agent_intern · job 75%Notion AI Hub · job 83%rtfm · job 73%Cursor Code MCP · job 77%uizze · job 77%mcp_opencode · job 74%index_codex_mcp · job 74%mcp_claude_code · job 73%ken-rank · job 73%desktop_commander_mcp · job 72%code_screenshot_mcp · job 72%relace_mcp · job 79%sverklo · job 74%recallnest · job 73%codex_win_to_wsl · job 71%codex_specialized_subagents · job 78%session_export · job 75%skrills · job 78%wcgw · job 77%code_graph_rag · job 76%claude_code_mcp · job 75%frontier_orchestrator · job 75%atlas_scout_mcp · job 71%monomind · job 75%patchloom · job 73%srcbridge · job 72%codeprovenance · job 72%antigravity_delegate_mcp · job 76%codex_mcp_bridge · job 73%werkel · job 73%Roslyn Codex LSP · job 73%Sol–Luna Orchestrator · job 71%Agent Env MCP · job 73%chat-recall · job 80%sous · job 73%CoolPlugz · job 73%DSH × Codex Bridge · job 73%Cheap Labor · job 70%Codex Bridge · job 77%mcp-stama · job 75%opencode-sandbox · job 75%Rekall · 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