Logsiegel

Prove your AI didn't lie.

Logsiegel gives AI systems and agents a tamper-evident action trail — every step hash-chained and signed, verifiable offline by anyone you hand a receipt to. Open source, no blockchain, runs where your agent runs.

Join the waitlist →
Early access · Apache 2.0 · Python SDK

When an AI decision is challenged, “our logs say X” proves nothing — database logs are silently editable, and everyone knows it.

The receipt still verifies offline — with the public key alone.

Provable, not just observable.

Observability shows what happened. Logsiegel makes it provable: any after-the-fact edit, reorder or truncation fails verification — loudly.

Receipts for single actions.

Hand a customer, auditor or ombudsperson one log entry plus its proof. They verify it offline with your public key alone — no access to your systems, no account, no trust required.

Privacy built in.

Only hashes and metadata enter the log. Content stays encrypted, maskable, and deletable (crypto-shredding) — GDPR deletion rights and tamper-evidence stop being a contradiction.

How it works

pip install logsiegel  →  plug in the adapter (LiteLLM today, MCP proxy for agents coming)  →  checkpoint, verify, done.

Early access to the agent-trail SDK as it lands

MCP proxy, mandate binding, browser verifier. Waitlist members shape the roadmap; pilot teams get hands-on integration support.

Join the waitlist →

Have a pilot code? Skip the line.