Skip to main content
Glama
Sign In
memsem

memsem

by WindSeries83
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to memsem

No user-submitted related servers found.

    Related Servers

    • neuromcp

      AdelElo13
      A
      license
      Not graded
      quality
      B
      maintenance
      Semantic memory for AI agents — local-first MCP server with hybrid search, knowledge graph, contradiction detection, and plan-then-commit consolidation.
      403 npm
      4
      AGPL 3.0

    • MemVault

      dreamor
      A
      license
      A
      quality
      B
      maintenance
      A self-hosted MCP memory server that gives every MCP-compatible agent a shared, persistent memory layer, so preferences, project conventions, and past decisions carry across sessions and across different agents and vendors. It combines hybrid keyword-plus-vector retrieval with automatic context injection, zero-config sync, and selective injection of memories by agent and priority.
      20
      2
      MIT

    • Memory OS AI

      romainsantoli-web
      A
      license
      Not graded
      quality
      C
      maintenance
      Universal MCP server providing adaptive semantic memory for AI agents, supporting document ingestion, semantic search, chat persistence, cross-project linking, and cloud storage overflow.
      151 PyPI
      3
      GPL 3.0

    • Selti

      Dek1m
      F
      license
      Not graded
      quality
      B
      maintenance
      A persistent memory server for AI agents using MCP protocol, enabling semantic storage and retrieval of dialogues, documents, and agent states.
      -
    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

    A3.6/5.0

    Scored across 18 tools

    Disambiguation4/5

    Most tools have clearly distinct purposes (add vs candidate_add vs episode_add, search vs list vs themes), and descriptions clarify boundaries. However, pairings like memory_add/memory_add_many and memory_forget/memory_purge could cause initial confusion, though the descriptions resolve it.

    Naming Consistency3/5

    All tools share the memory_ prefix, but the suffix pattern is mixed: verbs (add, search, list, verify, score, forget, purge) coexist with nouns (themes, stats, audit, index) and compound actions (candidate_add, episode_search). This inconsistency reduces predictability.

    Tool Count4/5

    At 18 tools, the server is slightly above the ideal 3-15 range but each tool addresses a specific aspect of memory management, from candidate review to episode tracking to scoring. The count feels justified by the domain's complexity rather than redundant.

    Completeness5/5

    The tool set covers the full memory lifecycle: write (add, add_many), review (candidate_*), retrieval (search, list, episode_search), maintenance (verify, score, unsuppress), and deletion (forget, purge), plus auxiliary views (themes, stats, audit, index). No obvious gaps for a semantic memory system.

    Maintenance

    ActivityInactive
    ResponsivenessSyncing

    Resources