iFixAi is an open-source auditing tool that checks whether an AI agent is doing the job it is supposed to do, balancing AI red-teaming with operational assurance.
A single `ifixai run` executes 32 inspections across five pillars and grades the agent with an A–F scorecard, from the CLI or from inside coding agents via a plugin or skill.
- 01
Guided `ifixai setup` wizard and zero-flag `ifixai run`, or fully scriptable flags for CI
- 02
32 inspections across five pillars with an A–F grade and scored core-pillar scorecard
- 03
Self, independent-vendor or multi-judge ensemble grading
- 04
JSON and Markdown reports plus a rich terminal scorecard
- 05
Claude Code and Codex plugins and a `uvx ifixai install` skill for Cursor, VS Code/Copilot, Windsurf, Cline, Continue, Gemini and Zed
Free
iFixAi is free and open source under the Apache 2.0 license; runs use your own model provider API keys for the system under test and the judge, and a free `--dry-run` shows the cost before anything is billed.
Best for
Teams shipping AI agents that want a fast, repeatable audit of agent behavior against business expectations before and after release.
Not ideal for
Teams that only need latency, token-cost or prompt-injection benchmarks, or that cannot spend model API credits on judge-graded runs.
A practical, agent-native auditing harness that turns 'is my agent doing its job?' into a graded, repeatable report.
iFixAi shipped v4.0.0 on September 15, 2026, renamed its plugin marketplace to ifixai-community, and the repository passed 21,000 GitHub stars with commits landing in early October 2026.
As of
Is iFixAi free?+
Yes - iFixAi is Free. iFixAi is free and open source under the Apache 2.0 license; runs use your own model provider API keys for the system under test and the judge, and a free `--dry-run` shows the cost before anything is billed.
Is iFixAi open source?+
Yes - iFixAi is open source. iFixAi is free and open source under the Apache 2.0 license; runs use your own model provider API keys for the system under test and the judge, and a free `--dry-run` shows the cost before anything is billed.
Who is iFixAi best for?+
Teams shipping AI agents that want a fast, repeatable audit of agent behavior against business expectations before and after release.
Who is iFixAi not ideal for?+
Teams that only need latency, token-cost or prompt-injection benchmarks, or that cannot spend model API credits on judge-graded runs.
What are the best iFixAi alternatives?+
The closest iFixAi alternatives on ai.dosa.dev are GitAuto, AgentDiff, Agent QA - all listed under AI Testing & Quality Assurance.
Who makes iFixAi?+
iFixAi is developed by iFixAi. It is listed in the AI Testing & Quality Assurance category on ai.dosa.dev.
Favorite this tool to revisit it later, or Zap it to contribute to the public vote count.