AgentKits Memory

Current plans

Direct accepted alternatives

Pollux · job 81%sigil · job 83%llmmemory · job 83%codemem · job 83%iai_personal_memory_engine · job 87%heimdall_mcp_server · job 86%DevMemory · job 84%Al Buddy · job 81%mymemory_bot_mymemory · job 79%Fornix · job 84%session-forge · job 87%OpenContext · job 80%Personal Memory MCP · job 79%decisionnode · job 82%Agent Vault MCP · job 83%MindGate MCP · job 85%memosaver · job 85%guild · job 85%Kiokuko · job 79%Memex · job 85%HiveMind · job 83%In-Memoria · job 86%Axon Works · job 83%context_engine · job 83%Pieces · job 83%zikkaron · job 84%graphmemory_ide · job 78%Remote MCP Memory Server · job 79%mimirs · job 84%codex_agent_mem · job 79%mcp_memory_keeper · job 83%engram_mcp · job 80%mindkeg_mcp · job 81%memoraeu · job 80%rtfm · job 82%cachly AI Brain · job 84%conxt · job 81%zerikai_memory · job 81%TeamMemory · job 85%Frugal Memory · job 81%mnemex · job 80%codebase-memory-mcp · 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.

Inspect histories

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