekli committed 1 month ago
d86ba61
8668dd5
fix: exclude native SUT aliases from judge fallbacks (#312)
Rudy Mizrahi Celekli committed 1 month ago
739e4c2
fix: judging, governance, CI exits (#317)
n-papaioannou committed 1 month ago
26c04a0
18078a4
fix(cli): restore analytic inspection seeds on resume (#313)
Rudy Mizrahi Celekli committed 1 month ago
130e8b3
fix: release native Bedrock clients after workers finish (#301)
Rudy Mizrahi Celekli committed 1 month ago
551d81a
87450c1