Skip to main content
Glama

Related Servers

Alternatives to RecallNest

No user-submitted related servers found.

    Related Servers

    • A
      license
      A
      quality
      B
      maintenance
      A codebase-memory MCP server for AI coding agents with hybrid semantic+BM25 code search, structural outlines, a work journal, and gaze-and-think deep reasoning over a local LanceDB database.
      9
      1
      Apache 2.0
    • 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
    • F
      license
      Not graded
      quality
      D
      maintenance
      Persistent memory server for AI assistants with semantic search and three-layer context (global, project, personality). Works with MCP-compatible AI tools like Claude Code, Cursor, Continue, Cline, and more.
      1
      -
    • A
      license
      B
      quality
      A
      maintenance
      Persistent memory MCP server that captures coding session context and automatically injects relevant memories into prompts using hybrid search for OpenCode and Claude Code.
      14
      71
      MIT

    TDQS

    A3.6/5.0

    Scored across 30 tools

    Disambiguation2/5

    Multiple tools have overlapping boundaries: store_memory explicitly covers 'reusable pattern' and 'solved case', making it hard to distinguish from store_workflow_pattern and store_case. store_skill also overlaps with workflow patterns, and pairs like distill_memory/brief_memory, list_assets/list_pins, and data_checkup/memory_lint add further ambiguity.

    Naming Consistency4/5

    The vast majority of tools follow a clear verb_noun snake_case pattern such as store_memory, search_memory, and forget_memory. A few outliers like memory_stats, latest_checkpoint, data_checkup, memory_lint, and dream break the pattern, but the overall convention remains predictable.

    Tool Count2/5

    At 30 tools, this is well above the comfortable scope for a memory server and feels over-granular. Many could be consolidated: multiple store_* variants, multiple diagnostic tools, and multiple list/export tools add bulk without clear functional separation.

    Completeness4/5

    The memory lifecycle is broadly covered: store, search, retrieve, forget, import/export, maintenance, and session recovery are all present. The main gap is the lack of a direct update/edit operation for existing memories, though promote_memory and dream partially cover memory mutation.

    Maintenance

    ActivityActive
    ResponsivenessSlow