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

AI Vault Memory

puriapuria78 downloads

AI-powered local vault memory and context-aware chat with any OpenAI-compatible API.

Add to Obsidian
  • Overview
  • Scorecard
  • Updates10

Local vault memory and context-aware AI chat for Obsidian.

AI Vault Memory indexes Markdown notes locally, retrieves relevant passages when you ask a question, and sends only the chat request and selected context to the OpenAI-compatible provider that you configure.

Features

  • Local Markdown indexing and semantic-style retrieval without an external database.
  • Context-aware chat grounded in relevant notes from your vault.
  • Support for any OpenAI-compatible API, including OpenAI, OpenRouter, Groq, LM Studio, and self-hosted services.
  • Attach specific Markdown files or send selected text to a chat.
  • Rebuild, update, and clear the local memory index.
  • Saved chat sessions and English/Persian interface support.

Install

From the Community plugins directory

Once accepted, open Settings → Community plugins, search for AI Vault Memory, then install and enable it.

Manually from GitHub

  1. Download main.js, manifest.json, and styles.css from the latest GitHub release.

  2. Create this folder in your vault:

    <vault>/.obsidian/plugins/vault-ai-chat/
    
  3. Copy the three files into that folder.

  4. Reload Obsidian and enable AI Vault Memory in Settings → Community plugins.

Setup and use

  1. Open AI Vault Memory from the ribbon icon or Command Palette.
  2. In the plugin settings, set your API base URL, API key, and chat model.
  3. Rebuild the vault memory index.
  4. Ask a question in the chat panel, or use Analyze current file / Send selection to chat from the Command Palette.

Privacy and network use

  • The index, indexed note chunks, settings, and chat history are stored locally in Obsidian plugin data.
  • The plugin connects to the API base URL that you configure. It uses that endpoint to list models and process chat or analysis requests.
  • When you send a chat or analysis request, the request includes your prompt and the relevant note excerpts, selected text, or explicitly attached files needed as context. Do not configure a provider you do not trust with that content.
  • Your API key is stored in the plugin's local data and sent only as a Bearer token to your configured API provider.
  • The plugin has no built-in telemetry, advertising, or payment service.

Development

npm install
npm run build

Release assets are main.js, manifest.json, and styles.css. Create a GitHub release with a tag exactly matching the version in manifest.json, then attach those three files.

License

Licensed under the MIT License.

HealthExcellent
ReviewCaution
About
Index Markdown notes locally and retrieve relevant passages for context-aware AI chat without relying on an external database. Send only your prompt plus selected note context to any OpenAI-compatible API, attach files or selections to chats, rebuild or clear the local memory index, and save chat sessions with English/Persian interface.
AISearchIntegrations
Details
Current version
1.1.4
Last updated
Last month
Created
Last month
Updates
10 releases
Downloads
78
Compatible with
Obsidian 1.13.0+
Platforms
Desktop, Mobile
License
MIT
Report bugRequest featureReport plugin
Author
puriapuriapuriakazemieh
GitHubpuriakazemieh
  1. Community
  2. Plugins
  3. AI
  4. AI Vault Memory

Related plugins

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.

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.

Agent Client

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

Smart Composer

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

Semantic Notes Vault MCP

Give Claude Desktop and other AI assistants semantic access to your notes through a built-in Model Context Protocol (MCP) server.

Claude Sidebar

Run Claude Code in your sidebar.

Smart Lookup

Semantic search for your vault. Ask in natural language, find notes by meaning when exact words fail, preview matching notes, and turn forgotten ideas into links, context, and next steps.

Claude Code IDE

Connect your vault to Claude Code and share editor context with the CLI.

Snipd Official

Sync Snipd podcast highlights to your vault with transcript, notes, AI summaries and metadata.

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.