Hivemind

io.github.hiveforge-shPublished by GitHub account hiveforge-shv3.6.3Updated Oct 24, 2026

MCP server for Obsidian vaults - AI tools with consistent canonical context. Local-first.

VerifiedSTDIODesktop onlyFiles & StorageKnowledge & Memory

Overview

AI-generated overview

Local MCP server that gives AI assistants structured, read-oriented access to an Obsidian vault so answers stay grounded in the user's own notes.

What you can do
Query vault notes and entities so the assistant references actual characters, events, and concepts instead of inventing details, across templates such as worldbuilding, research, people management, and software architecture. Follow entity relationships and timelines defined in markdown, YAML frontmatter, and wikilinks. Work with the canon workflow, where content is tracked as draft, pending, or approved. The manifest lists no individual tools, so exact operations are not documented here.
When to use it
Useful when you keep a structured Obsidian vault and want an AI assistant to answer from your established canon rather than hallucinating, for example when writing fiction, organizing research, tracking team context, or documenting architecture decisions.
Requirements
Runs as a local process via the npm package over stdio. Requires the HIVEMIND_VAULT_PATH environment variable pointing to your Obsidian vault directory, and optionally HIVEMIND_CONFIG_PATH for a config file. The README recommends installing the Obsidian plugin first and following its MCP setup guide.
Before you install
The server reads your vault, so point HIVEMIND_VAULT_PATH only at a directory you are comfortable exposing to the assistant. The canon workflow can change note status, so review any writes the assistant proposes. Data stays local per the README, but confirm what your AI client sends to its provider.

Installation

In SourceWeft

  1. Open Hivemind in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

[Hivemind for Obsidian]

Hivemind for Obsidian

[License: MIT]

Your canon is the source of truth. AI stays inside the lines.

Why Hivemind?

When building fictional worlds — whether you're writing a novel, designing a game, or running an RPG campaign — AI tools can be powerful collaborators. But they hallucinate. Ask your AI assistant about a character you created last week, and it might invent details that contradict your established canon.

Hivemind solves this by giving AI tools structured access to your Obsidian vault. Think of it as an AI Firewall: your worldbuilding notes become a truth anchor that keeps AI grounded in facts you control. Ask about a character, and the AI reads your actual notes — not a hallucinated version. Query a timeline, and it references your established events — not invented dates.

Beyond AI integration, Hivemind provides powerful visualization tools:

  • Timeline View — See your story's events laid out chronologically
  • Graph View — Explore relationships between characters, locations, factions, and more
  • Canon Workflow — Track which content is approved, in review, or still draft

Hivemind is built for worldbuilders, but the same principles apply to research vaults, people management, software architecture — anywhere you need AI to respect your established knowledge.

Features

  • Timeline View — Visualize events chronologically with filtering and search
  • Graph View — Explore entity relationships with interactive visualization
  • AI Integration — MCP-compatible server for Claude, GitHub Copilot, and other AI tools
  • Pluggable Templates — Built-in templates for worldbuilding, research, people management, and more
  • Canon Workflow — Draft → Pending → Canon approval system with consistency validation
  • Obsidian Native — Works with standard markdown, YAML frontmatter, and wikilinks
  • Local-First — Your data stays on your machine

Built-in Templates

TemplateUse CaseEntity Types
WorldbuildingFiction writers, game designers, RPG creatorsCharacters, Locations, Events, Factions, Lore, Assets
ResearchAcademics, knowledge workersPapers, Citations, Concepts, Notes
People ManagementManagers, team leadsPeople, Goals, Teams, 1:1 Meetings
Software ArchitectureEngineers, architectsSystems, Components, ADRs, Constraints

Define your own custom entity types via config — no code required. See CONTRIBUTING_TEMPLATES.md for details.

Installation

Obsidian Plugin (Recommended)

  1. Open Obsidian Settings
  2. Go to Community plugins → Browse
  3. Search for "Hivemind"
  4. Click Install, then Enable

Manual Installation

  1. Download the latest release from GitHub Releases
  2. Extract to your vault's .obsidian/plugins/hivemind directory
  3. Reload Obsidian and enable the plugin in Settings

AI Integration (Optional)

Want AI tools to query your vault? Set up the MCP server:

MCP Setup Guide →

The guide covers:

  • Claude Desktop configuration (Windows, macOS, Linux)
  • GitHub Copilot configuration
  • Template selection
  • Troubleshooting

Quick Start

  1. Choose a template — Open Hivemind settings in Obsidian and select a template (worldbuilding, research, etc.)

  2. Create entities — Use Obsidian's note creation as usual. Add YAML frontmatter to define entity types:

    yaml
    ---entity_type: charactercanon_status: draft---

  3. Visualize — Open the Timeline view or Graph view from the ribbon icons

  4. Connect to AI — Follow the MCP Setup Guide to let AI tools query your vault

For detailed setup instructions, see docs/SETUP_GUIDE.md.

Screenshots

Timeline View

Coming soon — chronological visualization of events

[Timeline View Placeholder]

Graph View

Coming soon — interactive entity relationship visualization

[Graph View Placeholder]

Use Cases

Worldbuilding:

  • Track characters, locations, and events across your novel
  • AI remembers your character details when helping with dialogue
  • Visualize timeline of your story's key events

Research:

  • Organize papers, citations, and concepts in your field
  • AI references your actual research when answering questions
  • Explore connections between concepts in your knowledge base

People Management:

  • Track team goals, 1:1 meeting notes, and people details
  • AI recalls context from previous meetings when drafting agendas
  • Visualize team relationships and reporting structures

Software Architecture:

  • Document systems, components, and architectural decisions (ADRs)
  • AI references your ADRs when suggesting design patterns
  • Track dependencies between components visually

Documentation

Community

Contributing

We welcome contributions! Please see CONTRIBUTING.md for guidelines.

Important: This project uses Conventional Commits. Commit messages must follow the format:

<type>: <description>
[optional body]

Common types: feat, fix, docs, style, refactor, test, chore

License

MIT — Free for personal and commercial use.

Source: README.md at commit 983ec1d

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v3.6.3LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts