Skip to main content
Glama
Newmannn91

MemDrive

by Newmannn91
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to MemDrive

No user-submitted related servers found.

    Related Servers

    • 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.
      219
      MIT

    • AIBrain

      NitishKashyapR
      A
      license
      Not graded
      quality
      B
      maintenance
      A personal, offline-first memory for AI assistants that enables them to read, search, and write to a shared folder of Markdown files, so they all remember you without needing a cloud.
      1
      MIT

    • mor

      laat
      A
      license
      Not graded
      quality
      A
      maintenance
      Enables AI assistants to search, read, create, update, and remove personal markdown notes stored locally, providing persistent memory across sessions.
      84 npm
      2
      MIT

    • tua

      Tuacircles
      A
      license
      A
      quality
      B
      maintenance
      Enables saving, searching, retrieving, linking and importing AI work as plain markdown files with automatic provenance in a local folder the user owns. Runs entirely on the user's machine with no account, key or network calls, and never deletes anything.
      11
      AGPL 3.0

    • mcp-ltm

      kvas-it
      A
      license
      Not graded
      quality
      D
      maintenance
      Provides persistent long-term memory for AI assistants with tag-based retrieval, wiki-style linking, and source references, storing memories as markdown files with SQLite index.
      1
      MIT
    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

    A4.2/5.0

    Scored across 6 tools

    Disambiguation5/5

    Each tool maps to a distinct operation: browsing (list_directory), recursive lookup (search_files), write (save_file), read (read_file), and two explicit OS-side actions (open_image, open_containing_folder). The read_file vs open_image vs open_containing_folder boundary is spelled out in the descriptions ('returned to the model' vs 'opens a viewer window'), so misselection is unlikely.

    Naming Consistency5/5

    All six tools follow a strict snake_case verb_noun pattern: list_directory, search_files, save_file, read_file, open_image, open_containing_folder. Verbs are accurate and never clash (no duplicate verbs across the set).

    Tool Count5/5

    Six tools is well-scoped for a sandboxed file/memory library: one per core operation plus two narrowly gated OS-integration tools. Nothing feels redundant or padded.

    Completeness3/5

    Read, write (new/overwrite/append), list, and search are covered, but there is no delete, rename, or move operation — agents cannot clean up or reorganize the library, a likely dead end for memory-management workflows. The surface is usable but missing lifecycle operations.

    Maintenance

    ActivityMaintained
    ResponsivenessNo issues

    Resources