An assistant should remember.
An AI that forgets who you are every morning is not an assistant. It is a stranger wearing a familiar voice. Tanya runs a seven-level memory system — from working memory to biographical — so the relationship compounds instead of resetting.
An assistant should say "I don't know."
Hallucinations are not bugs. They are the predictable output of systems optimised to sound fluent rather than to be calibrated. Tanya is built around an anti-hallucination engine that checks claims against grounded sources. When confidence is low, Tanya tells you.
An assistant should evolve.
The pace of AI research is inhuman. No model trained six months ago is current. Tanya continuously watches the ecosystem and auto-integrates new, vetted capabilities — so you never wake up to a stale tool.
An assistant should be yours.
Self-host Tanya on your own machine for total sovereignty, or use the managed cloud if you prefer. The core is MIT licensed. Your data, your memory, your choice.
An assistant should be built in the open.
No black boxes. No marketing leaps. Every sprint ships behind public issues, public plans, and honest changelogs. If Tanya fails, you will see it fail. If it breaks new ground, you will see exactly how.
An assistant should act when it matters.
Apple Intelligence parity is the floor, not the ceiling. The differential we are building toward is agency — the ability to surface unprompted when something deserves your attention. Manifestations are scarce, earned, and always under your structural consent.
This is the minimum bar for a cognitive partner in 2026.
Anything less is just a chatbot.