Skip to main content
Glama
owrede

vault-memory

by owrede
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Related Servers

Alternatives to vault-memory

No user-submitted related servers found.

    Related Servers

    • Brainstem

      DarkCodePE
      A
      license
      Not graded
      quality
      D
      maintenance
      Local-first knowledge backend for AI agents that connects MCP hosts to an Obsidian-compatible vault with indexed retrieval, token-budgeted memory recall, and secure ingestion.
      1
      MIT

    • exomem

      Artexis10
      A
      license
      Not graded
      quality
      C
      maintenance
      Durable memory with sources, proof, history, and review for MCP-capable agents. It turns a Markdown/Obsidian vault into a local knowledge substrate, enabling agents to store, search, and retrieve governed knowledge.
      16,405 PyPI
      9
      AGPL 3.0

    • epsilongraph

      silverenternal
      A
      license
      A
      quality
      B
      maintenance
      Exposes a typed, provenance-aware knowledge graph over an Obsidian vault to coding agents over MCP, so they can trace what grounds a claim, compute which other notes a change makes wrong, surface contradictions and admitted gaps, and assemble a task-specific token-budgeted subset of the vault. Indexing, retrieval, and impact analysis run with zero third-party runtime dependencies beyond the Python standard library.
      10
      MIT
    • cog-brain by cog-sh

      cog-brainofficial

      cog-sh
      A
      license
      A
      quality
      B
      maintenance
      Turns a plain-Markdown Obsidian vault into a second brain that any MCP-speaking coding agent can search, read, extend, and maintain, using swappable SQLite, Qdrant, or markdown memory backends with automatic re-indexing and wiki-link graph navigation. Exposes read, write, and index tools plus an operator CLI for health, linting, and graph export.
      12
      MIT

    • ragvault

      maxrotemberg04-spec
      A
      license
      Not graded
      quality
      D
      maintenance
      MCP server for local-first RAG over Obsidian vaults, enabling AI agents to search and ask questions about notes with grounded citations.
      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

    B3.4/5.0

    Scored across 37 tools

    Disambiguation3/5

    Several search/retrieval tools overlap (search_semantic, search_text, search_hybrid, search, search_sections, fetch, recall) and five deprecated tools parallel MCP resources, causing potential misselection despite detailed descriptions differentiating them.

    Naming Consistency4/5

    All tools use lowercase snake_case, but the pattern is not strictly verb_noun: several are single verbs (recall, expand, cluster, fetch, search) or nouns (audit_log, index_runs). Consistent style with minor deviations.

    Tool Count2/5

    37 tools is too many for the scope, including five deprecated aliases, multiple overlapping search adapters, and several graph/retrieval functions. The surface is heavy and hard to navigate, exceeding the 25+ threshold for 'too many'.

    Completeness4/5

    Covers notes CRUD, multiple search modes, memory sinks, briefs, contracts, indexing, audit, and graph retrieval. Missing a body-only update or rename/move operation, but overall the lifecycle is well represented.

    Maintenance

    ActivityMaintained
    ResponsivenessUnresponsive

    Resources