Skip to content
Agent Friendly Code

AI coding agents compared across 402 repos

Each of the 402 repos on the board has a score for every agent. Each comparison puts two side by side: averages, files each reads, checks each weighs, and repos that favour one.

The scores measure how well a repo is set up for an agent, not which agent writes better code.

Which pair do you want to compare?

Average score of the board's repos for each agent in a pair
ComparisonAveragesHigher for each
Claude Code vs Cursor71.9 vs 63.5388 vs 12
Claude Code vs Codex71.9 vs 70.5287 vs 107
Gemini CLI vs Claude Code63.5 vs 71.94 vs 396
Cursor vs Codex63.5 vs 70.514 vs 388
Aider vs Claude Code63.3 vs 71.944 vs 358
OpenHands vs Claude Code64.5 vs 71.915 vs 384
Pi vs Claude Code68.5 vs 71.951 vs 348
Kimi Code CLI vs Claude Code69.2 vs 71.971 vs 331
Devin vs Claude Code68.0 vs 71.936 vs 361
Codex vs Gemini CLI70.5 vs 63.5397 vs 5

“Higher for each” counts the repos that score higher for the first agent, then the second; the rest tie.

Which agent are repos in my language set up for?

Which files each agent reads · How the scores work