Skip to main content
Glama
fastmcp-me

Mnemex

by fastmcp-me
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to Mnemex

No user-submitted related servers found.

    Related Servers

    • Mnemex

      prefrontal-systems
      A
      license
      A
      quality
      C
      maintenance
      Provides human-like memory dynamics for AI assistants where memories naturally fade over time unless reinforced through use, mimicking the Ebbinghaus forgetting curve. Enables automatic saving, searching, and management of contextual information with temporal decay algorithms.
      11
      36
      AGPL 3.0
    • JauMemory MCP Server by Jau-app

      JauMemory MCP Serverofficial

      Jau-app
      A
      license
      A
      quality
      C
      maintenance
      Provides persistent memory capabilities for AI assistants, enabling storage, recall, and analysis of information across conversations with intelligent memory management.
      25
      28 npm
      MIT

    • agent-memory

      tahasiddiquii
      A
      license
      Not graded
      quality
      C
      maintenance
      Provides long-term memory for AI agents with per-user scoped recall, ranking by relevance, recency, and importance, consolidation of repeated events, and automatic forgetting.
      MIT

    • recall

      andrewhomeyer
      A
      license
      A
      quality
      D
      maintenance
      Gives AI assistants a persistent memory across conversations, allowing them to remember user preferences, notes, and facts between chats.
      6
      8 npm
      MIT

    • hippmem-mcp

      hippmem
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI assistants to have persistent associative memory across sessions by storing memories, discovering associations, and retrieving them via spreading activation.
      Apache 2.0
    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

    A4.1/5.0

    Scored across 13 tools

    Disambiguation4/5

    Tools are mostly distinct, with clear separation between search, retrieval, mutation, and maintenance operations. The main potential confusion is between search_memory and search_unified, and between cluster_memories and consolidate_memories, but descriptions clarify their different scopes.

    Naming Consistency4/5

    Nearly all tools follow a consistent verb_noun snake_case pattern (e.g., save_memory, search_memory, consolidate_memories). The abbreviation 'gc' for garbage collection is the only notable deviation, making the naming slightly inconsistent.

    Tool Count5/5

    The 13 tools are well-scoped for a memory server, covering creation, retrieval, search, maintenance, relations, and metrics. Each tool has a clear role without redundancy or excessive fragmentation.

    Completeness4/5

    The tool set covers the core memory lifecycle: creation (save_memory, create_relation), retrieval (open_memories, search_memory, read_graph), reinforcement (touch_memory), consolidation (cluster_memories, consolidate_memories), promotion (promote_memory), and deletion (gc). Minor gaps include lack of direct memory content update and relation deletion, but these are workable via existing tools.

    Resources