Vuppala Anand Vardhan @Vardhan_v

CryptoMind AI is a fully autonomous crypto trading agent built solo for the lablab.ai AI Trading Agents Hackathon. It operates on a 15-minute trading cycle across three pairs: BTC/USD, ETH/USD, and SOL/USD. The agent pulls live market data via Kraken CLI, calculates technical indicators (RSI, SMA, EMA, MACD, Bollinger Bands) using Python's ta library, and sends a structured analysis prompt to Groq's LLaMA 3.3 70B model. The AI returns a JSON decision: BUY, SELL, or HOLD — with confidence score, position size, stop-loss, and take-profit targets. A key engineering challenge was building from India, where Kraken account creation is blocked. The entire agent was built and tested using Kraken CLI's paper trading mode with live market data — no real account required. This became a feature: the agent is fully functional for anyone in a restricted region. Over 5 days of autonomous operation, CryptoMind AI executed 150 trades across all three pairs, achieving a 51.5% win rate. The system includes a portfolio reconciliation function (reconcile_state()) to fix state desync bugs, a force_decisive mode after 3 consecutive HOLDs, and a SELL guard that prevents selling assets not currently held. Tech stack: Python + Kraken CLI (subprocess) + Groq API (llama-3.3-70b-versatile with llama-3.1-8b-instant fallback on rate limits) + Claude Code as the development tool.

⏱️ Design, build, and deploy trustless AI trading agents. 📅 March 30 – April 12, 2026 🌐 Build AI trading agents that execute strategies using ERC-8004 or Kraken CLI. 🤝 Build solo or in teams to create autonomous trading, risk, yield, or protection agents. 💰 $55,000 prize pool, allocated and shared via Surge and Kraken. Your team should have registered project at early.surge.xyz in order to be eligible for the prize. Get access in your team profile or our discord 🔑 Access to early.surge.xyz If prompted for login credentials, use: • Username: admin • Password: JBRv2xWG7AzwVrLz88