lemon07r/SanityBoard

Home of the SanityHarness Leaderboard website.

18
/ 100
Experimental

This tool provides a centralized hub to track and compare the performance of AI coding agents. It takes in structured evaluation data from agent runs, like scores and pass rates for different coding tasks, and displays them on a browsable leaderboard. This is ideal for researchers, developers, or evaluators who need to assess and benchmark AI agents.

Use this if you need a clear, interactive way to visualize and compare the evaluation results of various AI coding agents.

Not ideal if you're looking for a tool to run the AI agent evaluations themselves, as this focuses solely on displaying pre-existing results.

AI-agent-evaluation coding-agent-benchmarking AI-performance-tracking developer-tools research-analytics
No License No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 3 / 25
Community 0 / 25

How are scores calculated?

Stars

14

Forks

Language

HTML

License

Last pushed

Feb 28, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/lemon07r/SanityBoard"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.