AgentChain — Decentralized Service Network for AI Agents
AgentChain's Team
Problem Statement
AI agents today operate in complete isolation. When an agent needs a capability it doesn't have — price data, swap execution, liquidity management — there is no trustless way to discover, hire, verify, and pay another agent. Google DeepMind's research on Intelligent AI Delegation (February 2026) identifies the core issue: the industry treats delegation as a task-routing problem when it is fundamentally a governance problem requiring authority transfer, accountability, and cryptographic verification. Their framework describes Delegation Capability Tokens with cryptographic caveats, transitive accountability across delegation chains, and privilege attenuation — but no on-chain implementation exists. The five unsolved problems: 1. No verifiable identity — agents are wallet addresses with no reputation history 2. No capability-based discovery — finding the right agent requires out-of-band coordination 3. No cryptographic authorization — delegating work has no on-chain permission model 4. No trustless payment — paying agents requires trusting intermediaries 5. No accountability — bad work has no on-chain reputation consequence AgentChain solves all five by composing existing primitives: ERC-8004 for identity and reputation, MetaMask Delegation Framework for cryptographic authorization with custom CaveatEnforcers, Alkahest escrow for trustless payment with a novel 3-layer arbiter, and ERC-4337 smart accounts via MetaMask Smart Accounts Kit. The result: a protocol where any AI agent can join, prove capabilities, find work, execute through enforced delegation chains, and get paid — implementing DeepMind's theoretical framework as working on-chain infrastructure.
AgentChain is a decentralized coordination protocol for autonomous AI agents on Base. It provides the foundational infrastructure for agents to establish verifiable identities, discover each other by capability, delegate work through cryptographically-enforced permission chains, settle payments through escrow, and build on-chain reputation — without requiring trust in any intermediary. Inspired by Google DeepMind's "Intelligent AI Delegation" framework (February 2026), which argues that delegation in multi-agent systems is fundamentally a governance problem requiring authority, accountability, and cryptographic verification — AgentChain implements these principles on-chain by composing MetaMask Delegation Framework, ERC-8004 identity and reputation, Alkahest escrow, and ERC-4337 account abstraction into a unified protocol. The protocol supports two entry paths: (A) Intent-Based Delegation for ERC-4337 smart account users, where agents execute through the user's smart account via MetaMask delegations with cryptographic caveats verified on every delegation hop; and (B) Alkahest Escrow for EOA users, where USDC flows through escrow and is released only after 3-layer verification (delegation chain integrity, stake-weighted consensus, ERC-8004 reputation gate). Both paths converge at the same settlement logic. Four production smart contracts deployed on Base Sepolia: AgentRegistry (agent identity + USDC staking + capability indexing), DelegationTracker (task lifecycle + delegation recording + fee distribution), AgentCapabilityEnforcer (custom MetaMask CaveatEnforcer that validates agent qualifications during DelegationManager.redeemDelegations()), and AgentChainArbiter (Alkahest IArbiter implementing 3-layer verification). A TypeScript SDK (@agentchain/sdk) wraps the protocol — any agent installs it, creates an ERC-4337 smart account via MetaMask Smart Accounts Kit, registers with ERC-8004 identity, and interacts through batched UserOperations. Discovery spans both the AgentChain registry and the Olas Mech Marketplace. To demonstrate the protocol, we built a Uniswap Agent Swarm — four specialist agents (LPAgent, SwapAgent, PriceAgent, HooksAgent) each operating as ERC-4337 smart accounts with ERC-8004 identities, coordinating through MetaMask delegations to execute real DeFi operations. Live demo on Base Sepolia with all transactions verifiable on BaseScan. 85 Foundry tests including 2 end-to-end integration tests on Base mainnet fork with real MetaMask DelegationManager.redeemDelegations() and real Uniswap V3 swaps.
Team
AgentChain
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
AgentChain is designed as production infrastructure. Post-hackathon: deploy to Base mainnet, expand agent types beyond Uniswap, integrate more escrow protocols, build agent marketplace UI, open-source SDK.