Skip to main content
Glama
purmemo-ai

pūrmemo

Official
by purmemo-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Related Servers

Alternatives to pūrmemo

No user-submitted related servers found.

    Related Servers

    • SAE4U Memory by Simple4uhq

      SAE4U Memoryofficial

      Simple4uhq
      A
      license
      A
      quality
      C
      maintenance
      Provides persistent memory for Claude with hierarchical categorization, cross-corpus recall, session journals, and customizable persona, enabling memory continuity across sessions.
      7
      MIT

    • memcp

      moshez
      -
      license
      Not graded
      quality
      D
      maintenance
      Provides persistent memory for AI assistants like Claude, storing and retrieving information across conversations using a local SQLite database.
      -

    • agent-mem0

      ccperdst-lab
      A
      license
      Not graded
      quality
      D
      maintenance
      Provides persistent cross-session memory for Claude Code, enabling it to remember user preferences, decisions, and project context across new sessions.
      Apache 2.0

    • CyberMem

      mikhailkogan17
      F
      license
      Not graded
      quality
      C
      maintenance
      Enables AI tools like Claude and Cursor to share persistent memory across sessions.
      5
      -

    • Claude Memory Server

      xiy
      A
      license
      Not graded
      quality
      D
      maintenance
      Provides long-term memory capabilities for Claude through persistent storage and full-text search of context across conversations. Enables storing, searching, and managing memories organized by categories like facts, preferences, projects, and goals.
      8 npm
      1
      MIT
    • BaseGrid MCP Server by basegridio

      BaseGrid MCP Serverofficial

      basegridio
      F
      license
      Not graded
      quality
      D
      maintenance
      Gives Claude Desktop, Cursor, Cline, and other MCP-compatible AI tools persistent memory, enabling them to store and recall information seamlessly across sessions.
      9 npm
      1
      -
    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

    A4.2/5.0

    Scored across 29 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose, from saving conversations to recalling memories, managing tasks, handling errors, and sharing public content. Even similar-sounding tools like get_investigations vs get_acknowledged_errors are precisely scoped (investigation results vs errors to investigate). The snapshot workflow tools (snapshot, snapshot_sources, save_snapshot, accept_snapshot) follow a clear pipeline with distinct roles.

    Naming Consistency5/5

    All tools use consistent snake_case with a verb_noun pattern (e.g., get_next_task, save_artifact, recall_public). Even standalone verbs like 'snapshot' and 'commit' fit the imperative style. There are no mixed conventions or unpredictable patterns.

    Tool Count3/5

    29 tools is above the typical well-scoped range and feels heavy, but it's justified by the breadth of the server's domain (memory, tasks, snapshots, workflows, errors, public sharing). Still, the sheer number may overwhelm agents and increase misselection risk.

    Completeness4/5

    The tool surface covers core CRUD-like operations for memories (save, recall, get details, share), artifacts (save, list), snapshots (generate, save, accept, get), tasks (get next, complete), and errors (fetch, save investigation). Minor gaps exist like no explicit delete for memories or artifacts, but these are likely intentional (insert-only design) and agents can work around them.

    Maintenance

    ActivityActive
    ResponsivenessNo issues

    Resources