agent_platform · handle agentos_ai
openagent · job 79%opensandbox · job 74%TalkCody · job 76%cua · job 79%litellm_agent_platform · job 79%bitontree_ai_agent_development · job 75%Kilo · job 76%massgen · job 75%Aegis Autonomous AI Agent Platform · job 78%credal_ai · job 77%browsermcp · job 81%Jinba · job 77%Fast Agent · job 78%Kilo Code · job 77%cua_ai · job 76%Cline · job 76%Claw Code · job 85%SuperNinja · job 77%humanbrowser · job 74%Kernel · job 78%mcp_aoai_web_browsing · job 80%GenPark · job 80%hatchable · job 76%freya_mcp_server · job 81%local_coding_agent · job 79%Agents @Kopern.ai · job 79%Browser Infrastructure for AI Agents · job 81%floot_mcp · job 80%vibekit_mcp · job 80%rove · job 78%Ink · job 77%trope_cua · job 76%Browserous - Instant Browser for Your Agent · job 76%apify_mcp · job 75%browser_mcp · job 74%ternlang · job 79%CreateOS MCP · job 77%autonomo_mcp · job 75%cloakbrowser_mcp · job 77%CodeGPT AI Agents · job 84%ZeroCrawl MCP · job 78%unified-fetch · job 80%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