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

Copilot

Logan YangLogan Yang1.8M downloads

Run AI agents such as Claude Code, Codex, and OpenCode inside your vault. Turn your second brain into a smart assistant that gets knowledge work done.

Add to Obsidian
Copilot screenshot
  • Overview
  • Scorecard
  • Updates122

Agents for your Obsidian vault

Copilot V4 brings opencode, Claude Code, and Codex into Obsidian for research, writing, and knowledge work.

Best LLM Integration Award

No. 1 Obsidian AI Plugin

Copilot V4 agent organizing research into connected Obsidian notes

Install in Obsidian · View plans · Get started


Choose your agent

Agent is the main Copilot experience for multi-step work. It can inspect notes, use tools, create Obsidian files, and continue across several turns with permissions you control.

  • opencode (recommended): Let Copilot download and manage it, then use Copilot-hosted models, your own provider key, or a local model.
  • Claude Code: Connect an existing installation. Copilot detects common install locations and uses your Claude Code login.
  • Codex: Connect Codex through the @agentclientprotocol/codex-acp adapter and use your existing Codex login.

Already pay for Claude or ChatGPT, or already have model API access? You can bring that access to Copilot without buying a Copilot plan. Provider terms and usage limits still apply.

Learn how Agent works →

Set up Copilot

  1. Install Copilot from Obsidian Community Plugins.
  2. Open Settings → Copilot → Basic → Agents.
  3. Select Download opencode, or connect Claude Code or Codex with Auto-detect. Codex requires the codex-acp adapter first.
  4. Select the Agent ribbon icon, or run Open Copilot Agent Chat Window.

The Getting Started guide covers each setup path, including the Codex adapter commands and manual adapter paths.

Built around your vault

  • Projects: Give ongoing work its own instructions, reusable context, and chat history. A project works with opencode, Claude, or Codex. Learn about Projects.
  • Skills shared across agents: Add a skill once, then enable it for each installed agent. Copilot also includes skills for Obsidian Markdown, Bases, Canvas, and the Obsidian CLI. Learn about Skills.
  • Commands: Save repeatable prompts, run them with / in Agent, or expose them in the editor and Command palette. Create a Command.
  • Quick Ask: Ask about a selection without leaving the note. Continue the conversation, replace text, insert the answer, or copy it. Quick Ask uses your Quick Chat model. Set up Quick Ask.
  • Multiple sessions: Keep separate Agent tabs open for different tasks. With active Plus access, mention multiple installed agents with @ for one read-only research or review request.

For a short conversation that does not need an agent, use Quick Chat.

Use hosted, BYOK, or local models

  • Copilot-hosted: Add a Copilot license, then choose an available hosted model for opencode or Quick Chat. The model picker and dashboard show current access.
  • Bring your own key: Add a cloud, local, or OpenAI-compatible provider under Settings → Copilot → BYOK. Keys are stored in this device's Obsidian Keychain, not in the vault's data.json.
  • Claude and Codex accounts: These agents use their own CLI login rather than a key from Copilot's BYOK settings.
  • Models reported by opencode: opencode routes them to their backing provider. Free opencode Zen models show a warning because that provider may log or train on prompts; review its terms before sending sensitive content.

Your chosen route determines where prompts and included context are processed. Read LLM Providers for setup and Copilot Plus and Self-Host for privacy and routing details.

Plans

The Copilot plugin is open source and works without a Copilot license when you use your own agent account, provider key, or local model. Free use includes normal single-agent Agent chats, Projects with Markdown context, custom Skills and Commands, Quick Chat, Quick Ask, and local Miyo search.

Paid access can include Copilot-hosted models and cloud-backed tools. Multi-agent requires active Plus access; check your dashboard for the current entitlement. Model availability and service limits can change, so the pricing page and in-app model pickers are the current source of truth.

Compare plans →

Trusted by people who think for a living

"The first tool that truly unifies how I search, organize, and retrieve knowledge without ever leaving Obsidian. My workflow is faster, deeper, and more connected. I can't imagine working without it."

Jason Zhang, Investor & Research Analyst

More from the community

"I drop meeting transcriptions, personal notes, and architecture ideas into my vault. Copilot gives me a personal assistant that finds missing puzzle pieces and surfaces relevant info during live calls, no manual searches."

Brad Decker, CTO, Concierge Auctions

"Since discovering Copilot, my writing process has been completely transformed. Conversing with my own articles and thoughts is the most refreshing experience I've had in decades."

Mat QV, Professional Writer

Frequently asked questions

Can I use Copilot without a paid plan?

Yes. Connect Claude Code or Codex with its existing account, or use opencode and Quick Chat with your own API key or local model. Your provider may charge for its own usage.

Does Agent work on mobile?

Agent is a desktop feature because its backends run local processes. Quick Chat, custom Commands, and Quick Ask remain available on mobile.

How is my data handled?

Your notes remain files in your vault, and local Miyo indexes stay on your device. Prompts and any included context go to the model or service you choose. Copilot-hosted models and hosted features send the required input to Brevilabs for processing. See the disclosure below and the privacy policy.

Help and links

Documentation · YouTube · Report a bug · Request a feature · Privacy

Support the project

If Copilot is useful to you, consider sponsoring the project on GitHub or buying us a coffee.

Thank you to our GitHub Sponsors

Special thanks to our top sponsors: @mikelaaron, @pedramamini, @Arlorean, @dashinja, @azagore, @MTGMAD, @gpythomas, @emaynard, @scmarinelli, @borthwick, @adamhill, @gluecode, @rusi, @timgrote, @JiaruiYu-Consilium, @ddocta, @AMOz1, @chchwy, @pborenstein, @GitTom, @kazukgw, @mjluser1, @joesfer, @rwaal, @turnoutnow-harpreet, @dreznicek, @xrise-informatik, @jeremygentles, @ZhengRui, @bfoujols, @jsmith0475, @pagiaddlemon, @sebbyyyywebbyyy, @royschwartz2, @vikram11, @amiable-dev, @khalidhalim, @DrJsPBs, @chishaku, @Andrea18500, @shayonpal, @rhm2k, @snorcup, @JohnBub, @obstinatelark, @jonashaefele, @vishnu2kmohan

Paid Plan Disclosure

Copilot is a product of Brevilabs LLC and is not affiliated with Obsidian. Visit obsidiancopilot.com for current plan details.

  • An account and payment are required for paid access.
  • Hosted models and cloud-backed features require network access.
  • Privacy and data handling:
    • Free use: Messages and note context go to the LLM provider, local endpoint, or CLI agent you configure. Brevilabs does not receive them unless you invoke a Brevilabs-hosted feature.
    • Paid hosted services: Brevilabs's backend and its vetted enterprise model providers process the full request. Hosted features receive the inputs they need, such as search queries, URLs, and files used by Quick Chat tools or Agent project context. The privacy policy says request content is processed transiently, not retained, and not used for training.
    • User ID: Hosted feature requests include a randomly generated UUID for service delivery, license abuse prevention, and rate limiting. It is not used for tracking, profiling, or analytics.
  • See the privacy policy for full terms.
  • The Copilot plugin frontend is fully open source. The backend services that support hosted features are closed source and proprietary.
  • We offer a full refund within 14 days of purchase if you are not satisfied.

Authors

Brevilabs Team · [email protected] · @logancyang

HealthExcellent
ReviewSatisfactory
About
Copilot turns your Obsidian vault into a workspace for AI agents. On desktop, run opencode, Claude Code, and Codex inside Obsidian to research, write, organize notes, and complete multi-step knowledge work. Agents work with Markdown, wikilinks, and canvases, search your vault by meaning, and save useful results as files you keep. Connect Codex with your ChatGPT subscription or Claude Code with your Claude subscription. You can also bring your own API keys or use local and OpenAI-compatible models. Add a skill once, then enable it across your agents. Local Miyo indexing helps surface related notes and connect your vault with PDFs and EPUBs.
AICommandsProject management
Details
Payments
Optional
Current version
4.0.6
Last updated
14 hours ago
Created
3 years ago
Updates
122 releases
Downloads
1.8M
Compatible with
Obsidian 1.11.4+
Platforms
Desktop, Mobile
License
AGPL-3.0
Report bugRequest featureReport plugin
Payments
Copilot is free to use with supported agent subscriptions, your own API keys, local models, OpenAI-compatible endpoints. A paid Copilot license adds hosted models that do not require a separate provider account or API key, multi-agent collaboration, managed web search, PDF parsing, built-in skills
Sponsor
Buy Me a Coffee
GitHub Sponsors
Author
Logan YangLogan Yanglogancyang
x.com/logancyang
GitHublogancyang
  1. Community
  2. Plugins
  3. AI
  4. Copilot

Related plugins

Claudian

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

Smart Second Brain

Chat with an agent that knows your notes, search by meaning, and see your vault grouped into topics. Runs on Ollama, OpenAI, Anthropic, and more.

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.

Tasks

Track tasks across your vault. Supports due dates, recurring tasks, done dates, sub-set of checklist items, and filtering. Maintained by Clare Macrae and Ilyas Landikov, created by Martin Schenck.

ChatGPT MD

A seamless integration of ChatGPT, OpenRouter.ai and local LLMs via Ollama into your notes.

Quick Switcher++

Enhanced Quick Switcher, search open panels, and symbols.

Find orphaned files and broken links

Find files that are not linked anywhere and would otherwise be lost in your vault. In other words: files with no backlinks.

Note Toolbar

Add customizable toolbars to your notes.

Longform

Helps you write and edit novels, screenplays, and other long projects.