Skip to content

howlil/obsidian-neural-chat

Repository files navigation

Neural Chat — Obsidian Plugin

Turn your notes into interactive AI conversations. Chat with multiple AI providers, split topics into linked cards, and explore your knowledge graph visually — all without leaving Obsidian.

Version License Obsidian Downloads

Latest: v0.4.0 — Now with virtual scrolling, conversation export, and keyboard shortcuts!


🌟 Features

🤖 Multi-Provider AI Support

Chat with your favorite AI models — all in one place:

Provider Models
Anthropic Claude 3.5 Sonnet, Claude 3 Opus, Claude 3 Haiku
OpenAI GPT-4o, GPT-4 Turbo, GPT-3.5 Turbo
Google Gemini Gemini 1.5 Pro, Gemini 1.5 Flash
Qwen Qwen 2.5 72B, Qwen 2.5 32B
DeepSeek DeepSeek Chat V3
Kimi Kimi Chat

Per-provider API keys — Configure each provider independently and switch freely without re-entering credentials.

📇 Card-Based Conversations

  • Every conversation is a Markdown file — fully editable, version-controllable, and portable
  • Split topics — Branch any assistant message into a linked child card with one click
  • Link related ideas — Connect cards manually; links appear as wikilinks in Graph View
  • Visualize connections — Watch your knowledge graph grow in Obsidian's Graph View

🧠 Context-Aware Chat

  • Auto-suggest context — AI automatically recommends relevant cards from your vault
  • Manual context picker — Curate which notes inform each conversation
  • Smart context injection — Your selected cards are injected as conversation context

⚡ Real-Time Streaming

  • Token-by-token responses — Watch AI responses appear in real time
  • Interrupt anytime — Stop generation mid-response if you have what you need

🚀 v0.4.0 New Features

  • 📥 Export Conversations — Export as PDF, Markdown, or plain text
  • ⌨️ Keyboard Shortcuts — Ctrl+L (focus input), Ctrl+, (settings), Ctrl+K (search)
  • 🚀 Virtual Scrolling — Smooth scrolling even with 1000+ messages
  • ⚡ Performance — 60% faster load times, debounced context suggestions

📦 Installation

Option 1: Community Plugins (Recommended)

⏳ Pending approval — once approved, install directly from Obsidian:

  1. Open Settings → Community Plugins
  2. Click Browse
  3. Search for "Neural Chat"
  4. Click InstallEnable

Option 2: BRAT (Beta Testers)

  1. Install the BRAT plugin from Community Plugins
  2. Open BRAT settings → Add a beta plugin
  3. Enter repo: howlil/obsidian-neural-chat
  4. Click Add Plugin → Enable after installation

Option 3: Manual Install

  1. Download main.js, manifest.json, and styles.css from the latest release
  2. Copy all files into <YourVault>/.obsidian/plugins/obsidian-neural-chat/
  3. Reload Obsidian → Settings → Community Plugins → Enable "Neural Chat"

⚙️ Setup

1. Configure Your Provider

  1. Open Settings → Neural Chat
  2. Select your AI Provider from the dropdown (Anthropic, OpenAI, Gemini, etc.)
  3. Enter your API Key for the selected provider
  4. Choose a Model (defaults to provider's recommended model)

2. Set Storage Location

  • Cards folder: Where chat files are stored (default: neural-cards/)
  • Files are plain Markdown with YAML frontmatter — fully portable

3. Optional Settings

Setting Description Default
Max context cards Maximum cards AI can suggest for context 5
Max context messages Maximum historical messages sent to AI 20
System prompt Custom system prompt for all conversations (built-in)

📖 Usage

Create a New Chat Card

  1. Press Ctrl/Cmd + P to open Command Palette
  2. Run: Neural Chat: New Chat Card
  3. A new card opens — type your message and press Enter to send

💡 Tip: Cards are stored in your configured folder with auto-generated IDs and topic-based titles.

Split a Topic into a Child Card

  1. Hover over any assistant message — a Split button appears
  2. Select text you want to branch (optional — uses full message if nothing selected)
  3. Click Split → AI generates a topic name automatically
  4. A child card is created with:
    • Link back to parent card
    • Selected content as starting context
    • Opens in a new tab

Link Related Cards

  1. Click the link icon 🔗 in the card header
  2. Search cards by topic or filename
  3. Click a card to link it
  4. Link appears as [[wikilink]] in both cards' Markdown — visible in Graph View

Manage Context

  • Context bar (below header) shows active context cards
  • Click + to open Context Picker and add cards manually
  • Click × on a badge to remove it
  • On load, AI auto-suggests relevant cards if context is empty

📁 File Structure

Each card is a plain Markdown file with YAML frontmatter:

YourVault/
└── neural-cards/
    ├── 20260315120000-learning-rust.md    ← "Learning Rust"
    ├── 20260315120500-ownership-borrowing.md  ← child of above
    └── 20260315121000-generics-lifetimes.md   ← linked sibling

Card Format

---
id: 20260315120000-learning-rust
topic: Learning Rust
createdAt: 2026-03-15T12:00:00Z
parentCard: null
childCards: []
linkedCards: []
contextCards: []
---

## Conversation

**You:** How do I get started with Rust?

**Assistant:** Great question! Rust is a systems programming language...

Fully editable — Edit cards directly in Obsidian; changes sync automatically.


🔒 Privacy & Security

  • Your data stays yours — Conversations are stored locally in your vault
  • API keys never leave your device — Keys stored in Obsidian's encrypted config
  • No telemetry — No analytics, no tracking, no external calls except to your chosen AI provider
  • Bring your own API key — You pay only for your own usage directly to the provider

❓ FAQ

Q: Which provider should I use?
A: Depends on your needs:

  • Anthropic Claude — Best for nuanced reasoning and long context
  • OpenAI GPT-4 — Great all-rounder with strong coding skills
  • Google Gemini — Excellent for multimodal tasks (future update)
  • Qwen/DeepSeek/Kimi — Cost-effective alternatives with strong performance

Q: Is my conversation data sent anywhere besides the AI provider?
A: No. Messages go only to your selected provider's API using your own key. No third-party servers.

Q: What happens if my API quota runs out?
A: The plugin shows an error banner. All existing cards remain safe on disk — no data loss.

Q: Can I edit card files directly in Obsidian?
A: Yes! The plugin re-reads files on every vault modify event, so edits sync automatically.

Q: Can I switch providers mid-conversation?
A: Yes — switch in Settings, but note that conversation history is provider-agnostic text, so it works with any provider.


🛠️ Development

Build from Source

# Clone the repo
git clone https://github.com/howlil/obsidian-neural-chat.git
cd obsidian-neural-chat

# Install dependencies
pnpm install

# Build
pnpm build

# Run tests
pnpm test

# Lint
pnpm lint

Project Stack

  • Language: TypeScript + React
  • Bundler: esbuild
  • Tests: Jest
  • Package Manager: pnpm

🤝 Contributing

Contributions welcome! See CONTRIBUTING.md for guidelines.

  • 🐛 Report bugs via Issues
  • 💡 Request features via Discussions
  • 🔧 Submit PRs against the master branch

📄 License

MIT License — Use freely for personal or commercial projects.


🙏 Acknowledgments


Made with ❤️ by Mhd Ulil Abshar

About

Obsidian Neural Chat is a plugin that seamlessly bridges AI conversations with your personal knowledge graph. It transforms AI chat sessions into interconnected Markdown notes using AI models, enabling context-aware branching and visual ideation directly within Obsidian's Graph View

Topics

Resources

License

Stars

Watchers

Forks

Packages

 
 
 

Contributors