Skip to main content
Glama
Lyellr88

marm-memory

by Lyellr88
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python

Related Servers

Alternatives to marm-memory

No user-submitted related servers found.

    Related Servers

    • Cortex OS

      qi-mouren
      A
      license
      Not graded
      quality
      C
      maintenance
      MCP server that provides AI agents with persistent memory, cross-agent sharing, and context management, enabling them to remember conversations, track complex tasks, and evolve skills across tools.
      2
      MIT

    • memento-mcp-server

      jee1
      A
      license
      Not graded
      quality
      A
      maintenance
      Provides AI agents with persistent, human-like memory infrastructure via MCP, enabling them to store, search, summarize, and forget episodic, semantic, procedural, and working memories across sessions.
      423 npm
      MIT

    • AgentRecall

      Goldentrii
      A
      license
      A
      quality
      A
      maintenance
      MCP server for persistent, compounding memory that automatically captures corrections and insights across AI sessions, enabling agents to learn and improve over time.
      5
      371
      MIT

    • memry

      mrtheroi
      A
      license
      Not graded
      quality
      A
      maintenance
      Gives AI coding agents a persistent memory that carries across sessions and projects, letting them save and search decisions, bug fixes, and discoveries through MCP tools. Each new session loads the recent memories of the current project so agents resume with the same context instead of re-explaining it.
      5
      MIT
    • Memory Crystal MCP Server by memorycrystal

      Memory Crystal MCP Serverofficial

      memorycrystal
      A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to maintain persistent memory across sessions by capturing conversations, extracting durable knowledge, and injecting relevant context, supporting various MCP-compatible platforms.
      12
      MIT

    • marrow

      aryawidjaja
      A
      license
      Not graded
      quality
      A
      maintenance
      Provides persistent, shared memory for AI agents via MCP, enabling retrieval of relevant memories instead of loading entire context. Allows agents across projects, machines, and tools to share a single auditable, markdown-native brain.
      3
      AGPL 3.0
    Deploy Server
    Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

    TDQS

    A4/5.0

    Scored across 16 tools

    Disambiguation4/5

    Most tools have distinct purposes, and the descriptions actively steer choice (marm_code_context explicitly says to prefer it over marm_code_lookup). However, there is real adjacency among the retrieval tools (marm_smart_recall vs marm_concept_recall vs marm_code_context vs marm_code_lookup) and between note-keeping tools (marm_log_entry vs marm_notebook) that could cause occasional misselection.

    Naming Consistency4/5

    All 16 tools share a consistent marm_ prefix with snake_case and clear domain sub-prefixes (log_, graph_, code_, concept_). Minor deviation: several tools use bare nouns (marm_compaction, marm_notebook, marm_summary) rather than verb_noun, but the schema is still predictable and readable.

    Tool Count4/5

    16 tools is slightly heavy but justified: the server covers two coherent subsystems (memory store and code/concept graph), each with a handful of operations. No tool feels redundant enough to cut, though the surface leans toward the upper end of comfortable.

    Completeness4/5

    Coverage is broad: memory write/recall/distill/compaction, log and notebook lifecycle, plus a full code-graph set (index, lookup, trace, architecture, impact) and concept build/recall. Deletion exists, but there is no explicit memory update/edit or pruning operation, a minor gap agents can work around via distill/compaction.

    Maintenance

    ActivityActive
    ResponsivenessWithin a week

    Resources