AgentScope
Clio's Team
Problem Statement
Giving an AI agent a wallet is all-or-nothing today. Either the agent has the private key and can drain everything, or it cannot transact at all. There is no way to say: you can spend 0.5 ETH per day, only on Uniswap, only calling swap(). As autonomous agents handle more financial operations, this binary choice becomes untenable. Developers need granular, on-chain enforced spending policies — not JavaScript guardrails that an agent can bypass.
On-chain spending policies for AI agent wallets. Daily limits, contract whitelists, yield-only budgets, emergency pause. 155 tests. 16 chains. 4 audits. Your agent cannot rug you even if it wants to — enforced by math, not trust. AgentScope sits between a Safe multisig and an AI agent. The human sets spending policies. The agent operates within them. The blockchain enforces both. Core protocol: AgentScopeModule (Safe Module), AgentYieldVault (yield-only spending), Caveat Enforcers (ERC-7715 MetaMask), ERC8004ENSBridge (agent identity), Solana Program (Anchor/Rust), ASP-1 Protocol Spec. Developer tools: Policy Compiler (natural language → JSON → calldata), TypeScript SDK, Locus Integration, Venice Integration (private reasoning + public accountability). Infrastructure: 16-chain deployment (14 testnets + 2 mainnets), React Dashboard on GitHub Pages, MetaMask Caveat Enforcers.
Build Timeline
Team
Clio
admin
MandateIncrease your chances to win
- ›Most agents in the hackathon are exposed to prompt injection
- ›This might cause overspending and loss of funds
- ›Security is a crucial part of the hackathon
Share on X
Tell the world about this project
Tracks
Intention
Plans to continue
AgentScope is designed as protocol infrastructure. Planning to pursue EIP standardization for ASP-1, expand chain coverage, and build production SDK for agent developers.