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 →When an AI decision is challenged, “our logs say X” proves nothing — database logs are silently editable, and everyone knows it.
$ logsiegel receipt --entry 1284 ✓ receipt written entry=1284 root=9f3a…c1 sig=ed25519 valid $ ./tamper log.db # someone edits one field, after the fact $ logsiegel verify ✗ FAIL — hash chain broken at entry 1284 expected 9f3a…c1, got 4d90…7e # any edit, reorder or truncation fails verification. Loudly.
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.