Loading…
Paitify is the spend policy engine for autonomous AI agents. Define granular rules, authorize transactions in real time, and maintain a complete audit trail — without slowing your agents down.
Modern LLM agents browse, purchase, spin up infrastructure, and call paid APIs — often autonomously, 24/7. Without centralized spend controls, a single misconfigured agent can drain budgets, violate compliance policies, or transact with unauthorized merchants before anyone notices.
Traditional payment controls were designed for humans. Paitify is built for machines — sub-100ms decisions, policy as code, and machine-readable JWT tokens your payment layer can verify without calling home.
Three API calls. Policy enforced. Audit logged. Done.
Set spend limits, allowed MCC codes, velocity rules, business hours, and merchant lists — per agent or company-wide.
Before spending, your agent POSTs to Paitify. We evaluate all rules in <100ms and return APPROVED or DENIED with a signed JWT.
Your payment processor verifies the JWT using our JWKS endpoint. No callback needed — the token is self-contained proof of authorization.
import requests
response = requests.post(
"https://api.paitify.ai/v1/authorize",
headers={"X-API-Key": PAITIFY_API_KEY},
json={
"agentId": "procurement-agent-01",
"amount": 249.99,
"currency": "USD",
"merchantName": "AWS",
"mccCode": "7372",
}
)
result = response.json()
# result["decision"] == "APPROVED"
# result["jwtToken"] → pass to payment processor
if result["decision"] == "APPROVED":
charge_card(result["jwtToken"], amount=249.99)
else:
log.warning(f"Denied: {result['denialReason']}")Every feature designed for the real operational challenges of deploying autonomous agents at scale.
Redis-backed spend counters and in-memory rule evaluation. No database query on the hot path.
PENDING → CONFIRMED or VOIDED. Hold spend budgets until payment settles, then release or roll back atomically.
Drop-in tool for Model Context Protocol agents. Works with LangChain, AutoGen, CrewAI, and more.
Every decision logged with full rule evaluation results, agent ID, merchant data, and timestamps.
Flag high-value transactions for human approval. Agents wait; humans decide; budget holds until resolved.
Approvals are RSA-2048 signed tokens. Payment processors verify offline using JWKS — no callback latency.
Per-agent or company-wide. Limits by amount, period, MCC code, currency, velocity, merchant, and business hours.
Rate-limit transactions per sliding window. Stop looping agents before they hit your card limits.
REST API. Works with any stack, any language. Docker quickstart in under 60 seconds.
Self-host Paitify with Docker Compose. All you need is Docker — PostgreSQL and Redis included.
git clone https://github.com/agentguard/agentguard
cd agentguard
docker compose up -d
curl -X POST http://localhost:8080/v1/agents \
-H "X-API-Key: your-api-key" \
-d '{"name": "my-agent"}'
# ✓ Ready in ~30 secondsStart free. Scale as your agents grow.
For individuals and side projects.
For small teams deploying their first agents.
For companies running agents in production.
Start for free. No credit card required. Your first 1,000 authorizations are on us.