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

OpenAgent

nikitaclicksnikitaclicks204 downloads

AI agent for your vault — vault-aware, tool-capable, BYOK, and cross-platform (desktop + mobile).

Add to Obsidian
  • Overview
  • Scorecard
  • Updates4

An AI agent that lives inside your vault — vault-aware, tool-capable, BYOK, and cross-platform (desktop + mobile).

Hackathon build: See hackathon/README.md for the Gemma 4 hackathon submission story, local MLX setup, eval results, and demo assets.

Features

  • OpenAI-compatible provider — works with OpenAI, Anthropic (via proxy), Ollama, LM Studio, or any OpenAI-compatible endpoint
  • Vault tools — read, write, edit, append, search, list notes, manage frontmatter and links
  • Consent & safety — per-action confirmation dialogs with diff previews before any destructive write
  • BYOK — bring your own API key; no data leaves your vault except to the endpoint you configure
  • Cross-platform — same bundle runs on desktop (macOS / Windows / Linux) and mobile (iOS / Android)

Installation

From Obsidian Community Plugins

Search for OpenAgent in Settings → Community Plugins → Browse. Or simply open this page and press 'Add to Obsidian': https://community.obsidian.md/plugins/open-agent

Manual install

  1. Download main.js, styles.css, and manifest.json from the latest release.
  2. Copy them into <vault>/.obsidian/plugins/open-agent/.
  3. In Obsidian: Settings → Community Plugins → enable OpenAgent.

Mobile

Sync the plugin folder to your mobile vault's .obsidian/plugins/open-agent/ via Obsidian Sync or any file-sync tool.

Configuration

Open Settings → OpenAgent and fill in:

Field Description Default
Base URL Your provider's API endpoint https://api.openai.com/v1
API Key Your API key —
Model Model name to use gpt-4o-mini
System prompt Optional system-level instruction —

Privacy & network use

This plugin makes network requests only to the LLM endpoint you configure (e.g. OpenAI, OpenRouter, Ollama, LM Studio). No data is sent to any other server.

With vault tools enabled, the agent may transmit note bodies, paths, frontmatter, and tags to that endpoint — only use endpoints you trust.

Your API key is stored in .obsidian/plugins/open-agent/data.json. If you sync your .obsidian/ folder (e.g. via Obsidian Sync), the key travels with it.

Development

git clone https://github.com/nikitaclicks/obsidian-openagent.git
cd obsidian-openagent
npm install
npm run dev        # esbuild watch → writes main.js

Then copy main.js, styles.css, and manifest.json into a test vault at <vault>/.obsidian/plugins/open-agent/ and enable the plugin.

npm run build      # production bundle
npm run lint       # TypeScript ESLint

Project layout

src/
  main.ts          # plugin entry point
  settings.ts      # settings tab + defaults
  view.ts          # chat panel UI
  loop.ts          # agent run loop
  provider.ts      # OpenAI-compatible HTTP client
  types.ts         # shared types
  tools/
    registry.ts    # tool registration
    vault/         # read / write / edit / search / list / frontmatter / links
  consent/
    manager.ts     # per-action consent state
    modal.ts       # confirmation dialogs
    render-diff.ts # diff previews

Contributing

Pull requests are welcome. For larger changes, open an issue first to discuss what you'd like to change.

  1. Fork the repo and create a branch from main.
  2. Make your changes with tests where applicable.
  3. Run npm run lint and fix any issues.
  4. Open a PR — describe what changed and why.

Roadmap

  • Additional providers (Anthropic native, Google Gemini)
  • MCP server support
  • Inline agent commands
  • Tool call history / audit log

License

MIT

HealthExcellent
ReviewSatisfactory
About
Run an AI agent in your vault to read, write, edit, append, search and list notes, and manage frontmatter and links. Connect any OpenAI-compatible provider (OpenAI, Anthropic via proxy, Ollama, LM Studio), bring your own API key so requests go only to your chosen endpoint, confirm destructive writes with diff previews, and run the same plugin on desktop and mobile.
AIEditingDevelopers
Details
Current version
0.1.2
Last updated
2 months ago
Created
2 months ago
Updates
4 releases
Downloads
204
Compatible with
Obsidian 1.5.0+
Platforms
Desktop, Mobile
License
MIT
Report bugRequest featureReport plugin
Author
nikitaclicksnikitaclicks
github.com/nikitaclicks
GitHubnikitaclicks
  1. Community
  2. Plugins
  3. AI
  4. OpenAgent

Related plugins

Claudian

Embeds Claude Code/Codex as an AI collaborator in your vault. Your vault becomes agent's working directory, giving it full agentic capabilities: file read/write, search, bash commands, and multi-step workflows.

Gemini Scribe

Allows you to interact with Gemini and use your notes as context.

AI Agent

Lend your vault to an AI agent. It can read, write, and search your notes.

Advanced Tables

Improved table navigation, formatting, and manipulation.

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.

BRAT

Easily install a beta version of a plugin for testing.

Meta Bind

Make your notes interactive with inline input fields, metadata displays, and buttons.

Copilot

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

Local REST API with MCP

Unlock your automation needs by interacting with your notes over a secure REST API.

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.