Skip to main content
Glama
lulin70

CarryMem

by lulin70
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to CarryMem

No user-submitted related servers found.

    Related Servers

    • Sovereign Universal Memory MCP

      nnaveenraju
      A
      license
      Not graded
      quality
      D
      maintenance
      Provides a persistent, vendor-neutral memory layer that allows AI tools and agents to share context and knowledge across different platforms while maintaining local data ownership. It enables users to store, recall, and manage structured memories through hybrid semantic search and automated context assembly.
      14 npm
      Apache 2.0

    • DataDam Personal Data MCP

      KennethLeeJE8
      A
      license
      Not graded
      quality
      D
      maintenance
      A persistent memory layer for AI tools that decouples personal data from AI's unstable memory, enabling you to mention information once and have it remembered forever across all conversations.
      3
      MIT

    • Smara MCP Server

      nnaveenraju
      A
      license
      Not graded
      quality
      C
      maintenance
      A vendor-neutral, user-sovereign memory layer for AI agents and tools, providing persistent, cross-tool memory that users fully own and control.
      17 npm
      Apache 2.0

    • epitome

      gunning4it
      A
      license
      Not graded
      quality
      D
      maintenance
      Provides a shared, persistent memory layer for AI agents, enabling them to recall, memorize, and review user information across different applications.
      8
      MIT
    Deploy Server
    One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

    TDQS

    B3.1/5.0

    Scored across 31 tools

    Disambiguation3/5

    Several tools overlap in purpose: my_profile and get_memory_profile both surface summaries/statistics; list_rules and my_rules both list rules; match_rules and inject_rules both return applicable rules. That said, descriptions are detailed enough that an agent can usually pick the right one with careful reading.

    Naming Consistency4/5

    All tool names use snake_case and mostly follow verb_noun (classify_message, recall_memories, delete_rule). A few outliers use possessive/noun phrases (my_profile, my_rules, shortest_path) or bare verbs (onboard), but the overall pattern is predictable.

    Tool Count2/5

    31 tools is well past the 25-tool threshold and the surface is bloated: there are multiple overlapping recall and rules-listing tools that could be consolidated. The core memory domain is broad, but many tools feel like variants rather than distinct operations.

    Completeness3/5

    The memory lifecycle covers create, read, search, and delete, but update_memory is missing, forcing delete-and-recreate flows. Rules and knowledge base coverage are solid, and graph/consolidation features fill out the domain, so the gap is notable but not fatal.

    Maintenance

    ActivityActive
    ResponsivenessWithin a week

    Resources