search-gpt · job 75%memcord · job 76%longhand · job 74%pūrmemo · job 76%memoryos · job 72%Claude KB · job 76%MyAITwin · job 75%DeepMem · job 79%nxm-memory · job 73%MCP Server Chat History · job 73%Carry-On · job 73%GPT History MCP · job 73%Local Search · job 75%RelayHistory · job 73%soroka · job 70%PawRecall · job 81%alexandria · job 75%neurostack · job 75%claude_semantic_memory_mcp · job 71%memex_mvp · job 80%thimiko · job 74%kept · job 71%Local RAG MCP · job 72%brain_mcp · job 83%llama-memory · job 72%Dotiphant · job 72%Tailpipe · job 78%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