Skip to main content
Glama
Sign In
vanguard-memory-node

vanguard-memory-node

by ezumba
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to vanguard-memory-node

No user-submitted related servers found.

    Related Servers

    • mcp-vl-msa-rs

      DioNanos
      A
      license
      Not graded
      quality
      C
      maintenance
      A searchable long-term memory server for AI agents using BM25 indexing over document chunks, enabling durable recall across sessions without cloud dependencies.
      1
      Apache 2.0

    • MCP Memory

      GermaniU
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents and any MCP-compatible client to persist, search, update, and delete plain-text memories across sessions, using BM25 lexical ranking over SQLite FTS5 with namespace filtering, tags, free-form metadata, and JSONL export/import — entirely local, with zero external infrastructure.
      1
      MIT

    • kb-memory

      fish827-08
      A
      license
      A
      quality
      B
      maintenance
      Local-first agent memory & knowledge service (v2.4.4): hybrid retrieval (vector + BM25) + offline CSV/Excel row-level Q&A without LLM; REST + MCP dual protocol (13 tools incl. list/delete documents); memory governance; Python.
      13
      203 PyPI
      5
      Apache 2.0

    • recall-mcp

      jadeleke
      A
      license
      Not graded
      quality
      D
      maintenance
      Persistent, searchable memory for AI agents over the Model Context Protocol, enabling memory storage, full-text search with BM25 ranking, and retrieval across sessions.
      8 npm
      MIT

    • memalyze

      mahaoboy
      A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to store and retrieve self-hosted memories over MCP (stdio or Streamable HTTP) using local embeddings that work fully offline. Writes are redacted before they hit storage and every read is recorded in an exportable, append-only audit log.
      4
      AGPL 3.0

    • NarratorDB

      WilliamJnsson
      A
      license
      Not graded
      quality
      D
      maintenance
      Local-first long-term memory database for AI systems, providing SQLite FTS5/BM25 retrieval and optional SentenceTransformer embeddings via MCP server.
      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

    A3.7/5.0

    Scored across 11 tools

    Disambiguation4/5

    Each tool targets a distinct operation (ingest, search, recall, delete, index management), so selection is mostly clear. The search/recall and ingest/ingest_file pairs are related but descriptions differentiate candidate-root listing versus evidence retrieval and raw-text versus cursor-tracked file ingestion.

    Naming Consistency4/5

    All tools share the vmn_ prefix and most use an imperative verb (recall, ingest, delete, rebuild, sync), which is easy to predict. vmn_stats and vmn_index_status break the verb-first pattern by using noun phrases, but this is a minor inconsistency.

    Tool Count5/5

    Eleven tools is a reasonable size for a memory-vault server and every tool addresses a concrete function: storage, retrieval, deletion, stats, index health, and external sync. It avoids both bloat and minimalism for the stated scope.

    Completeness4/5

    The surface covers the core memory lifecycle: ingest text/files, list, search, recall evidence, inspect metadata, delete, index maintenance, stats, and sync. No critical dead ends appear, though there is no explicit update operation—probably appropriate because memory objects are addressed by immutable hashes.

    Maintenance

    ActivityStale
    ResponsivenessNo recent community issues

    Resources