Capture what your AI did.
Verify the record.
Your agents take real actions on their own — approve refunds, move money, make calls for your customers. Swarrm gives each captured action a signed receipt in a tamper-evident log. If a decision is questioned, you hold a self-contained E1 bundle whose integrity anyone can check offline, without an account.
“Our logs say so” isn’t proof.
Editable logs ask a later reviewer to trust whoever controlled them. A signed, checkpointed log gives that reviewer integrity checks they can rerun.
Your logs can be edited
Whoever controls a conventional database may be able to rewrite it. That weakens the record precisely when its history matters.
The AI vendor can’t vouch for itself
A platform grading its own AI’s homework is not enough. A separate verifier can test signatures and log structure without calling the producer.
Integrity checks have to survive the wait
Incidents and reviews show up months later. A self-contained bundle keeps the base integrity checks available to someone who was not there.
Four steps. No black box in the black box.
Plain enough to follow, real enough to hand your engineer or your auditor. The technical name for each step is on the right.
Recording is designed to stay outside the agent's critical path, and the gateway supports fail-open operation. Swarrm is Beta: validate capture, persistence, and failure behaviour in your own setup before relying on it.
Don’t take our word for E1 integrity.
Drop a real bundle into your browser and check its signed receipts and log structure offline. Then change one character and watch base verification fail. Anchor and timestamp fields remain labelled claims.
Start free, on your own machine.
No account, no cloud bill, no sales call. Install it, run the demo, and inspect an E1-verified record locally.
Executive briefing
A one-page summary: what Swarrm proves today, what is withdrawn, and what higher assurance still requires.