Skip to main content
Glama
oleksiijko

io.github.oleksiijko/pmb-ai

by oleksiijko
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to io.github.oleksiijko/pmb-ai

No user-submitted related servers found.

    Related Servers

    • Thoth-Mem

      EremesNG
      A
      license
      A
      quality
      A
      maintenance
      Persistent memory for AI coding agents, storing learned architecture decisions, patterns, and bug fixes in a local SQLite database with full-text search, enabling agents to recall information across sessions.
      6
      90 npm
      1
      MIT

    • code-recall

      AbianS
      A
      license
      Not graded
      quality
      C
      maintenance
      Gives AI coding agents persistent memory by storing observations, decisions, and learnings in a local SQLite database with vector search, full-text search, and a rules engine.
      4
      MIT

    • MCP Vector Memory

      vertexhub-ai
      A
      license
      Not graded
      quality
      Not graded
      maintenance
      Provides AI coding agents with persistent, long-term memory through local semantic search and SQLite storage. It enables agents to save and retrieve architectural decisions or project context across different conversation sessions without requiring cloud services.
      MIT
    • Memryzed by memryzed

      Memryzedofficial

      memryzed
      F
      license
      Not graded
      quality
      C
      maintenance
      Local-first cross-agent memory for AI coding agents. Persistent, shared memory over MCP — what you tell one agent can be recalled by another — with all data stored in a single local SQLite file, no cloud and no API keys.
      -

    • rekal

      janbjorge
      A
      license
      Not graded
      quality
      B
      maintenance
      Provides long-term memory for LLMs via local SQLite storage with hybrid search (BM25, vectors, recency decay), enabling AI coding agents to persist and recall memories across sessions without cloud or API keys.
      53
      MIT
    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

    A3.7/5.0

    Scored across 10 tools

    Disambiguation3/5

    Multiple tools surface project context and lessons (prepare, project_overview, recall, find_lessons, session_brief), and their triggers overlap. Descriptions help clarify but an agent could misselect, especially between prepare and project_overview.

    Naming Consistency3/5

    Tool names mix verb_noun patterns (record_keyed_fact, find_lessons, update_goal, list_goals) with noun-only names (prepare, session_brief, project_overview) and bare verbs (recall). Inconsistent style reduces predictability.

    Tool Count5/5

    10 tools is a reasonable scope for a personal memory/project management server, balancing specialized functions without excessive granularity.

    Completeness3/5

    The surface covers recording, recalling, goal listing/updating, and project context, but lacks explicit delete/archive operations for memories or goals, and goal creation is only available via the batch API. This leaves some dead ends for long-term maintenance.

    Maintenance

    ActivityMaintained
    ResponsivenessUnresponsive

    Resources