Skip to main content
Glama
VonderVuflya

Yggdrasil

by VonderVuflya
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Related Servers

Alternatives to Yggdrasil

Related Servers

  • Leteo

    asanabrial
    A
    license
    A
    quality
    A
    maintenance
    Persistent memory for AI coding agents, storing decisions, bug fixes, conventions, and discoveries in a local SQLite database and automatically recalling them when relevant. Works with Claude Code, Codex, Cursor, Gemini CLI, and other MCP-compatible agents.
    22
    2
    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.
    -

  • umo-memory

    UmoLab
    A
    license
    Not graded
    quality
    B
    maintenance
    Persistent memory for AI coding agents that stores and recalls preferences, decisions, and conventions via semantic similarity, with zero cloud dependencies and plug-and-play MCP integration for Claude Code.
    Apache 2.0

  • agentmem

    Thezenmonster
    A
    license
    A
    quality
    D
    maintenance
    Governed memory for coding agents with trust lifecycle, conflict detection, staleness tracking, and health scoring. SQLite + FTS5, zero infrastructure. Works with Claude Code, Cursor, Codex, Windsurf.
    13
    3
    MIT

  • pathmark

    hacksurvivor
    A
    license
    B
    quality
    A
    maintenance
    Local-first memory for MCP clients. It provides shared durable memory without requiring hosted accounts, vector databases, or API keys, and works with Codex, Claude Code, Cursor, and other MCP clients.
    25
    222 npm
    3
    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

A4.4/5.0

Scored across 6 tools

Disambiguation4/5

The tools are largely distinct: health, remember, and materialize are clearly separate, while recall, bootstrap, and search all retrieve memories but are differentiated by scope (cross-project vs. project context vs. targeted query). Descriptions include explicit guidance on when to use each, reducing but not eliminating the chance of confusion.

Naming Consistency4/5

All tools share the consistent 'ygg_' prefix and use lowercase snake_case. Most follow a verb-based pattern (recall, bootstrap, search, remember, materialize), though 'ygg_health' is a noun rather than a verb, creating a minor inconsistency.

Tool Count5/5

Six tools is a well-scoped count for a memory server. Each tool earns its place: health monitoring, cross-project recall, project priming, targeted search, memory persistence, and file export. There are no redundant or filler tools.

Completeness3/5

The server covers create, read/retrieve, and export operations well, but lacks explicit update and delete capabilities for stored memories. Automatic near-duplicate merging partially addresses updates, but there is no clear way to edit or remove a stale or incorrect memory, which is a notable lifecycle gap.

Maintenance

ActivitySlowing
ResponsivenessNo issues

Resources