Skip to main content
Glama
Sign In
Neotoma

Neotoma

by markmhendrickson
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

Related Servers

Alternatives to Neotoma

No user-submitted related servers found.

    Related Servers

    • nuzo-memory

      fabionfsc
      A
      license
      Not graded
      quality
      F
      maintenance
      Local-first, auditable memory for AI agents. Provides durable context for MCP hosts with SQLite storage, CLI, and MCP tools for memory management.
      2
      Apache 2.0

    • CP Memory

      CJhuochai
      A
      license
      C
      quality
      B
      maintenance
      Local-first, governable long-term memory for AI agents. Provides SQLite-backed storage, cross-session recall, and traceable memory corrections through a standard MCP interface.
      40
      36 PyPI
      1
      MIT

    • midas-memory-mcp

      vornicx
      A
      license
      A
      quality
      C
      maintenance
      Local-first, source-traceable memory for AI agents — no LLM at ingest, $0 per message, zero data egress. Gives Claude Code, Cursor, and any MCP client one shared persistent memory with semantic recall, belief revision, selective forgetting, and a provenance guard that blocks acting on stale or unconfirmed memories.
      23
      14
      MIT

    • forgemind-brain

      sleepingfreak94
      A
      license
      Not graded
      quality
      B
      maintenance
      Gives AI coding agents a private local SQLite memory over MCP so Claude Code, Cursor, and Codex can share approved project lessons, conventions, decisions, and session history without cloud services or telemetry.
      MIT

    • Mneme Memory MCP

      ethos-zero
      A
      license
      A
      quality
      B
      maintenance
      A local-first shared memory layer for MCP-aware agents like Claude, Codex, and Hermes, enabling persistent memory across chats and clients via Markdown files and SQLite FTS.
      6
      2
      MIT

    • Mnemosyne

      28naem-del
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI agents to maintain auditable, local-first long-term memory in a single SQLite file, preserving source evidence and retiring dependent memories when sources are corrected so Claude Code, Cursor, and Codex start from current recorded evidence.
      158 npm
      159
      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

    C2.8/5.0

    Scored across 67 tools

    Disambiguation3/5

    Many tools overlap in purpose: retrieval is split across retrieve_entities, retrieve_entity_by_identifier, identify_entity_by_signals, retrieve_entity_snapshot, retrieve_related_entities, and retrieve_graph_neighborhood; writing/correcting across store, correct, correct_transaction, and patch_array_item; and generic vs issue-specific submission across submit_entity, submit_issue, add_entity_message, and add_issue_message. Detailed descriptions help, but the boundaries still require careful reading and invite misselection.

    Naming Consistency4/5

    Most tools follow a snake_case verb_noun pattern (list_observations, retrieve_entity_snapshot, create_relationship, delete_entity), with reasonable variety among verbs like get, list, and retrieve. Minor deviations include single-word imperative tools (store, correct, subscribe) and noun-first names (neotoma_turn_summary, npm_check_update, health_check_snapshots), but the overall convention remains readable and predictable.

    Tool Count1/5

    With 67 tools, the surface is far beyond the typical 3-15 range and qualifies as an extreme mismatch according to the rubric. Even for a complex knowledge-graph platform, this volume creates selection overhead and makes it hard for an agent to hold the whole toolset in working memory.

    Completeness4/5

    The server covers a broad lifecycle: storing, correcting, deleting, and restoring entities; managing schemas, relationships, observations, provenance, submissions, subscriptions, peers, bundles, and issues. Some gaps remain, such as resolve_sync_conflict being an explicit stub and no direct update_relationship operation, but core workflows are otherwise well supported.

    Maintenance

    ActivityActive
    ResponsivenessSyncing

    Resources