I gave my AI agent a cryptographic identity. Here is what changed.

Description and use

AgentPass gives AI agents a cryptographic identity, enabling signed actions, automatic revocation, and easy framework integration.

Problem

AI agents lack verifiable identity, trust level, and signed evidence of actions, making it hard to audit and control their behavior.

Outcome

AgentPass provides zero‑trust identity for AI agents, enabling cryptographic proof of actions, automatic revocation, and seamless integration across frameworks with minimal setup.

Workflow

• Install AgentPass via npm: npm install -g @proofxhq/agentpass
• Add AgentPass MCP server to LLM config (e.g., Claude Desktop) with AGENTPASS_URL
• Restart LLM to load seven new tools
• Create an agent with a command like "Create an AI agent called \"my-scanner\" with capabilities read and query."
• AgentPass generates a key pair, requests a signed certificate, and stores it locally
• Use the agent to sign actions; the signature is verified server‑side
• If needed, revoke the agent with a command; future actions are refused
• Certificates auto‑renew at 80% TTL; revocation stops renewal
• Integrate AgentPass into frameworks (CrewAI, LangChain, OpenAI SDK) with a single import
• Optionally deploy AgentPass Mesh, Inference, OPA, or DB extensions for deeper enforcement

Evidence

AgentPass generates an ECDSA P-256 key pair on your machine. The private key never leaves. A certificate signing request goes to the API. You get back a signed X.509 certificate with your agent's trust level and capabilities embedded as OID extensions

Source

Revoke it immediately. Revoked. Every future action refused. The revocation is permanent and cannot be bypassed by re-registering the same name.

Source