auto_browser · job 75%browseros · job 74%skyvern_ai · job 74%pilotbrowsemcp · job 73%mcp_realbrowser · job 70%bowmark · job 74%nodriver_mcp_server · job 72%browser_agent_py · job 71%drissionpage_mcp_server · job 73%asteroid · job 77%charlotte · job 73%Kernel · job 76%BrowserCat Remote Browser Automation · job 75%humanbrowser · job 72%patchright_browser · job 72%Browser Infrastructure for AI Agents · job 78%AgentLock Browser · job 73%playwright_browser · job 72%ai_browser_mcp · job 76%oculo · job 74%AgentSmith · job 75%haden-browser · job 72%Cognitive Browser · job 71%BrowserMesh · job 70%Web Scraper x402 · job 72%multi_browser_mcp · job 74%vibedeploy_mcp · job 74%Brave DevTools MCP · job 72%librecrawl_mcp · job 74%glance · job 73%vynix · job 71%Percentages are graph-similarity metadata, not suitability scores. A graph edge answers “is it connected” — plan fit and comparable cost are checked below.
Pick the exact reference and alternative series. Each history is separate; gaps stay gaps.
This view calls the same get_evidence tool your agent would — chart, table and MCP response describe the same records. Watch the reference series