The payment firewall for AI agents
The security layer between an agent deciding to spend and the money moving.
Task ↔ purchase
Does the purpose match the submitted task context?
Amount + budget
Is it within transaction, daily, and velocity limits?
Counterparty
Is the vendor or address blocked or otherwise risky?
Wallet controls check limits and addresses. They do not check whether the purchase matches the job.
A valid wallet action can still be the wrong action for the job. Same amount, same category, same counterparty — and still the wrong purchase. Safe4 inserts an enforceable checkpoint.



x402
Start with the SDK, or read how the policy engine reaches a decision.
What is Safe4?
How does Safe4 work?
What does Safe4 evaluate?
How is Safe4 different from wallet controls?
What technologies does Safe4 use?
Is Safe4 a replacement for Circle Agent Wallet?
Get the SDK
Start integrating Safe4 into your agent. Check the quickstart guide for setup instructions.
Read the Docs
Full SDK reference, policy engine documentation, and integration patterns.
View on GitHub
Source code, examples, and contribution guidelines. Open issues and PRs welcome.
The rails for autonomous commerce are landing now. The control layer above them is still open.