mcp · handle mnemosyne
local-memory · job 85%GhostPaw Codex · job 84%Arcana · job 82%Unified Memory MCP · job 82%Distill Kura · job 81%memora · job 84%Open Brain · job 78%yourmemory · job 82%linksee_memory · job 84%MemPalace-rs · job 83%MemoryD · job 87%iifa · job 85%sqlite_memory_mcp · job 85%SuperMemory · job 81%mnema · job 79%memalyze · job 80%rekal · job 82%Al Buddy · job 79%Hippocampus MCP · job 84%memory39 · job 81%Meniscus · job 85%noema · job 80%marm_memory · job 80%RCLL · job 80%Tideline Memory · job 87%Plastic Memory · job 83%Human Memory · job 83%MCP Server Memory SQLite · job 80%AiMem · job 81%Zymor · job 79%Vault · job 84%qcdoc-mem · job 82%nocturne_memory · job 79%MCP SQLite Persistent Memory Knowledge Server · job 77%Agent Memory Router · job 86%DevMemory · job 80%Personal Memory MCP · job 81%Recall MCP · job 81%Cairn.ink Memory · job 82%nmemory · job 77%Memory Palace · job 80%agent-memory-api · job 86%motecloud_memory · 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