VaultTalk

by zhenghaoyang24
5
4
3
2
1
Score: 35/100
New Plugin

Description

This plugin has not been manually reviewed by Obsidian staff. AI-powered chat assistant in Obsidian sidebar. Stream responses, chat with your entire vault as context, and get answers grounded in your notes. Supports OpenAI-compatible APIs (DeepSeek, OpenAI, etc.

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

README file from

Github

中文 | English

VaultBuddy

AI-powered chat assistant for Obsidian. Chat with your entire vault as context.

Obsidian Plugin


Features

VaultBuddy turns your Obsidian vault into an intelligent Q&A system. Simply ask a question, and the AI automatically retrieves the most relevant passages from your notes as context to provide grounded answers. It helps you locate scattered information, connect ideas across different notes, or generate summaries and suggestions—with automatic source citations. Compatible with any API endpoint that supports curl calls, you can configure multiple models and switch between them on the fly. API keys are stored locally with encryption, and all conversations are automatically saved.


Installation

From Obsidian Community Store (once published)

  1. Open Obsidian → Settings → Community Plugins → Browse
  2. Search for VaultBuddy
  3. Click Install → Enable

Manual Installation

  1. Go to GitHub Releases and download these 3 files:
    • main.js
    • manifest.json
    • styles.css
  2. Create a folder .obsidian/plugins/vaultbuddy/ inside your vault
  3. Put the 3 files into that folder
  4. Enable the plugin in Settings → Community Plugins

Quick Start

Add a Model

Open Settings → VaultBuddy and click + Add Model. Fill in:

Field Example
Display Name DeepSeek
Base URL https://api.deepseek.com/chat/completions
API Key sk-...
Model ID deepseek-chat
Context Window 131072

The Base URL must be a cURL-compatible chat completions endpoint (e.g. https://api.openai.com/v1/chat/completions).

Click Save Model, then select your model as the Default Model in the dropdown below.


Configuration

Setting Description
Models Add, edit, delete, and test API model configurations
Default Model Which model to use for new conversations
Max Response Tokens Maximum length of AI responses (recommended 4096-8192)
Custom Rules Extra instructions appended to the system prompt
Resume Last Conversation Automatically reload the previous chat on startup

Development

# Install dependencies
npm install

# Watch mode (auto-rebuild)
npm run dev

# Production build
npm run build

# Type check only
tsc --noEmit

Project Structure

vaultbuddy/
├── manifest.json
├── package.json
├── styles.css
├── build/                  # Build output
└── src/
    ├── core/               # Plugin entry & types
    │   ├── main.ts
    │   ├── types.ts
    │   └── i18n.ts         # Multi-language module
    ├── services/           # Business logic
    │   ├── aiService.ts    # API calls & streaming
    │   ├── contextBuilder.ts # Vault content compression
    │   └── storage.ts      # Conversation persistence
    ├── ui/                 # UI components
    │   ├── view.ts         # Chat panel
    │   └── settings.ts     # Settings tab
    └── utils/
        └── sourceManager.ts

Compatibility

  • Desktop — Obsidian v0.15.0+
  • Mobile — Fully supported (isDesktopOnly: false)
  • API — OpenAI-compatible endpoints (DeepSeek, OpenAI, Groq, etc.)

Contributing

Contributions are welcome! Here's how you can help:

  1. Report bugs — Open an issue with steps to reproduce
  2. Suggest features — Share your ideas in the Discussions tab
  3. Submit PRs — Fork the repo, create a branch, and submit a pull request

Please follow the existing code style and include tests when applicable.


License

MIT

Author

zhenghaoyang24GitHub