mcp · handle memfw
Hierarchical Attention Memory · HFA 2.2 · job 82%connapse · job 83%Arcana · job 82%local-memory · job 84%lil memory · job 81%Mnemosyne · job 81%agent-memory-api · job 81%Meniscus · job 80%motecloud_memory · job 80%WanYi Memory Core · job 78%CentricMem · job 80%Cairn.ink Memory · job 79%mwe_mcp · job 79%rekal · job 80%memalyze · job 85%Agent Memory Router · job 84%clawmem · job 79%MemPalace-rs · job 85%qcdoc-mem · job 83%Zymor · job 86%AiMem · job 83%Awareness Local · job 85%brain-core · job 79%Omoikane · job 81%MCP-Memory · job 84%Graphmory · job 81%noema · job 85%Vaultic · job 78%dxmt · job 80%AINative ZeroDB Memory MCP Server · job 79%Personal Memory MCP · job 81%tabellio · job 85%agentbrain · job 86%githippo · job 80%Human Memory · job 81%RCLL · job 79%Compartment · job 80%Keephaven MCP · job 81%Perenna · job 82%Memora · job 82%Memex · job 81%myMemory · job 78%Memcairn · job 81%Manthan · job 81%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