Skip to main content
Glama
udjin-labs
by udjin-labs

Related Servers

Alternatives to mnemostack

No user-submitted related servers found.

    Related Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      MCP server that enables persistent, hybrid, local memory for LLM agents, with vector + BM25 search, knowledge graph, and policy-driven retention, providing token-budgeted context injection for AI assistants.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Persistent, semantically-searchable memory for AI agents using local PostgreSQL, pgvector, and Ollama embeddings, exposed via MCP with hybrid retrieval, knowledge graph, and auto-recall hook.
      3 npm
      MIT
    • A
      license
      A
      quality
      A
      maintenance
      Persistent memory MCP server for AI coding agents (Claude Code, Codex, Gemini CLI). Hybrid retrieval (vector + BM25), cross-encoder reranking, knowledge graph, session checkpoint/resume, and multi-scope isolation. Local-first with LanceDB.
      30
      200 npm
      15
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Local-first AI memory layer with hybrid retrieval and brain-inspired namespaces. Enables agents to save, search, and manage memories directly via MCP tools.
      5 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Persistent AI memory server with hybrid search and embedded sync. Enables AI agents to store, retrieve, and manage information across sessions with temporal knowledge graph support.
      MIT

    TDQS

    A4.4/5.0

    Scored across 7 tools

    Disambiguation5/5

    Each tool has a clearly distinct role: health checks backend status, search returns raw matches, answer synthesizes an answer, resolve verifies citations, invalidate retracts memories, remember stores new memories, and feedback records learning signals. The only potentially confusing pair is search vs. answer, but the descriptions explicitly separate raw retrieval from synthesized response.

    Naming Consistency4/5

    All tools share the consistent mnemostack_ prefix and mostly use verb-like action names such as search, answer, resolve, invalidate, and remember. health and feedback are noun-style rather than verb-style, which is a minor deviation from an otherwise uniform pattern.

    Tool Count5/5

    Seven tools is a well-scoped size for a memory server covering health, ingestion, retrieval, synthesis, retraction, citation verification, and feedback. Each tool earns its place without redundancy or bloat.

    Completeness4/5

    The core memory lifecycle is covered: store with remember, retrieve with search/answer, retract with invalidate, verify with resolve, and learn with feedback. However, there is no permanent delete operation, and the invalidate description references a mnemostack_graph_add_triple write tool that is not present in the set, leaving graph-write coverage unclear.

    Maintenance

    ActivityActive
    ResponsivenessUnresponsive