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.
    40 PyPI
    3
    Apache 2.0

  • neurakeep

    dominiclachance
    A
    license
    Not graded
    quality
    C
    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.
    70 npm
    13
    Apache 2.0

  • kepta

    DamianTodorovic
    F
    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 Facts carry a validity window and a confidence score, so an outdated one is superseded and downweighted rather than deleted, and retrieval fuses BM25, vector similarity and a knowledge graph.
    2
    -

Related Servers

  • memory

    go-ports
    A
    license
    Not graded
    quality
    A
    maintenance
    Provides coding agents with persistent local memory by exposing tools to save, search, and retrieve decisions, bugs, and context as Markdown with hybrid keyword and semantic search.
    4
    MIT

  • 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
    C
    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.
    -

  • ThreadSatchel

    stevej52
    A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI assistants to search and retrieve a locally stored archive of past conversations, notes, and captured Codex events, preserving full original text and provenance in SQLite full-text search. It offers read-only access through two tools, search_memory and get_memory, so context from earlier chats can be reused without pasting it again.
    MIT

  • 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.
    190
    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

A4.2/5.0

Scored across 25 tools

Disambiguation4/5

Domains are cleanly partitioned by prefix (agenda, todo, memory, agent, pheme), and the one genuinely overlapping pair — memory_query vs memory_ask — is explicitly disambiguated (quote the source vs find/re-rank). The main wrinkle is the resonance domain: the entity is read via resonance_list but written/read via position_get and position_update, so the vocabulary shifts mid-domain. Otherwise each tool has a clearly distinct action+resource.

Naming Consistency4/5

Consistent mnemosyne_ prefix with snake_case domain_action naming (agenda_add/list/update/remove, todo_add/list/update, agent_list/collisions/files). Minor deviations: position_* tools stand in for the resonance domain instead of resonance_get/resonance_update, and mnemosyne_about and mnemosyne_git_log carry no resource-action pair. Still readable and predictable overall.

Tool Count4/5

25 tools is at the heavy end, but they distribute across ~10 well-scoped sub-domains (calendar, todo, memory, vault, resonance, agents, Pheme, cockpit, git, diagnostics), and each tool earns its place with no redundant variants. It sits just under the 'too many' threshold but never feels padded.

Completeness4/5

Core lifecycles are complete: calendar and todo both have add/list/update/remove (todo even splits list-shape management into todo_categories), memory has ingest/query/ask, and agents/Pheme/vault have read and write sides. Gaps are minor: no memory update or delete (memories are permanent by design), no vault creation, and git is read-only (log only). An agent can work around all of these.

Maintenance

ActivityActive
ResponsivenessNo issues

Resources