mcp · handle session_steward
Codex Subagent for Claude · job 77%Bottari · job 78%Wingman · job 72%Qoder as Subagent · job 81%Tin Can · job 74%session-hub · job 74%Colmena MCP · job 80%ChatGPT Codex CLI Bridge · job 75%TokenGraph · job 75%Tandem · job 82%AI Chat Memory · job 73%cc-as-subagent · job 81%Cursodex · job 73%index_codex_mcp · job 76%Codex Job Orchestrator · job 79%Terraforma Memory · job 74%Jev Context MCP · job 78%magents · job 74%Notion AI Hub · job 79%Agent Wire · job 80%nouez · job 79%hey Bro! · job 74%recallnest · job 74%Escritório · job 73%Codex Thread Bridge · job 75%Codex History MCP Bridge · job 76%Farcall MCP · job 79%Agent Bus MCP · job 72%Claude Codex MCP · job 77%Personal Agent · job 77%codex_mcp_tool · job 81%Hermes ChatGPT Extension · job 75%Codex Session Messenger · job 79%mcp_opencode · job 77%Claude-Desktop-Bridge · job 76%Threadboard · job 75%thimiko · job 75%chat-recall · job 79%Codex Supervisor MCP · job 79%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