GitHub radar

iFixAi: An AI agent audit in less than 2 minutes!

iFixAi evaluates AI agents from A to F on 5 key pillars with 49 checks — as a Claude Code plugin/Codex plugin/CLI wizard/One Click Skill for Cursor/VS Code/Windsurf/Cline/… Result is generated within 2 mins. Launched in late April 2026, it has gained over 11,000 stars within 4 months.

01ifixai-ai/iFixAi 11kPython

iFixAi is an independent AI agent scoring platform that emphasizes on non-technical factors like deceit, lies, manipulation, randomness, etc. You can use iFixAi to score your own AI service (like OpenAI, Anthropic, Gemini, Azure, Bedrock, OpenRouter, etc.) or any other custom AI agent through HTTP requests. iFixAi will return you a final score between A–F and explanations for each category. You can use iFixAi to score any AI agent (e.g., OpenAI, Anthropic, Gemini, Azure, Bedrock, OpenRouter, your own AI agent, etc.) You can also use iFixAi as a Claude Code plugin/Codex plugin/CLI wizard/One Click Skill for Cursor/VS Code/Windsurf/Cline/… To get a citable score, we have to ask a second opinion from another independent AI service provider (not the one being tested). It only takes you less than 2 minutes to finish all the tests. It would cost you around $12–18 to use claude-sonnet-4.6 as the judge (OpenRouter price in mid-2026). Apache 2.0 License.

Why a vibe-coder should care

Existing AI testing platforms only care about technical metrics like efficiency, latency, prompt injection, etc. However, they don’t tell us how good the AI agent performs in its specific tasks. With iFixAi, we want to test AI agents at a higher level and give them a score (A–F) and reasons for poor scores. This process only takes you less than 2 minutes using plugins or command lines.

How to install

Copy this and send it to your agent — Claude Code, Codex, any of them:

Install the iFixAi plugin from https://github.com/ifixai-ai/iFixAi in Claude Code (commands: `/plugin marketplace add ifixai-ai/iFixAi` then `/plugin install ifixai@ifixai-community`), run an audit of my agent, and show me the scorecard with per-pillar breakdown. Ask me for the API key for the provider you need.

Runs on a regular laptop — only Python 3.10+ and an API key from your chosen provider needed.

Open on GitHub