mcp · handle task_journal
cortex · job 81%claude_code_mcp · job 80%astryke_hub · job 78%Knos · job 78%watercooler · job 78%threadctx · job 79%stele · job 80%knowledge-commons · job 82%Agent Work MCP · job 75%Bridge · job 79%mcp_memory_keeper · job 79%sudocode · job 79%MemBridge · job 80%Project Desk · job 75%session-hub · job 81%Agent Cowork Memory · job 84%Effort · job 78%claude-dig · job 79%RelayHistory · job 75%magents · job 77%jevmem · job 82%subtask · job 76%RelayFence · job 78%Kimetsu · job 82%OptChat · job 79%Bellek · job 76%roo_logger · job 75%Engram · job 79%ClaudeBase · job 75%cli_history_hub · job 75%Ego Chat · job 77%Hive · job 80%remem · job 85%one_brain · job 79%claude_memory_mcp_2 · job 77%CodeBudget · job 78%linklore · job 81%MemHub · job 81%CommitLore · job 76%agent_mesh · job 79%Basemind · 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