Agentic EVM Blockchain Processor

An intelligent agent system that generates production-ready Go code for EVM blockchain monitoring, using Groq's ultra-fast LLM inference.

What is EVM?

The Ethereum Virtual Machine (EVM) is a decentralized runtime environment that executes smart contracts on Ethereum and 50+ compatible blockchains (Polygon, BSC, Avalanche, etc.). It enables:

• DeFi applications (trading, lending, borrowing)
• NFTs (digital ownership, marketplaces)
• DAOs (decentralized governance)
• Smart contracts (trustless, transparent code execution)

Your system monitors the EVM (read-only) - it observes blockchain activity without executing transactions.

Architecture

┌─────────────────────────────────────────────────────────────────┐ │ PYTHON AGENT (Orchestrator) │ ├─────────────────────────────────────────────────────────────────┤ │ CONFIG → PLAN → GENERATE → TEST → VALIDATE → EXECUTE → FIX │ │ ↑_______________________________________________________↓ │ │ GROQ LLM | │ └─────────────────────────────────────────────────────────────────┘ │ ▼ generated/ ┌─────────────────────────────────────────────────────────────────┐ │ GO BACKEND (EVM Processor) │ ├─────────────────────────────────────────────────────────────────┤ │ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ │ │ │ Blockchain │ │ Metrics │ │ REST API │ │ │ │ Client │→│ Collector │→│ Server │ │ │ └─────────────┘ └─────────────┘ └─────────────┘ │ │ ↓ ↓ ↓ │ │ ETH RPC TPS Calc :8080/metrics │ └─────────────────────────────────────────────────────────────────┘ │ ▼ ┌─────────────────────────────────────────────────────────────────┐ │ REACT DASHBOARD │ ├─────────────────────────────────────────────────────────────────┤ │ • Real-time Block Height • TPS (blocks/sec) │ │ • Gas Price (Gwei) • Pending Transactions │ └─────────────────────────────────────────────────────────────────┘

text

Project Structure

agentic-evm-processor/ ├── agent/ # Python agent (orchestrator) │ ├── core/ # Agent loop, state, Groq client │ └── stages/ # 7-stage pipeline (config → fix) ├── configs/ # YAML configuration files ├── dashboard/ # React frontend │ ├── src/ │ │ ├── App.tsx │ │ └── pages/Dashboard.tsx │ └── package.json ├── generated/ # Created by agent (not committed) │ ├── cmd/processor/ # Go main entry point │ ├── internal/ # Blockchain client, API server │ └── go.mod ├── .env # API keys (never commit) ├── .env.example # Template for API keys ├── requirements.txt # Python dependencies └── run_agent.py # Start the agent

What the Agent Does

The agent executes a 7-stage loop to generate the Go backend:

Stage	Purpose
CONFIG	Loads agent_config.yaml and chain_config.yaml
PLAN	Creates build plan based on configuration
GENERATE	Writes Go code (blockchain client, API server, main.go)
TEST	Runs go test on generated code
VALIDATE	Checks formatting, linting, module dependencies
EXECUTE	Builds and runs the Go binary
FIX	Auto-fixes compilation errors (uses Groq)

What the Generated Go Backend Does

Once generated, the Go binary:

• Connects to Ethereum RPC endpoint (read from .env)
• Fetches real-time blockchain data:
  • Current block height
  • Gas price (in Gwei)
  • Pending transaction count
  • Calculates TPS (blocks per second)
• Exposes REST API at :8080/api/metrics
• Serves CORS-enabled endpoints for the dashboard

Prerequisites

• Python 3.9+ (for the agent)
• Go 1.21+ (to run generated code)
• Node.js 18+ (for dashboard)

Required API Keys

1. GROQ_API_KEY (for the agent)

• Purpose: LLM inference for code generation
• Get it: console.groq.com (free tier available)
• Where to use: .env file

2. ETH_RPC_URL (for the Go backend)

• Purpose: Fetch real blockchain data
• Get it: alchemy.com or infura.io (free tier)
• Where to use: .env file
• Without it: Backend runs in mock mode (static data)

Setup & Execution

# 1. Clone and enter directory
cd agentic-coding-evm-processor

# 2. Install Python dependencies
pip install -r requirements.txt

# 3. Setup dashboard
cd dashboard && npm install && cd ..

# 4. Configure API keys
cp .env.example .env
# Edit .env and add your GROQ_API_KEY and ETH_RPC_URL

# 5. Run the agent (generates Go code for bsckend)
python run_agent.py

# 6. Start the generated Go backend
cd generated
go mod tidy
go run cmd/processor/main.go

# 7. Start the dashboard (new terminal)
cd dashboard
npm start
Dashboard Access
Dashboard: http://localhost:3000

API (served by Go): http://localhost:8080/api/metrics

Health: http://localhost:8080/api/health

Testing the API
bash
curl http://localhost:8080/api/metrics
Expected response (example):

json
{
  "blockHeight": 18500000,
  "transactionsPerSecond": 0.12,
  "gasPrice": 35,
  "pendingTransactions": 127
}
Agent Behavior
With GROQ_API_KEY: Groq s requires for intelligent code generation

With ETH_RPC_URL: Real blockchain data

Without ETH_RPC_URL: Mock blockchain data (static values)

Environment Variables

bash
# Required for agent intelligence
GROQ_API_KEY=your_groq_key

# Required for real blockchain data
ETH_RPC_URL=https://eth-mainnet.g.alchemy.com/v2/your_key

# Optional: Change default ports
DASHBOARD_PORT=3000
API_PORT=8080
Common Issues
Issue	Solution
Port 8080 already in use	lsof -i :8080 then kill -9 <PID>
Dashboard shows 0.0 for gas price	API returning hex - check curl output
Module not found: react-scripts	Run npm install in dashboard directory
go.mod file not found	Agent generates it - run python run_agent.py first
Advanced: eRPC Proxy
For production deployments, consider using eRPC - an open-source proxy that aggregates multiple RPC endpoints for failover, caching, and load balancing.

License
MIT