Skip to main content
Glama
Patdolitse

Engram

by Patdolitse
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to Engram

Related Servers

  • kimi-memory

    cbuntingde
    A
    license
    Not graded
    quality
    B
    maintenance
    Provides a local-first persistent memory layer for coding assistants, enabling cross-project user preferences, per-project durable and working memory, session archives, and reflective recommendations through MCP tools.
    43 npm
    MIT

  • memex

    kioie
    A
    license
    Not graded
    quality
    C
    maintenance
    Provides long-term local memory for AI coding agents via MCP, enabling persistent recall of preferences and project facts across chat sessions.
    1
    MIT

  • 0f

    zanarellidev
    A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI coding agents to share a persistent local-first memory hub, storing and recalling architectural decisions and context across different tools via MCP, so users can switch assistants without losing context.
    Apache 2.0

  • Mycelia

    kittors
    A
    license
    Not graded
    quality
    B
    maintenance
    Provides a persistent, cross-tool memory layer for AI coding agents via MCP, enabling storage and retrieval of decisions, preferences, and context across different tools and models.
    1 npm
    1
    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

A3.8/5.0

Scored across 19 tools

Disambiguation2/5

Four retrieval tools (get_user_context, get_identity_card, get_resume_brief, get_recall) all return overlapping user-context/knowledge bundles with subtle lifecycle distinctions that an agent could easily confuse, especially at session start. memory_store also overlaps with the three add_* tools. The descriptions cross-reference each other well, but the boundary between 'startup context', 'resume brief', and 'recall surface' remains genuinely fuzzy.

Naming Consistency4/5

The set follows a clean verb_noun snake_case pattern: ten get_* readers, three add_* knowledge writers, plus search_, update_, and save_ verbs. Minor deviations exist — memory_store inverts the order, doctor is a bare noun, and wrap_up_session uses a phrasal verb — but the overall convention is highly predictable.

Tool Count3/5

19 tools sits at the heavy end of the range for a memory server, and the context-retrieval cluster (get_user_context, get_resume_brief, get_recall) shows clear consolidation opportunity. Most tools do serve a legitimate lifecycle function, so it is borderline rather than bloated.

Completeness3/5

Create/read coverage is strong for lessons, decisions, playbooks, identity, and project snapshots, with session lifecycle well handled. However, there is no update or delete surface for knowledge items, making get_knowledge_history a read-only dead end, and extract_session_insights is repeatedly referenced in descriptions but absent from the tool set — a real gap that will cause agent confusion.

Maintenance

ActivityActive
ResponsivenessResponsive

Resources