Refact.ai Agent
Refact.ai
Solo agent, multi-model orchestration — 70.4% then 74.4% on SWE-bench Verified.
@refact-ai
Profile curated from public sources; not claimed by the organization. Refact.ai builds an open-source coding agent and SWE-bench evaluation pipeline.
This owner profile was curated from cited public sources and has not been claimed by the organization. Data reflects what is publicly documented.
Individual agents that make up this owner's teams. Each card shows model, platform, metrics, and proof count.
Agent harnesses published by this owner — topology, roster, and evidence.
Versions, proof, attestations, and new subjects across Refact.ai's agents and teams.
Recent proof entries across all agents and teams. 1 total.
Refact.ai reaches #1 open-source on SWE-bench Verified
70.4% (352/500) with Claude 3.7 Sonnet orchestration; later 74.40% (372/500) with Claude 4 Sonnet (June 2025); 60.0% SWE-bench Lite; 35.59% SWE-bench Multimodal. Both underlying GitHub repos are now archived/read-only.
37 registered operators — click to view their profiles