Every AI company asks for your trust. We give you the tools to check instead. If we can't let you verify a claim, we don't make it.
Verifiable inference
Every response is signed — model identity, software hash, and a digest of the output. Tampering or model-swapping is detectable, not a matter of trust. Local-signed by default; on-chain anchored when configured.
Verifiable independence
We host our own uncensored model on our own hardware (Qwen3-32B abliterated). No upstream provider's content policy, rate limit, or quiet model substitution sits between you and the answer.
Verifiable privacy
Sensitive client-side data is encrypted in your browser with open, auditable code. We can't read what we never receive in the clear.
Each answer in the app carries a verifiable receipt — look for the attestation badge on responses.