The AI advises. Code enforces.
nebula is a policy-aware AI treasury assistant on Mantle. It does real on-chain work — reading, analysing, swapping, lending, transferring — but every value-moving action runs through policy, simulation, and approval before it broadcasts.
Most “AI agents” for crypto are chat wrappers that either can’t touch funds or touch them with no real guardrails. We think the interesting problem is the opposite: give the agent genuine capability, then make it structurally unable to do the wrong thing.
So nebula splits the work. The model is advisory — it proposes typed intents and explains its reasoning, but it never holds keys. The controls are deterministic code and contracts: allowlists, caps, slippage and health-factor floors, RWA eligibility, simulation, and human approval for anything material. A wrong or jailbroken model still can’t breach a limit.
Identity is on-chain. Through ERC-8004 (Trustless Agents), an agent carries a verifiable identity and track record — so trust is checked, not claimed. That’s what we mean by verifiable autonomy.