LIVE-Last scan updating-53 sources active-167 signals today-BENCHMARKSPerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception

SWE-agent/mini-swe-agent

The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

RDR65Python5,476 stars+0 stars / 7dOpen source

Why this repo matters

Latest release 11d ago, 5 developer signals, 2 package/install signals

The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified! (5476 stars, 747 forks, Python, fresh release, 3 AI signals, 3 developer signals). Latest release: v2.4.2.