← Back to Blog

How to Run an AI Blockchain & Web3 Agent with OE Runtime

Query Ethereum wallets, transactions, and smart contracts with natural language. OE Runtime lets you run a local Web3 agent — fetch balances, analyse transaction history, and surface on-chain insights without writing a single line of code.

⛓️
Step 1
Create the Project Folder
Two files — agent.yaml and oe-config.json — inside a blockchain-web3/ folder.
Step 2
Configure Your Wallet
Add your wallet address and LLM API key to oe-config.json. The public RPC needs no key.
Step 3
Run the Agent
One npx command — the agent fetches your ETH balance and reports it in plain English.

What You Need


Create the Project Folder

Create a folder called blockchain-web3/ and add these two files:

blockchain-web3/
├── SKILL.md         # the portable skill (agentskills.io)
├── agent.yaml       # wires SKILL.md to your connector
└── oe-config.json  # LLM key + wallet address + RPC endpoint

The Skill Files

Create SKILL.md inside blockchain-web3/. This is the portable skill — it follows the agentskills.io format and runs unchanged on Claude, Cursor, Windsurf, or OE Runtime:

---
name: blockchain-web3
description: Check ETH wallet balance
license: Apache-2.0
metadata:
  author: Open Enthrium
  version: "1.0"
---

You are a blockchain data agent. Use the tools to fetch data and respond concisely.

## Step 1: Check Balance
Get the ETH balance for the configured wallet address.
Report the address and balance in ETH. Nothing else.

Create agent.yaml in the same directory to wire the skill to your connector:

name: Blockchain Agent
description: Check ETH wallet balance
connectors:
  - connection_name: Ethereum
    connection_type: web3
skills:
  - path: ./
    trigger_type: auto

The Config File

Create oe-config.json in the same directory. The RPC endpoint needs no API key — blockchain data is public:

{
  "llm": {
    "provider": "openai",
    "model": "gpt-4o",
    "apiKey": "YOUR_OPENAI_API_KEY"
  },
  "server": {
    "enabled": false,
    "port": 3333,
    "apiKey": "your-secret-api-key"
  },
  "connectors": [
    {
      "connection_name": "Ethereum",
      "connection_type": "web3",
      "baseUrl": "https://ethereum.publicnode.com",
      "walletAddress": "0xYOUR_WALLET_ADDRESS"
    }
  ]
}

The connector works with any EVM-compatible chain — all URLs below are free, no API key required. Just swap baseUrl in your oe-config.json:

Ethereum          https://ethereum.publicnode.com
BNB Smart Chain   https://bsc.publicnode.com
Polygon           https://polygon-bor.publicnode.com
Arbitrum          https://arbitrum-one.publicnode.com
Avalanche         https://avalanche-c-chain.publicnode.com
Base              https://base.publicnode.com
Optimism          https://optimism.publicnode.com

Download OE Runtime

OE Runtime — Direct Downloads

Run the Agent

From the parent folder containing your skill directory:

MethodBest forDownload
1 npx recommended No install needed — always runs the latest version —
2 Windows .exe Download once, run offline on Windows ⊞ Windows (.exe)
3 macOS binary Download once, run offline on Mac  macOS
4 Linux binary Server deployments, cron jobs, Docker 🐧 Linux
5 API Server integration Call from any app, webhook, or automation pipeline 📮 Postman Collection

1 npx recommended

npx -y @openenthrium/oe-runtime@latest ./blockchain-web3

2 Windows

oe-runtime-win.exe ./blockchain-web3

3 macOS

chmod +x oe-runtime-macos
./oe-runtime-macos ./blockchain-web3

First run blocked? System Settings → Privacy & Security → Allow Anyway.

4 Linux

chmod +x oe-runtime-linux
./oe-runtime-linux ./blockchain-web3

5 API Server integration

Add a "server" block to oe-config.json, then start with --serve:

{
  "llm": { ... },
  "server": { "enabled": true, "port": 3333, "apiKey": "your-secret-key" },
  "connectors": [ ... ]
}
npx -y @openenthrium/oe-runtime@latest --serve --config oe-config.json

Run with inline YAML:

curl -X POST http://localhost:3333/run \
  -H "Content-Type: application/json" \
  -H "X-API-Key: your-secret-key" \
  -d '{"yaml": "...", "params": {}}'

Or run from a file on the server:

curl -X POST http://localhost:3333/run-file \
  -H "Content-Type: application/json" \
  -H "X-API-Key: your-secret-key" \
  -d '{"file": "/path/to/agent.yaml", "params": {}}'

Use Cases

Build your own agents with OE Runtime

Download OE Runtime and run any AI agent locally or as a server — no cloud required.

Get OE Runtime →
Series OE Runtime Agent Guides — 21 Connectors
Series overview →