iFixAi · 2026-10-15 · notable
iFixAi v4.2.0 — the agent auditor adds offline policy checks
iFixAi v4.2.0 makes a 10-inspection suite the default for its open-source AI agent auditor, adds Vercel and Cloudflare AI Gateway support, and ships two offline commands that check agent actions and tool permissions against a policy.
The trending open-source agent auditor gets faster default runs and two offline policy tools.
Key specs
| GitHub stars | 27,969 |
|---|
What is it?
iFixAi v4.2.0 adds two offline commands to the open-source auditor that grades whether an AI agent does the job it was given. `ifixai trajectory` checks recorded agent actions against a business policy, and `ifixai policy-lab` finds harmful combinations of tools that are each allowed on their own.
How does it work?
A plain `ifixai run` now runs a 10-inspection 'essential' suite that still covers all three mandatory minimums, with about six times fewer agent and judge calls; `--full-run` runs all 60 inspections. The trajectory checker reads JSONL or OTLP traces, and policy-lab suggests the smallest permission removal that keeps legitimate goals reachable.
Why does it matter?
Teams can now audit agents in CI quickly and check real recorded runs without calling a model at all. Note that CI exit codes changed in this release: an invalid run now exits 2 and a partial run exits 1, so pipelines that read the exit code should be checked.
Who is it for?
teams shipping AI agents to production
Try it
pip install "ifixai[openai]" && ifixai setup && ifixai run