Skip to main content
Glama

Related Servers

Alternatives to Vigente

No user-submitted related servers found.

    Related Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Gives AI agents governed, provenance-tagged memory where facts are invalidated rather than deleted and every recall result carries validity dates, confidence, and replacement links. Stores memory in a local SQLite file with tools for remembering, recalling, invalidating, and pinning facts, plus policy enforcement and an audit trail.
      103 npm
      3
      Apache 2.0
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to save, recall, and forget persistent memories stored entirely on the local machine in SQLite, using hybrid semantic and keyword search with on-device embeddings, plus spaces and profile context injection.
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to persist facts with tags, sources, and importance in a local SQLite database, retrieve them through hybrid BM25 plus embedding search weighted by retention decay, link or supersede related entries, and review everything in a read-only visual dashboard showing the memory graph and timeline.
      6
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to keep durable long-term memory in a single local SQLite file, ingesting documents, session transcripts and time-bounded facts without any LLM, then serving ranked hybrid keyword-and-vector context, timeline lookups and provenance-aware search over MCP. It also supports temporal queries, shareable compartmentalized memory with trust levels, and verifiable forgetting that proves removed content is gone from every read path.
      Apache 2.0
    • A
      license
      Not graded
      quality
      B
      maintenance
      Local memory for AI agents in one SQLite file on your own machine. Facts carry a validity window and a confidence score, so an outdated one is superseded and downweighted rather than deleted, and retrieval fuses BM25, vector similarity and a knowledge graph.
      4
      Business Source 1.1
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to keep a durable, local-first long-term memory in a single SQLite file, where frequently recalled facts strengthen and unused traces decay, with sleep-time consolidation that merges duplicates and distills episodes into semantic gists. Exposes six tools — remember, recall, context, forget, dream, and stats — so clients can store facts, pull prompt-ready memory blocks, and permanently erase data on request.
      MIT

    TDQS

    A3.8/5.0

    Scored across 6 tools

    Disambiguation4/5

    Each tool maps to a distinct lifecycle step: remember (create), recall (search), forget (hard delete), supersede (version link), history (version trail), list_memories (enumerate). The main soft spot is recall vs list_memories and recall vs history, which both surface stored memories and could be picked interchangeably, though the descriptions clarify the difference (semantic search on current truths vs. chronological listing vs. full version chain).

    Naming Consistency4/5

    Five tools are bare, memorable verbs (remember, recall, forget, supersede) or a bare noun (history), which read consistently as a memory vocabulary. The outlier is list_memories, the only verb_noun compound, but it is still predictable and readable.

    Tool Count5/5

    Six tools is well-scoped for a versioned memory store: one per core operation with no redundant or filler tools. Nothing feels thin, since the supersession model is fully expressible with these six.

    Completeness5/5

    Full lifecycle is covered: create (remember), search/read (recall, list_memories, history), update-by-versioning (supersede, including new_content as an in-place update path), and delete (forget). The supersession model even has an error-recovery path (current_id) and a history view, so agents have no dead ends.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues