-
Notifications
You must be signed in to change notification settings - Fork 0
Getting Started
This guide will walk you through setting up the Dissensus AI Debate Engine locally or on a VPS.
Before you begin, ensure you have the following:
| Requirement | Version | Notes |
|---|---|---|
| Node.js | 20+ (18+ minimum) | Download from nodejs.org |
| npm | 9+ | Included with Node.js |
| API Key | — | From DeepSeek, Google, or OpenAI |
cd dissensus-enginenpm install
Copy the example environment file and add your API keys:
cp .env.example .env
Edit .env with your preferred editor:
# Server PORT=3000 NODE_ENV=development # API Keys — Add at least one provider DEEPSEEK_API_KEY=sk-your-deepseek-key GOOGLE_API_KEY=AIza-your-gemini-key OPENAI_API_KEY=sk-your-openai-key
npm start
The server will start on http://localhost:3000
| Provider | URL | Free Tier | Cost per Debate |
|---|---|---|---|
| DeepSeek | platform.deepseek.com | Limited | ~0ドル.008 ⭐ Recommended |
| Google Gemini | aistudio.google.com | Yes — generous free tier | ~0ドル.006 |
| OpenAI | platform.openai.com | Limited (5ドル credit) | ~0ドル.15 (GPT-4o) / ~0ドル.01 (GPT-4o Mini) |
| Provider | Model | Cost/Debate | Quality | Speed |
|---|---|---|---|---|
| 🔥 DeepSeek | V3.2 | ~0ドル.008 | Very Good | Fast |
| ⚡ Google Gemini | 2.0 Flash | ~0ドル.006 | Good | Very Fast |
| ⚡ Google Gemini | 2.5 Flash | ~0ドル.03 | Very Good | Fast |
| ⚡ Google Gemini | 2.5 Flash-Lite | ~0ドル.006 | Good | Very Fast |
| 🧠 OpenAI | GPT-4o | ~0ドル.15 | Excellent | Medium |
| 🧠 OpenAI | GPT-4o Mini | ~0ドル.01 | Good | Fast |
Recommendation: Start with DeepSeek V3.2 for the best value, or Gemini 2.0 Flash for the free tier.
Once the server is running:
-
Open the app — Navigate to http://localhost:3000 in your browser
-
Select your AI Provider — Choose from the dropdown (DeepSeek, Gemini, or OpenAI)
-
Enter your API Key — Paste your key (or skip if using server-side keys)
-
Select a model — Pick based on your quality/speed/cost preferences
-
Type a debate topic — Examples:
- "Is Bitcoin a good store of value for the next 10 years?"
- "Should companies adopt a 4-day work week?"
- "What are the top 5 AI cryptocurrencies for 2025?"
-
Click "⚡ Start Debate" — Watch CIPHER, NOVA, and PRISM battle it out in real-time!
NODE_ENV=development npm start
- Rate limiting: 100 debates/minute (relaxed)
- Verbose error messages
- No server-side API keys required
NODE_ENV=production npm start
- Rate limiting: 10 debates/minute (strict)
- Minimal error details
- Server-side API keys recommended for visitor access
For production deployments, set API keys in .env so visitors can debate without entering their own keys:
# .env NODE_ENV=production PORT=3000 # Server-side keys (visitors can use these without entering their own) DEEPSEEK_API_KEY=sk-your-key GOOGLE_API_KEY=AIza... OPENAI_API_KEY=sk-your-key
Users can still override with their own key if they prefer to use their quota.
| Variable | Default | Description |
|---|---|---|
PORT |
3000 |
Server port |
NODE_ENV |
development |
Environment mode |
TRUST_PROXY |
(enabled) | Set 0 only if no reverse proxy |
TRUST_PROXY_HOPS |
1 |
Number of trusted proxy hops |
DEEPSEEK_API_KEY |
— | DeepSeek API key |
GOOGLE_API_KEY |
— | Google/Gemini API key |
GEMINI_API_KEY |
— | Alternative Gemini key name |
OPENAI_API_KEY |
— | OpenAI API key |
DEBATE_OF_THE_DAY_TZ |
UTC |
Timezone for daily topic rotation |
- Ensure you've set at least one API key in
.env - Or enter a key directly in the web interface
- This happens when behind a proxy without proper trust settings
- Leave
TRUST_PROXYunset (default) when using nginx/Hostinger - Update to the latest code — trust proxy is now enabled by default
# Kill process on port 3000 (Linux/Mac) lsof -ti:3000 | xargs kill -9 # Or use a different port PORT=3001 npm start
- Learn about the Architecture
- Understand the The-Three-Agents
- Explore the Debate-Methodology
Ready to forge truth from disagreement? Start your first debate!