← Discover
GitHub · ifixai-ai/iFixAi↑ +2,109 today

Audit AI agents

iFixAi is an independent auditing tool that verifies whether AI agents perform their assigned tasks correctly. Developed in Python, this system can be run by humans or the agent itself to analyze process accuracy in under two minutes.

Updates

  • October 23, 2026: Stars 32,525 → 33,443, latest release v4.3.0 (October 22, 2026).
  • October 22, 2026: Stars 30,965 → 32,525, latest release v4.2.1 (October 21, 2026).
  • October 21, 2026: Stars 29,783 → 30,965, latest release v4.2.1 (October 21, 2026).
  • October 19, 2026: Stars 28,006 → 29,783, latest release v4.2.0 (October 15, 2026).

What you get

  • Tests whether your AI agents perform their tasks correctly.
  • Provides a detailed analysis report in less than two minutes.
  • Preemptively catches system vulnerabilities and overlooked errors.

Installation

Install the package
pip install "ifixai[openai]"   # or anthropic, gemini, etc.: install the provider extra you'll test
Open the setup wizard
ifixai setup                    # arrow-key wizard: pick provider, model, judge, suite → writes ifixai.yaml

Running it

Run the tool
ifixai run                      # no flags needed; reports land in ./ifixai-results/

If you don't write code

Paste this into your AI agent (Claude Code · Codex · Antigravity)

I want to check whether my AI agent is working correctly and achieving its goals. For this purpose, perform the necessary tests using the tool named iFixAi and report the results.

Repository: https://github.com/ifixai-ai/iFixAi. Follow the official instructions in the README of this repository for setup and execution.

Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.

Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.

Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.

Related dictionary terms

Who it is forIt is for software developers who build AI agents and want to audit the accuracy of the processes.
LicenseApache-2.0

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-10-15: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.