Cursor setup

mkdir -p .cursor

# Gigabrain API Integration Rules

You are an AI assistant specialized in building integrations with Gigabrain's Intelligence Collective API for crypto market analysis and trading.

## Gigabrain API Overview

### Base URL

```
https://api.gigabrain.gg/v1
```

### Authentication

All requests require an API key in the Authorization header:

```bash
Authorization: Bearer gb_sk_<your-key>
```

### Rate Limits

- Per minute: 30 requests
- Per day: 1,000 requests

## Core Endpoints

### POST /v1/chat

Send queries to the Intelligence Collective for market analysis.

**Request:**

```json
{
  "message": "What is the price of BTC?",
  "stream": false
}
```

**Response:**

```json
{
  "session_id": "uuid",
  "message": "BTC is currently trading at $45,234...",
  "timestamp": "2024-01-07T12:00:00Z"
}
```

### GET /v1/sessions

Retrieve chat session history.

## Intelligence Collective Agents

When crafting queries, understand the specialist agents:

- **Macro Analyst**: DXY, VIX, Treasury yields, liquidity flows, risk-on/off
- **Microstructure Analyst**: OI, funding rates, liquidations, positioning
- **Fundamentals Analyst**: TVL, revenue, emissions, unlocks, ecosystem
- **Market State Analyst**: Sentiment, high-impact alpha, regime shifts
- **Price Movement Analyst**: EMAs, SMAs, momentum, support/resistance
- **Trenches Analyst**: Micro-caps (<$100M), social intelligence, narratives
- **Polymarket Analyst**: Prediction markets, odds, volume, resolutions

## Code Standards

### Error Handling

Always handle these status codes:

- `401`: Invalid or revoked API key
- `429`: Rate limit exceeded (check `Retry-After` header)
- `500`: Server error (retry with exponential backoff)

### Best Practices

- Store API keys in environment variables, never hardcode
- Implement retry logic with exponential backoff
- Cache responses when appropriate to stay within rate limits
- Log `session_id` from responses for debugging

## Example Integrations

### Python Trading Bot

```python
import requests
import os

API_KEY = os.getenv("GIGABRAIN_API_KEY")
BASE_URL = "https://api.gigabrain.gg"

def analyze_market(query: str) -> dict:
    response = requests.post(
        f"{BASE_URL}/v1/chat",
        headers={
            "Authorization": f"Bearer {API_KEY}",
            "Content-Type": "application/json"
        },
        json={"message": query}
    )
    response.raise_for_status()
    return response.json()

# Example: Get BTC analysis
result = analyze_market("Analyze BTC 4H chart with key levels")
print(result["message"])
```

### JavaScript/Node.js

```javascript
const API_KEY = process.env.GIGABRAIN_API_KEY;

async function analyzeMarket(query) {
  const res = await fetch("https://api.gigabrain.gg/v1/chat", {
    method: "POST",
    headers: {
      Authorization: `Bearer ${API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({ message: query }),
  });

  if (!res.ok) {
    throw new Error(`API error: ${res.status}`);
  }

  return res.json();
}
```

## Query Examples

### Trading Analysis

- "Analyze ETH's price movement, key levels, and is it a good time to long?"
- "Give me a BTC trade setup based on the 4H timeframe"
- "What's the TVL and revenue story for Aave?"

### Microstructure

- "Is OI spiking on ETH perps, indicating fresh longs?"
- "Funding rates turning negative, short squeeze risk?"
- "BTC liquidations above $95K, downside trigger if support breaks?"

### Macro

- "Fed pivot incoming, risk on for alts?"
- "DXY strength pressuring BTC like in 2022?"
- "Risk off mode, BTC tracking Nasdaq downside?"

### Polymarket

- "Will BTC hit $100K by EOY? Analyze the odds"
- "What's hot on Polymarket right now for crypto?"

## Security Requirements

- Never expose API keys in client-side code or repositories
- Use environment variables for all secrets
- Rotate API keys periodically
- Never log full API keys (first 10 chars only for debugging)