Skip to main content
Glama
donggyun112

keymem

by donggyun112
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to keymem

No user-submitted related servers found.

    Related Servers

    • mnemos

      vishalbanwari26
      A
      license
      A
      quality
      C
      maintenance
      Persistent memory for LLM agents — episodic/semantic/procedural memory, auditable forgetting, and a benchmark proving it actually recalls things days later.
      5
      MIT

    • agent-knowledge

      yucx-go
      A
      license
      A
      quality
      C
      maintenance
      Long-term memory for AI agents. Compiles conversations into a structured knowledge base with Claim/Evidence model, source provenance, append-only timeline, and contradiction detection. Multi-path retrieval (Exact + BM25 + Graph + weighted RRF + reranker) — 96.6% R@5 on LongMemEval-S, zero vector dependencies.
      8
      3
      MIT

    • Logica Mind

      Rovemark
      A
      license
      Not graded
      quality
      D
      maintenance
      Long-term memory for AI agents over MCP — episodic + semantic memory, a temporal knowledge graph, and a dialectic user model, exposed as 32 tools (recall, remember, context, graph, dreaming, peers). Zero dependencies, runs fully offline; leads the LoCoMo benchmark at ~35x fewer LLM calls.
      2
      Apache 2.0
    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

    A4.2/5.0

    Scored across 10 tools

    Disambiguation5/5

    Each tool targets a distinct operation in the memory lifecycle: recall/search, key browsing, key reading, memory reading, saving, confirming, correcting, dismissing, and forgetting. The hierarchical workflow (recall → read_key → read_memory) and the clear separation between content, validity, and key-link management eliminate ambiguity. No two tools appear to do the same thing.

    Naming Consistency4/5

    All names use lower snake_case and are readable, with no mixed casing or cryptic abbreviations. The main deviation is that some tools are bare verbs (recall, correct, dismiss, forget, remember) while others follow verb_noun (read_key, read_memory, browse_keys, confirm_memory, remember_batch), but this remains mostly predictable.

    Tool Count5/5

    Ten tools is well-scoped for a long-term memory server. The set covers discovery, read, write, update, delete, and link-reinforcement without obvious redundancy. Each tool earns its place, and the count stays within the ideal 3–15 range.

    Completeness5/5

    The surface covers full memory lifecycle operations: recall/search, browse, read, remember, remember_batch, confirm, correct, dismiss, and forget. It also handles navigation through keys and memories, validity, and link weakening. No core CRUD or lifecycle operation appears missing for the stated domain.

    Maintenance

    ActivityActive
    ResponsivenessNo issues

    Resources