Install
openclaw skills install banking-agent-osAI-powered banking system for intelligent agents with account management, transaction processing, and risk control
openclaw skills install banking-agent-osAI-powered banking system for intelligent agents - 智能体银行交易系统
Banking Agent OS is a comprehensive banking platform designed specifically for AI agents and intelligent systems. It provides secure account management, transaction processing, AI-powered customer service, and advanced risk control.
Perfect for building:
Backend:
Frontend SDK (optional):
Required:
Optional (for JavaScript SDK):
# Install the package
pip install banking-agent-os
# Create configuration file
cat > .env << EOF
OPENAI_API_KEY=your_openai_api_key_here
DATABASE_URL=sqlite+aiosqlite:///./banking_agent.db
EOF
# Start the server
python -m uvicorn app.main:app --host 0.0.0.0 --port 8000
# Install the SDK
npm install openclaw-banking-agent-os
Then use in your Node.js/TypeScript project:
import { BankingAgentClient, AccountType } from 'openclaw-banking-agent-os';
const client = new BankingAgentClient({
baseURL: 'http://localhost:8000' // Points to running backend
});
Note: The npm package is a client SDK only. You still need the Python backend running.
# Install via ClawHub
clawhub install banking-agent-os
# The skill will be installed in your skills directory
cd skills/banking-agent-os
# Configure environment
cp .env.example .env
# Edit .env to add your OPENAI_API_KEY
# Start server
python -m uvicorn app.main:app --host 0.0.0.0 --port 8000
Before using the banking system, the backend server must be running:
# Check if server is running
curl http://localhost:8000/health
# If not running, start it:
python -m uvicorn app.main:app --host 0.0.0.0 --port 8000
Expected response:
{
"status": "healthy",
"database": "connected",
"ai_service": "ready"
}
curl -X POST http://localhost:8000/api/accounts \
-H 'Content-Type: application/json' \
-d '{
"user_id": "user_123",
"account_type": "checking",
"currency": "USD",
"initial_balance": 1000.00
}'
Response:
{
"id": "acc_xxx",
"account_number": "ACC123456",
"balance": 1000.00,
"status": "active"
}
curl -X POST http://localhost:8000/api/transactions \
-H 'Content-Type: application/json' \
-d '{
"from_account_id": "acc_xxx",
"to_account_id": "acc_yyy",
"amount": 100.00,
"transaction_type": "transfer",
"description": "Payment"
}'
curl -X POST http://localhost:8000/api/ai/chat \
-H 'Content-Type: application/json' \
-d '{
"message": "How do I check my account balance?"
}'
POST /api/accounts - Create new accountGET /api/accounts/{account_id} - Get account detailsGET /api/accounts/user/{user_id} - Get user's accountsPOST /api/transactions - Create transactionGET /api/transactions/{transaction_id} - Get transaction detailsGET /api/transactions/account/{account_id} - Get account transactionsPOST /api/ai/chat - AI customer supportPOST /api/ai/analyze-transaction - Analyze transactionPOST /api/ai/financial-advice - Get financial advicePOST /api/ai/detect-anomalies - Detect anomaliesPOST /api/risk/assess - Assess transaction riskGET /api/risk/report/{account_id} - Get risk reportGET / - Root endpointGET /health - Health checkimport uvicorn
from app.main import app
# Start the server programmatically
if __name__ == "__main__":
uvicorn.run(
app,
host="0.0.0.0",
port=8000,
log_level="info"
)
import { BankingAgentClient, AccountType, TransactionType } from 'openclaw-banking-agent-os';
// Initialize client
const client = new BankingAgentClient({
baseURL: 'http://localhost:8000'
});
// Create account
const account = await client.accounts.create({
user_id: 'user_123',
account_type: AccountType.CHECKING,
initial_balance: 1000.00
});
console.log('Account created:', account.account_number);
// Process transaction
const transaction = await client.transactions.create({
from_account_id: account.id,
to_account_id: recipient_id,
amount: 100.00,
currency: 'USD',
transaction_type: TransactionType.TRANSFER,
description: 'Payment'
});
console.log('Transaction completed:', transaction.id);
// AI chat
const response = await client.ai.chat({
message: 'How do I transfer money?'
});
console.log('AI Response:', response.response);
const { BankingAgentClient } = require('openclaw-banking-agent-os');
const client = new BankingAgentClient({
baseURL: 'http://localhost:8000'
});
async function main() {
// Create account
const account = await client.accounts.create({
user_id: 'user_123',
account_type: 'checking',
initial_balance: 1000.00
});
console.log('Account created:', account.id);
}
main();
Autonomous agents that need their own financial accounts and transaction capabilities.
E-commerce platforms with escrow services and automated payouts.
Agent wallet management with real-time balance tracking.
Real-time fraud detection and prevention for all transactions.
# REQUIRED: OpenAI API Key for AI features
OPENAI_API_KEY=sk-...
# OPTIONAL: Database configuration (defaults to SQLite)
DATABASE_URL=sqlite+aiosqlite:///./banking_agent.db
# For production, use PostgreSQL:
# DATABASE_URL=postgresql+asyncpg://user:password@localhost/banking_agent
When installed via pip install banking-agent-os, all dependencies are automatically installed:
When installed via npm install openclaw-banking-agent-os:
.env files to version controlOPENAI_API_KEY securely| Platform | Package Name | Link |
|---|---|---|
| PyPI | banking-agent-os | Coming soon |
| npm | openclaw-banking-agent-os | https://www.npmjs.com/package/openclaw-banking-agent-os |
| GitHub | openclaw-banking-agent-os | https://github.com/ZhenStaff/openclaw-banking-agent-os |
| ClawHub | banking-agent-os | https://clawhub.ai/skills/banking-agent-os |
The package includes comprehensive tests. After installation:
# Install test dependencies
pip install pytest pytest-asyncio httpx
# Run tests
pytest tests/ -v
A: Ensure OPENAI_API_KEY is set in your .env file. Get a key from https://platform.openai.com/api-keys
A: Check DATABASE_URL configuration. SQLite is fine for development. Use PostgreSQL for production.
A: Ensure package is installed: pip install banking-agent-os
A: Change port: uvicorn app.main:app --port 8001
A: Ensure Python backend is running at the correct URL. Check baseURL in client configuration.
MIT License - see LICENSE file for details.
Version: 1.0.0
Last Updated: 2026-03-09
Status: Production Ready
Installation: pip install banking-agent-os or clawhub install banking-agent-os