agent_memguard · job 86%MCP KB SQLite · job 92%megamemory · job 80%MemHub · job 86%memorix · job 80%selvedge_2 · job 79%AnchorDB · job 82%OpenContext · job 78%Code Context Storage MCP · job 89%Engram · job 76%supermem · job 76%Knos · job 80%Memory Engine · job 80%memosaver · job 83%State Memory MCP · job 78%Mindtrail · job 90%DevMemory · job 86%remindb · job 76%cortex · job 86%Kardex · job 77%Kiokuko · job 83%Pollux · job 80%Kanban MCP · job 78%tether · job 77%Memlio · job 77%selvedge · job 77%sigil · job 79%CogMemory MCP Server · job 83%codex_agent_mem · job 80%Kimetsu · job 81%Engineering Continuity Graph · job 77%Basalt · job 79%AI Bridge · job 83%SQLiteMCP · job 75%mem-rfm · job 80%jovememory · job 78%repo-memory-mcp · job 85%AgentKanban · job 83%HiveMind · job 81%zerikai_memory · job 76%MemoryWhale · job 82%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