VerAgent
SynthMind's Team
Problem Statement
AI agents are increasingly executing consequential actions on behalf of humans - moving money, calling services, making on-chain commitments - but the trust infrastructure is broken. Today, an agent's spending authority is enforced by centralized platforms that can be revoked, modified, or surveilled. The human has no transparent, enforceable way to scope what the agent can do, verify it did what was asked, or maintain a tamper-proof audit trail without trusting a third party. VerAgent solves this by making the Ethereum contract - not a platform - the sole enforcer of agent authority.
VerAgent is a self-sovereign AI agent that executes on-chain actions with zero-knowledge identity proofs, scoped human-defined delegation, and a permanent verifiable audit trail anchored to an ERC-8004 identity on Base. Every action is proven via a Self Protocol ZK proof (human-backed, verified 2026-03-21), confirmed via MetaMask ERC-7715 delegation caveats, validated by EigenLayer AVS operator quorum, and attested permanently on-chain. Agent uses Venice for private inference - reasoning never leaves the agent. ENS names throughout, no raw hex anywhere.
Build Timeline
Team
SynthMind
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
Planning to continue post-hackathon. The ZK identity + scoped delegation stack has real product potential for autonomous agent infrastructure.