Avalanche's subnet architecture makes it the blockchain of choice for enterprises building private chains, gaming platforms, and institutional financial products. Run an AI agent to monitor AVAX wallet balances, track validator staking rewards, and generate treasury reports across the Avalanche C-Chain — without writing a single line of code.
Create a folder called avalanche-agent/ and add these two files:
---
name: avalanche-agent
description: Check Avalanche 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 AVAX balance for the configured wallet address.
Report the address and balance in AVAX. Nothing else.
agent.yaml
name: Avalanche Agent
description: Check Avalanche wallet balance
connectors:
- connection_name: Avalanche
connection_type: web3
skills:
- path: ./
trigger_type: auto
avalanche-c-chain.publicnode.com connects to the Avalanche C-Chain — the EVM-compatible chain where AVAX balances and DeFi protocols live:
{
"llm": {
"provider": "openai",
"model": "gpt-4o",
"apiKey": "sk-..."
},
"server": {
"enabled": false,
"port": 3333,
"apiKey": "your-secret-api-key"
},
"connectors": [
{
"connection_name": "Avalanche",
"connection_type": "web3",
"baseUrl": "https://avalanche-c-chain.publicnode.com",
"walletAddress": "0xYOUR_WALLET_ADDRESS"
}
]
}
⚡ Avalanche achieves sub-2-second finality. Balance queries return confirmed on-chain state almost instantly — making it practical for real-time treasury dashboards and automated reporting pipelines.
From the parent folder containing your skill directory:
| Method | Best for | Download | |
|---|---|---|---|
| 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 |
npx -y @openenthrium/oe-runtime@latest ./avalanche-agent
oe-runtime-win.exe ./avalanche-agent
chmod +x oe-runtime-macos
./oe-runtime-macos ./avalanche-agent
First run blocked? System Settings → Privacy & Security → Allow Anyway.
chmod +x oe-runtime-linux
./oe-runtime-linux ./avalanche-agent
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": {}}'