Search...Search plugins and themes...
⌘K
Sign in
  • Get started
  • Download
  • Pricing
  • Enterprise
  • Account
  • Obsidian
  • Overview
  • Sync
  • Publish
  • Canvas
  • Mobile
  • Web Clipper
  • CLI
  • Learn
  • Help
  • Developers
  • Changelog
  • About
  • Roadmap
  • Blog
  • Resources
  • System status
  • License overview
  • Terms of service
  • Privacy policy
  • Security
  • Community
  • Plugins
  • Themes
  • Discord
  • Forum / 中文论坛
  • Merch store
  • Brand guidelines
Follow us
DiscordTwitterBlueskyThreadsMastodonYouTubeGitHub
© 2026 Obsidian

Brains Sync

BrainsBrains149 downloads

Sync your vault with Brains, the persistent, cross-LLM second brain your AI never had. Pull pages in, edit, and push changes back. One memory for Claude, ChatGPT, and whatever's next.

Add to Obsidian
  • Overview
  • Scorecard
  • Updates6

Bidirectional sync between your Obsidian vault and a Brains wiki instance.

Features

  • Pull from Brains — fetches all wiki pages via the Brains API and writes them into a configurable vault subfolder (brains/ by default).
  • Push to Brains — scans the vault subfolder for markdown files and syncs each one back (updates existing pages, creates new ones).
  • Remote-wins on pull (V1): pulling always overwrites local copies with the server version.
  • Sync log — a sidebar Notice summarises every operation and logs details to the developer console.

Requirements

  • Obsidian ≥ 1.11.4 (desktop and mobile)
  • A Brains account (sign in with Connect to Brains — no manual token needed)

Installation

Manual (developer install)

  1. Build the plugin:
    npm install
    npm run build
    
  2. Copy main.js and manifest.json to your vault's plugin folder:
    <vault>/.obsidian/plugins/brains-sync/
    
  3. Enable the plugin in Settings → Community Plugins.

Community Plugin Registry

Once listed, search for Brains Sync in Settings → Community Plugins → Browse.

Configuration

Open Settings → Brains Sync:

Field Description Default
Brains instance URL Base URL of your Brains deployment https://lets.usebrains.app
Account Connect to Brains — one-click OAuth2 sign-in —
Vault folder Subfolder where pages are synced brains
API token (Advanced) Optional Personal Access Token fallback for self-hosters —

Click Connect to Brains to sign in: your browser opens the Brains login, you approve, and Obsidian receives the access token automatically. Tokens (and any fallback PAT) are stored via Obsidian's SecretStorage and are never written to data.json or the vault.

Usage

Pull from Brains

  • Click the download ribbon icon, or
  • Open the Command Palette (Cmd/Ctrl+P) → Brains Sync: Pull from Brains

The first pull bootstraps from GET /api/v1/export/download. Later pulls use GET /api/v1/pages (name + revision index) and fetch only changed pages, writing them to <vault-folder>/<page-name>.md.

Push to Brains

  • Open the Command Palette → Brains Sync: Push to Brains

Every .md file under <vault-folder>/ is read and synced back: existing pages are updated with a full-rewrite PUT /api/v1/page, and new pages are created with POST /api/v1/pages.

Auth

Sign-in uses OAuth 2.0 with PKCE (authorization-code flow). Click Connect to Brains, approve in the browser, and the plugin exchanges the code for an access token + refresh token; the access token is refreshed automatically before it expires. All API requests send Authorization: Bearer <token>.

For self-hosted servers or non-OAuth setups, an optional Personal Access Token can be entered under Settings → Brains Sync → Advanced.

License

MIT — see LICENSE.

HealthExcellent
ReviewPassed
About
Most AI memory is trapped inside one app and wiped when the chat ends. Brains (https://usebrains.app) keeps yours. Interlinked markdown pages, structured so an LLM can navigate them the way you do, not a pile of chat logs. It lives outside any single AI, so the same knowledge shows up in Claude, ChatGPT, and whatever you move to next. Your agents write back to it, not just read, and it stays in plain markdown you can export any time. This plugin makes Obsidian a window into that brain. Pull your whole knowledge base in with its links intact, edit the way you already work, and push changes back. Auto-sync runs in the background, incremental pull grabs only what changed, and OAuth means no keys to copy. Desktop and mobile. Shape your brain with brains-skills, a community library of filing systems, note templates, and agents you point your AI at. github.com/brainsforai/brains-skills Note to self: Cross platform ai workflows are now just a voice memo away.
AIBackupThinking
Details
Payments
Optional
Current version
1.1.2
Last updated
2 months ago
Created
2 months ago
Updates
6 releases
Downloads
149
Compatible with
Obsidian 1.11.4+
Platforms
Desktop, Mobile
License
MIT
Report bugRequest featureReport plugin
Payments
More storage than 50 pages (100 during beta!). Priority Support.
Author
BrainsBrainsbrainsforai
GitHubbrainsforai
  1. Community
  2. Plugins
  3. AI
  4. Brains Sync

Related plugins

Vault Operator

Real AI agent for your vault. Coworker, Copilot & thinking partner, that maintains your memory & knowledge, adapts to your workflows, uses plugins, skills & tools with full safety controls. BYOK & MCP

Claudian

Embeds Claude Code/Codex and other local Agents as AI collaborators in your vault.

Copilot

Your AI Copilot: Chat with Your Second Brain, Learn Faster, Work Smarter.

Fast Note Sync

Real-time sync of your vaults across server, mobile, and web; shareable with anyone; supports REST and MCP integrations to build your personal AI knowledge base.

Git

Integrate Git version control with automatic backup and other advanced features.

Agent Client

Chat with Claude Code, Codex, Gemini CLI, and more via the Agent Client Protocol — right from your vault.

Text Generator

Generate text content using GPT-3 (OpenAI).

ExcaliBrain

An interactive, structured mind-map of your Obsidian vault.

Smart Composer

AI chat with note context, smart writing assistance, and one-click edits for your vault.

Smart Connections

Find related notes and excerpts while writing. Your AI link building copilot displays relevant content in graph + list view. A local embedding model powers semantic search. Zero setup. No API key.