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.
      9 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.
      5 npm
      Apache 2.0

    • ContextFS

      contextfs
      A
      license
      Not graded
      quality
      C
      maintenance
      Universal AI memory layer that provides cross-client, cross-repo context management with semantic search, automatic code indexing, and session management. Enables persistent developer memory across projects with typed memories, graph-based relationships, and RAG-powered retrieval.
      5
      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

    B3/5.0

    Scored across 31 tools

    Disambiguation3/5

    Most tools target distinct resources/actions, but several pairs overlap heavily: my_profile vs get_memory_profile and list_rules vs my_rules could both be selected for 'show me what is remembered/saved'. suggestive_rules vs promote_rules and match_rules vs inject_rules also share intent, though descriptions help differentiate their outputs.

    Naming Consistency3/5

    The majority follow a readable verb_noun snake_case pattern (classify_message, recall_memories, add_rule, delete_rule), but there are notable deviations: my_profile, my_rules, health_check, and shortest_path are noun-style names. The mixed conventions are still navigable but not fully predictable.

    Tool Count2/5

    31 tools is a large surface for an agent to reason over, well above the generally well-scoped range. The count is justified by multiple subdomains (memory, classification, knowledge, rules, graph, consolidation), but the overall footprint feels heavy and would benefit from consolidation.

    Completeness3/5

    The surface covers most major lifecycle operations: memory ingest, recall, forgetting, rule CRUD, knowledge indexing/search, graph queries, and consolidation. However, direct memory update is missing (users must forget+re-store), and knowledge base deletion/reindexing is not exposed, leaving noticeable gaps.

    Maintenance

    ActivityActive
    ResponsivenessWithin a week

    Resources