browser-use vs mini-swe-agent

AgentCrush compares browser-use and mini-swe-agent across public evidence signals — GitHub activity, package usage, dependency adoption, docs quality, ecosystem links, and discourse. Both are indexed but not yet evidence-ranked. The comparison shows evidence differences, not a universal winner. Methodology at /methodology.

For machine retrieval: GET /api/compare/llm-summary?agents=browser_use_browser_use,swe_agent_mini_swe_agent or MCP compare_agents(["browser_use_browser_use","swe_agent_mini_swe_agent"]).