Turn "what did our agents actually do?" into a question you can answer with a signed, verifiable record.
Assessors for SOC 2 or the EU AI Act want evidence that the record of automated decisions is complete and unaltered. Liceat's log is append-only and hash-chained, its head signed by the issuer key. You can export a self-verifying bundle: the auditor recomputes the Merkle root and re-runs the chain to confirm nothing was added, removed, or edited.
The public transparency endpoints disclose only leaf hashes — commitments, never the plaintext of who did what. A party holding an entry can prove its inclusion; nobody else learns its contents. Full plaintext is available only to the owner or the owning tenant.
Liceat is permission infrastructure for AI agents. You issue a warrant — a scoped, spend-capped, revocable token — that grants an agent narrow authority; the agent presents it at the point of action; Liceat enforces it (scope, spend, rate, holder-binding, revocation) and records every decision in a tamper-evident log. It is open source with a zero-dependency SDK for TypeScript and Python.
The SDK and self-hosted gateway are free and open source. The hosted gateway at liceat.com gives 10,000 free decisions with no card, then meters at fractions of a cent per decision — payable by card or USDC.
Free to self-host. 10,000 free decisions on the hosted gateway — no card.
Get an API key Read the docs