Skip to main content
Glama
mnemoverse

Mnemoverse Memory

by mnemoverse
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Related Servers

Alternatives to Mnemoverse Memory

No user-submitted related servers found.

    Related Servers

    • Kronvex

      Daftgoldens
      A
      license
      A
      quality
      D
      maintenance
      Persistent memory API for AI agents — store, recall, and inject semantically-searchable context across sessions. EU-hosted, GDPR-compliant. Supports Claude, Cursor, Cline, and any MCP-compatible client.
      4
      2
      MIT

    • umo-memory

      UmoLab
      A
      license
      Not graded
      quality
      B
      maintenance
      Persistent memory for AI coding agents that stores and recalls preferences, decisions, and conventions via semantic similarity, with zero cloud dependencies and plug-and-play MCP integration for Claude Code.
      Apache 2.0

    • memmd-mcp

      matamong
      A
      license
      B
      quality
      D
      maintenance
      A shared memory layer for AI agents — one memory.md synced across Claude Desktop, Cursor, Claude Code, OpenAI Codex, and any MCP client.
      4
      2
      MIT
    Deploy Server
    Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

    TDQS

    A4.3/5.0

    Scored across 11 tools

    Disambiguation4/5

    memory_read (semantic search) and memory_list_recent (chronological catch-up) are the closest pair, but their descriptions explicitly draw the line ('what do I know about X' vs 'what happened lately'). memory_stats, memory_graph, and memory_feedback each target a distinct read/observe action, and the room tools (create/invite/join/list) are cleanly separated. vault_list is the one off-domain item, though its purpose is unmistakable.

    Naming Consistency4/5

    Ten of eleven tools follow a consistent snake_case memory_<verb>_<noun> pattern (memory_write, memory_read, memory_create_room, memory_join_room, etc.). The lone outlier, vault_list, breaks the prefix but is still readable and clearly scoped to a different resource.

    Tool Count5/5

    Eleven tools is well within a comfortable range and each maps to a real operation: core memory I/O, feedback/ranking, graph inspection, and a four-step room-sharing lifecycle. Nothing appears redundant or padding.

    Completeness4/5

    Core lifecycle is covered: write, search, list, rate, inspect stats/graph, plus full room create/invite/join/list. Deliberate omissions exist (no delete/update — corrections go through memory_write), but the vault surface is thin: only vault_list, with no way to store or manage secrets, and no room leave/revoke operation, which agents would have to work around.

    Maintenance

    ActivityActive
    ResponsivenessSlow

    Resources