Frisk

Pre-transaction risk screening for autonomous AI agents.

Before your agent pays an x402 seller or calls an unfamiliar tool, ask Frisk whether the counterparty is trustworthy and whether the transaction fits your policy. Frisk returns a verdict —allow,review, orblock— with a trust score and human-readable reasons. It is advisory: your agent stays in control of the decision.

import { Client } from "frisk-screen"; const client = new Client(); // lite mode, no key required const result = await client.screen("0x9a3f1b2c3d4e5f60718293a4b5c6d7e8f9a0bc12", { endpoint: "https://api.seller.x402/quote", amount: 2.5, asset: "USDC", policy: { maxPerCall: 5.0 }, }); if (!result.allowed) { console.log(result.verdict, result.trustScore, result.reasons); }

Both expose the same model: aClientwith ascreen()call, alitemode that runs locally with zero dependencies, and an optional hosted mode for reputation history and live threat intelligence.

Lite mode catches obvious problems — malformed counterparties,payToswaps, insecure endpoints, policy violations, and a small seed blocklist — without a network call. The hosted API (https://api.tryfrisk.dev) adds reputation history and continuously updated threat intelligence.

- Advisory, not in-path.Frisk never holds your funds or blocks a payment itself; it returns a verdict and your code decides.
- Zero runtime dependencies.The TypeScript SDK is built on the platformfetchAPI (Node, Bun, Deno, Workers, browser); the Python SDK uses only the standard library.
- Typed.Both SDKs ship with full type information.

SeeCONTRIBUTING.md. Security disclosures:SECURITY.md.

The hosted API atapi.tryfrisk.devis additionally governed by theTerms of Service.

Financial and quantitative modeling engine for AI agents. Typed, named, deterministic.