Skip to main content
Glama
Mnemosyne-OS

Mnemosyne OS

by Mnemosyne-OS
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to Mnemosyne OS

  • auxly-memory-cli

    Tzamun-Arabia-IT-Co
    A
    license
    Not graded
    quality
    A
    maintenance
    Local-first, file-based memory layer for AI agents — one shared Markdown vault across Claude, Codex, Gemini, Cursor and any MCP client. Provides read/write memory tools with an audit trail, per-agent trust levels, and Git sync; no cloud and no lock-in.
    2
    MIT

  • Talamus

    ampres-ai
    A
    license
    Not graded
    quality
    A
    maintenance
    Local-first, source-grounded memory for AI agents, with citations, bitemporal history, review-gated corrections, and MCP tools for search and recall.
    3
    Apache 2.0

  • neurakeep

    dominiclachance
    A
    license
    Not graded
    quality
    B
    maintenance
    Provides a local-first, source-cited memory layer for AI agents, with MCP tools to search, read, explain sources, and propose/apply memory updates.
    23 npm
    6
    Apache 2.0

  • kepta

    DamianTodorovic
    A
    license
    Not graded
    quality
    A
    maintenance
    Local memory for AI agents in one SQLite file on your own machine. Facts carry a validity window and a confidence score, so an outdated one is superseded and downweighted rather than deleted, and retrieval fuses BM25, vector similarity and a knowledge graph.
    3
    MIT

Related Servers

  • local-memory-mcp

    mason-yb-zhang
    F
    license
    Not graded
    quality
    C
    maintenance
    Provides AI agents with persistent, local cross-session shared memory by combining vector semantic retrieval with knowledge graph relationships, and supports short/long-term memory management and local backups.
    -

  • Engram Alpha

    lalithbuilds
    A
    license
    B
    quality
    A
    maintenance
    Enables local AI coding agents and web agents to store, retrieve, and search memories using hybrid semantic, lexical, and knowledge-graph ranking with cognitive decay modeling in a local on-device database.
    15
    MIT

  • MemoryAI

    toozuuu
    F
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to automatically capture durable knowledge and retrieve only relevant, token-bounded context from a secure local-first long-term memory, with support for progressive disclosure, snapshots, health diagnostics, and background tasks.
    -

  • Link

    gowtham0992
    A
    license
    Not graded
    quality
    A
    maintenance
    Enables AI agents to capture, structure, remember, and retrieve source-backed memory as local Markdown files, with reviewable writes and no cloud dependency.
    179
    MIT

  • Nexus RAG MCP Server

    kaushikkumarkr
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI agents with long-term memory and retrieval-augmented generation (RAG) capabilities, allowing them to recall past conversations, search local files, and learn user preferences.
    MIT
  • Lore by agentkitai

    Loreofficial

    agentkitai
    A
    license
    B
    quality
    A
    maintenance
    Cross-agent memory server: hybrid (vector + full-text + knowledge-graph) recall, per-user private/shared visibility, write-side secret/PII redaction, and as-of-date bi-temporal fact queries. Auto-injection hooks for Claude Code / Cursor / Codex; self-hostable on PostgreSQL or SQLite.
    46
    8
    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

A3.9/5.0

Scored across 25 tools

Disambiguation4/5

Most tools map to a distinct domain and action, and the long descriptions carefully separate mnemosyne_ask from mnemosyne_query and pheme_watch from pheme_radar. The main risk is mnemosyne_todo_list vs mnemosyne_todo_lists, whose singular/plural names point at two different operations (reading tasks vs managing list shapes), so one pair could still trip up an agent.

Naming Consistency3/5

All tools share the mnemosyne_ prefix, but the action-placement pattern is mixed: query/ask/ingest are bare verbs, get_position/update_position are verb_noun, while todo_add/agenda_update are noun_verb. This is readable but not predictable, and mnemosyne_todo_list versus mnemosyne_todo_lists is an especially confusing near pair.

Tool Count3/5

25 tools is at the heavy end and spans many subsystems—memory, resonances, pheme, todo, agenda, cockpit, and agent monitoring—so the count feels more like an OS surface than a focused MCP. Each tool is individually justified, but the overall set is borderline for agent selection and would benefit from consolidation or namespacing.

Completeness3/5

The todo and agenda domains have full add/read/update/remove coverage, and agent-collision checks fill real gaps. However, the core memory domain only offers ingest plus query/ask, with no explicit update or delete/forget path, which is a notable lifecycle gap even if permanence is intentional.

Maintenance

ActivityNo data
ResponsivenessNo issues

Resources