agent_platform · handle opensandbox
mistle · job 72%cua · job 75%sandbox_as_a_service · job 79%architect_mcp_server · job 76%mcp_filesystem · job 70%Together Code Interpreter MCP Server · job 82%mcpd · job 70%mithril · job 73%computesdk · job 81%mcp_workspace · job 75%agentos_ai · job 74%cua_ai · job 77%ghostdesk · job 76%Kernel · job 73%code_sandbox_mcp · job 71%litellm_agent_platform · job 78%mcp_test_2 · job 75%basic_fns_mcp · job 73%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