An LLM-powered decentralized content processing demo
This project is no longer maintained and is provided as-is for archival and educational purposes only.
- 🚫 No new features will be developed
- 🚫 No bug fixes or security patches will be applied
- 🚫 No support is available
- 📦 Dependencies may be outdated and potentially vulnerable
Use at your own risk. If you choose to use this code, you are responsible for updating dependencies and ensuring security compliance.
DataOS is a demonstration application showcasing the integration of Large Language Models (LLMs) with decentralized content storage. The application fetches content from Arweave and processes it through various LLM-powered pipelines to generate structured summaries, analyses, and debates.
This project was developed by Roark Technology as a proof-of-concept for intelligent content processing using decentralized infrastructure.
- 🔗 Decentralized Content — Fetches articles directly from the Arweave permanent storage network
- 🤖 LLM Processing — Multiple analysis modes powered by OpenAI's GPT models
- 📊 Financial Analyst Mode — Extracts key facts and figures into structured tables
- 💬 Debate Mode — Generates pro/con analysis of article topics
- 🔊 Text-to-Speech — Optional audio synthesis via ElevenLabs integration
- 🎨 Modern UI — Responsive Twitter-inspired interface built with React and TailwindCSS
┌─────────────────────────────────────────────────────────────────┐
│ DataOS Demo │
├─────────────────────────────────────────────────────────────────┤
│ │
│ ┌──────────────┐ ┌──────────────┐ ┌──────────────┐ │
│ │ Arweave │───▶│ LLM Chain │───▶│ React UI │ │
│ │ Gateway │ │ (LangChain) │ │ (Feed View) │ │
│ └──────────────┘ └──────────────┘ └──────────────┘ │
│ │ │ │ │
│ │ ▼ │ │
│ │ ┌──────────────┐ │ │
│ │ │ OpenAI │ │ │
│ │ │ GPT-3.5/4 │ │ │
│ │ └──────────────┘ │ │
│ │ │ │
│ │ ┌──────────────┐ │ │
│ └──────────────────▶│ ElevenLabs │◀────┘ │
│ │ (TTS) │ │
│ └──────────────┘ │
│ │
└─────────────────────────────────────────────────────────────────┘
| Layer | Technology |
|---|---|
| Frontend | React 18, TypeScript, TailwindCSS |
| Build | Vite |
| LLM Integration | LangChain |
| AI Provider | OpenAI (GPT-3.5, GPT-4) |
| Storage | Arweave (decentralized) |
| Audio | ElevenLabs (optional) |
dataos-demo/
├── src/
│ ├── components/ # React components
│ │ ├── feed/ # Content feed components
│ │ ├── layout/ # Page layout components
│ │ ├── navbar.tsx/ # Navigation components
│ │ ├── publisher/ # Interaction components
│ │ └── trends/ # Trending section components
│ ├── pages/ # Page components
│ │ ├── config.tsx # LLM chain configuration
│ │ ├── home.tsx # Main application page
│ │ └── start.tsx # Onboarding flow
│ ├── schemas/ # TypeScript type definitions
│ ├── data/ # Static demo data
│ └── assets/ # Images and icons
├── index.html
├── package.json
├── tailwind.config.js
├── vite.config.ts
└── tsconfig.json
Note: This is an archived project. The following instructions may require adjustments for newer dependency versions.
- Node.js 16+
- npm or yarn
- OpenAI API key (required)
- ElevenLabs API key (optional, for audio features)
-
Clone the repository
git clone https://github.com/autonomous-finance/dataos-demo.git cd dataos-demo -
Install dependencies
npm install
-
Configure environment variables
cp .env.example .env
Edit
.envand add your API keys:VITE_OPENAI_API_KEY=your_openai_api_key VITE_ELEVENLABS_API_KEY=your_elevenlabs_api_key # Optional VITE_ELEVENLABS_VOICE_ID=your_voice_id # Optional
-
Start the development server
npm run dev
-
Open in browser
Navigate to
http://localhost:5173
npm run build
npm run preview- Financial Analyst — Extracts quantitative data, facts, and figures from articles into structured HTML tables
- Debater — Generates balanced pro/con arguments for the article's main topic
- Launch the application
- Select your preferred persona (Analyst, Debater, etc.)
- Choose content category (Crypto, Entrepreneurship, etc.)
- Click "GO" to start processing
- View LLM-generated summaries in the feed
- Use suggestion buttons to refine output
- Toggle audio playback for text-to-speech (requires ElevenLabs)
- API Costs — Each processing run makes multiple API calls to OpenAI
- Rate Limits — High usage may hit OpenAI rate limits
- Outdated Dependencies — LangChain and other packages may have breaking changes in newer versions
- No Authentication — Demo app has no user authentication
- Arweave Content — Demo content IDs may become unavailable
This project was developed by Roark Technology.
- UI inspired by Twitter's design language
- Built with React, Vite, and TailwindCSS
- LLM integration via LangChain
- Decentralized storage via Arweave
- Icons from Heroicons
This project is licensed under the MIT License — see the LICENSE file for details.
Originally developed by Roark Technology • Archived December 2025


