Sentinel Transaction Safety

Pre-execution transaction safety oracle for autonomous AI agents. Before signing an on-chain transaction, an agent calls SENTINEL and receives a SAFE / UNSAFE / UNKNOWN verdict, a standardized SENTINEL Score (0-100, grade AAA-D), and an ed25519-signed receipt. Checks contract security (GoPlus), execution simulation (Alchemy eth_call), honeypot detection (honeypot.is), and LP concentration/rug risk. Pay-per-call via x402 ($0.005 USDC on Base) — no accounts, no API keys, no SDK required. No free trial.

by @teodorofodocrispin-cmyk·MIT-0