AgentShield — Firewall for AI Agent Spending

Stop runaway AI agents before they burn your budget. 9 composable rules evaluated per-transaction in <1ms. Pure Python stdlib — zero dependencies.

Install

pip install agentshield

Quick Start

from agentshield import SpendControlEngine

engine = SpendControlEngine()

# A transaction your agent wants to make
transaction = {
    "amount": 500.00,
    "merchant": "openai-api",
    "category": "llm_inference",
    "agent_id": "my-agent",
    "timestamp": "2026-08-10T10:00:00Z",
}

# Your spend-control rules
rules = [
    {"id": "r1", "type": "transaction_limit", "priority": 1,
     "params": {"max_amount": 250}, "action": "BLOCK"},
    {"id": "r2", "type": "daily_total", "priority": 2,
     "params": {"max_daily": 2000}, "action": "BLOCK"},
    {"id": "r3", "type": "velocity", "priority": 3,
     "params": {"window_minutes": 60, "max_count": 10}, "action": "FLAGGED"},
]

# Prior transactions today (for daily_total and velocity checks)
prior_transactions = []

# Evaluate — returns in <1ms
result = engine.evaluate(transaction, rules, prior_transactions)
print(result["decision"])  # BLOCKED
print(result["reason"])    # Transaction amount $500.00 exceeds limit of $250.00

Rule Types (9)

Eval Gym (56 scenarios)

from agentshield import run_eval

results = run_eval()
print(f"{results['passed']}/{results['total']} passed")  # 56/56

All 56 test scenarios are MIT licensed. Use them as test fixtures for your own spend-control implementation.

Key Design Decisions

• Pure Python 3.11 stdlib — no pip install required (except for the package wrapper itself)
• Decimal for money — never float, always decimal.Decimal
• Stateless — no file I/O, no network, no global state
• Deterministic — same inputs always produce the same output
• <1ms per evaluation

Links

• Live Demo
• Eval Gym Spec
• Risk Calculator
• GitHub

License

MIT