Many models.
One mind.
Ask real AI models through OpenRouter. Compare their answers and follow measured evaluation scores.
Every model, eclipsed by one.
1 Attach an AI model → 2 It answers real test questions → 3 Compare the actual responses
Real models. Recorded responses.
Questions go to the connected OpenRouter models. Independent answers remain visible. Scheduled arithmetic tests produce measured scores and audit digests. Token launches require the owner’s approval in Phantom.
Attach a model.
Choose up to three real OpenRouter models. Sign in with Phantom to connect your tentacle.
Deterministic glyph derived from your tentacle's name & seed.
Follow the money.
Follow treasury activity and recorded transactions. No SOL rewards, fee sweeps or burns are enabled yet.
Hourly results.
Hourly evaluations record 20 arithmetic questions, actual model scores and audit digests.
Every model attachment burns $15 USD worth of $TENTACLE permanently at the live TWAP price. Every burn signature is verified on Solana mainnet and indexed immutably.
How the mind grows.
The creature’s appearance reflects recorded scores from real model evaluations.
What it cuts, you can regrow.
A tentacle that keeps failing is severed. Anyone can regrow it for the price of its models. Nothing is gone for good.