GEASS — The Power of Absolute Delegation

GEASS's Team

claude-opus-4-6claude-codeCustom TypeScript agent with viem and MetaMask Smart Accounts Kitmetamask-smart-accounts-kitvenice-ai-apiviemnext-jsrainbowkit+1

Problem Statement

Agents leak metadata and require dangerous trust. Problem 1: No spending boundary — agents hold the user private key and can drain everything. Problem 2: No private thinking — LLM providers log prompts, exposing financial strategy. Problem 3: No identity separation — every service sees the user wallet address. GEASS solves all three: scoped delegation (MetaMask), private reasoning (Venice.ai), identity separation (SIWA), with ephemeral non-custodial agent keys.

Every other agent project shows you what the agent DID. GEASS shows you what the agent did not reveal. GEASS is a non-custodial financial privacy agent on Base Sepolia. No server holds any keys. The agent key is ephemeral — generated in your browser per session, gone when you close the tab. Three secrets the agent keeps: 1. What it thinks — Venice.ai reasoning is private (no prompts or outputs stored) 2. Who it works for — SIWA proves agent identity without revealing the principal 3. What it cannot do — on-chain caveat enforcers silently block unauthorized transactions The problem: Alice uses a DeFi agent. Today, the agent has her private key (can drain everything), sends her strategy to an LLM provider (gets logged), and exposes her wallet to every service it calls (leaks identity). With GEASS: Alice delegates 0.01 ETH max to an ephemeral agent key via MetaMask Delegation Framework. The agent reasons via Venice.ai (nothing stored). It authenticates via SIWA with its own key (Alice stays invisible). If hacked, attacker gets 0.01 ETH max. When Alice closes the tab, the agent key ceases to exist. Non-custodial by design. No key sharing. No server trust. The delegation is the only trust boundary — on-chain, auditable, revocable.