Obsidian Stats logoObsidian Stats

AI-Vault

by JamJan05
5
4
3
2
1
New Plugin
Install Code

Description

This plugin has not been manually reviewed by Obsidian staff. Chat with GPT and Claude directly inside your notes — RAG from your vault, history, projects and smart modes.

Reviews

No reviews yet.

Stats

stars
downloads
0
forks
0
days
NaN
days
NaN
days
0
total PRs
0
open PRs
0
closed PRs
0
merged PRs
0
total issues
0
open issues
0
closed issues
0
commits

Latest Version

Invalid date

Changelog

See all version on GitHub

README file from

Github

✨ AI-Vault for Obsidian

Chat with OpenAI GPT and Anthropic Claude directly inside Obsidian, with vault-aware context, conversation history, projects, smart modes, and local-first storage.

AI-Vault turns your Obsidian workspace into an AI assistant that can use your notes, canvases, selected files, and project history as context while keeping plugin data on your own machine.

🚀 Highlights

  • 🤖 Multi-provider chat - switch between OpenAI and Anthropic models from the chat view.
  • 📚 Vault RAG - search relevant Markdown and Canvas content from your vault.
  • 📎 Manual note context - attach specific notes or canvases to a conversation.
  • 🗂️ Projects - group related chats with custom prompts and shared project context.
  • 🕘 Conversation history - automatically save and reopen previous chats.
  • ⚡ Streaming responses - see answers as they are generated.
  • 🧠 Thinking modes - choose Fast, Normal, or Think mode.
  • 🎓 Learn mode - generate study-friendly answers and interactive quiz-style responses.
  • 💻 Code mode - get programming-focused answers with code formatting.
  • 🌐 Web search - use supported OpenAI and Claude web-search capabilities.
  • 🌍 Bilingual UI - English and Polish interface.
  • 🔐 Local-first storage - history, projects, keys, and RAG index can stay outside your vault.

🧩 Requirements

  • 🖥️ Obsidian desktop 1.7.2 or newer
  • 🔑 OpenAI API key and/or Anthropic API key
  • 📡 Internet access for model calls, embeddings, and web search

AI-Vault is desktop-only because streaming and external local storage rely on desktop APIs.

🤖 Supported Models

OpenAI

  • GPT-5
  • GPT-5 Mini
  • GPT-5 Nano
  • GPT-5 Search
  • GPT-4o
  • GPT-4o Mini
  • GPT-4 Turbo

Anthropic

  • Claude Opus 4.5
  • Claude Sonnet 4.5
  • Claude Haiku 4.5

📚 Vault Context

AI-Vault can add your notes to the model context in two ways:

  • 🔎 Automatic RAG searches indexed .md and .canvas files for relevant chunks.
  • 📎 Manual context lets you pick specific notes or canvases for the conversation.

Canvas files are parsed into readable text using their nodes and edges, so the model can understand the flow of a canvas instead of receiving raw JSON.

The RAG engine combines keyword search and embeddings when available. If no OpenAI key is configured for embeddings, lexical search can still provide useful matches.

🗂️ Projects

Projects let you keep related conversations together.

Each project can have:

  • 📝 its own custom system prompt,
  • 💬 linked conversations,
  • 🧠 context from other chats in the same project,
  • 🎨 a project color for easier scanning.

This works well for long-running research, coding tasks, study topics, writing work, or client-specific threads.

💬 Chat Tools

Inside the AI-Vault chat view you can:

  • 🧠 switch reasoning mode,
  • 🔁 regenerate the last response,
  • ⏹️ stop generation,
  • 📋 copy messages and code blocks,
  • 📤 export a conversation to a note,
  • 📚 toggle RAG,
  • 🔄 re-index the vault,
  • 📎 attach notes manually,
  • 🌐 toggle web search,
  • 🎓 enable Learn mode,
  • 💻 enable Code mode.

🔐 Privacy And Storage

By default, AI-Vault stores plugin data outside your vault in a local folder next to the vault directory:

<parent-of-vault>/<vault-name>-gpt-data/

This keeps data out of Obsidian Sync by default.

Stored locally:

  • 🔑 API keys
  • 🕘 conversation history
  • 🗂️ projects
  • 📚 RAG index

Data is sent to model providers only when it is part of a request, for example:

  • your chat message,
  • selected notes,
  • relevant RAG chunks,
  • project context,
  • web-search requests.

AI-Vault does not use its own backend server. Requests go directly from Obsidian to the configured OpenAI or Anthropic API.

📦 Installation

Manual Installation

  1. Download the latest release from the Releases page.
  2. Copy the plugin files into:
<your-vault>/.obsidian/plugins/ai-vault/

Required files:

main.js
manifest.json
styles.css
  1. Reload Obsidian.
  2. Open Settings -> Community plugins.
  3. Enable AI-Vault.

Community Plugins

Once available in the Obsidian Community Plugins directory:

  1. Open Settings -> Community plugins.
  2. Turn off Restricted mode if needed.
  3. Click Browse.
  4. Search for AI-Vault.
  5. Install and enable the plugin.

⚙️ Setup

  1. Open Settings -> AI-Vault.
  2. Choose the interface language.
  3. Add your OpenAI API key and/or Anthropic API key.
  4. Choose your default provider and model.
  5. Configure RAG, token limits, storage, and system prompt settings.
  6. Open AI-Vault from the ribbon icon or command palette.

🛠️ Development

Install dependencies:

npm install

Run a development build:

npm run dev

Run typecheck:

npm run typecheck

Create a production build:

npm run build

The production plugin files are:

main.js
manifest.json
styles.css

🐛 Reporting Issues

Found a bug or have a feature request? Open an issue on GitHub Issues.

Please include:

  • 🧱 Obsidian version
  • 💻 operating system
  • 🔖 AI-Vault version
  • 🤖 selected provider and model
  • 🧭 steps to reproduce
  • 🧾 relevant console errors, if available

🤝 Contributing

Pull requests are welcome. For larger changes, please open an issue first to discuss the proposed direction.

📜 License

MIT © 2026 JamJan05

Sponsors