Skip to main content
Glama
sleepunit-agents

loom

by sleepunit-agents
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to loom

No user-submitted related servers found.

    Related Servers

    • HippoDid MCP Server

      SameThoughts
      A
      license
      Not graded
      quality
      C
      maintenance
      Provides persistent, cloud-based memory for AI agents, letting them remember preferences, skills, and decisions across sessions via an MCP-compatible interface.
      Apache 2.0

    • Munnin

      alvseek
      A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents to maintain a persistent identity and structured memory—including reasoning patterns, episodic history, and knowledge—while exposing procedures for managing that memory over MCP.
      Apache 2.0
    • 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

    • 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.
      837
      MIT
    Deploy Server
    RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

    TDQS

    A4/5.0

    Scored across 32 tools

    Disambiguation4/5

    Most tools separate cleanly by store (memory vs knowledge) and lifecycle stage (propose/ratify/archive/restore). The nearest overlaps are memory recall vs find_similar, knowledge_merge vs knowledge_supersede, and harness_init vs harness_describe, but their descriptions define distinct workflows. Overall an agent can usually tell them apart.

    Naming Consistency4/5

    The server is strongly prefixed per subsystem (memory_, knowledge_, harness_) and uses consistent verb forms within each family. Deviations such as bare `update` alongside `update_identity`, noun-style `identity`/`dossier`, and `episodes`/`find_similar` are minor and readable. The convention is consistent enough to predict tool behavior.

    Tool Count2/5

    32 tools is well above the 25+ threshold and will tax an agent's selection even though every tool has a real purpose. The four subsystems (identity, memory, knowledge, harness) justify much of the count, but it still feels heavy for a single MCP surface. Consolidating rarely used maintenance operations would help.

    Completeness5/5

    The memory subsystem has full lifecycle coverage—create, read, update, delete, archive, restore, audit, prune—plus a proposal/ratification workflow. The knowledge store similarly covers write, recall, move, merge, supersede, purge, verify, and history. Harness and identity are thinner but sufficient for their roles, so no major dead ends exist.

    Maintenance

    ActivityMaintained
    ResponsivenessUnresponsive

    Resources