AgentStamp
Trust intelligence for AI agents — identity stamps, reputation scoring, and verified passports
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for AgentStamp, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
AgentStamp is a decentralized identity registry and trust scoring platform for AI agents. Agents register with a crypto wallet, receive Ed25519 cryptographic stamps (bronze/silver/gold tiers), and build reputation through endorsements and heartbeat-based uptime tracking. Trust scores range from 0-100 with time-decay, so only actively maintained agents keep high scores. Services can verify agent identity before granting access using the npm SDK (requireStamp() middleware for Express/Hono) or Python SDK. Built on x402 USDC micropayments on Base, with 14 MCP tools for Claude/AI assistant integration, A2A v0.3 passport protocol support, and ERC-8004 compatibility. Open source, developer-first, free tier available.
Key features and capabilities
- Ed25519 cryptographic identity stamps (bronze/silver/gold tiers)
- Trust scoring 0-100 with time-decay and heartbeat tracking
- 14 MCP tools for Claude and AI assistant integration
- x402 USDC micropayments on Base for pay-per-verification
- Express/Hono middleware SDK — gate APIs with requireStamp()
Use cases
- Verify AI agent identity before granting API access
- Build agent reputation through endorsements and uptime tracking
- Gate paid services behind trust-verified agent stamps
- Multi-agent coordination with verifiable identity
- Supply chain security for AI agent skills and plugins