Agent step
humanbrowser|Agent step|unknown|step
humanbrowser|Agent step|unknown|step
humanbrowser|Browser session|unknown|hour
humanbrowser|Captcha handling|unknown|solve
humanbrowser|Live viewer and human takeover|unknown|flat
humanbrowser|Residential traffic|unknown|gb
webhosting_mcp · job 78%AgentSmith · job 77%anansi · job 74%oculo · job 72%opentools · job 71%playwright_browser · job 71%Browser Infrastructure for AI Agents · job 77%worbrow · job 76%glance · job 75%agentos_ai · job 74%browser_mcp · job 71%mcp_server_browserbase · job 82%bowmark · job 70%ai_browser_mcp · job 73%unbrowser by Unchained · job 77%openowl · job 71%scrapegraph_mcp · job 71%Navette · job 77%MCP Browser Use · job 79%kitsuvo · job 76%Nexus Browser MCP · job 81%browseros · job 81%browsermcp · job 74%asteroid · job 72%mcp_aoai_web_browsing · job 74%StableBrowse · job 72%BrowserCat Remote Browser Automation · job 81%browser_agent_py · job 79%playwright_mcp · job 75%Kernel · job 72%chrome_playwright_mcp · job 71%multi_browser_mcp · job 74%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