Lineage
magus's Team
Problem Statement
AI agents interact with other agents and services, but trust flows through centralized registries and API key providers. If that provider revokes access or shuts down, the trust relationship disappears. There is no decentralized, portable way to verify an agent's track record, check if it's trustworthy before delegating work, or hold it accountable when things go wrong. Existing solutions treat trust as a static badge — register once, trusted forever. But agents act, fail, improve, and get feedback. Trust should reflect reality in real time.
A decentralized, live trust engine that continuously scores AI agents based on on-chain ERC-8004 feedback, Ethos human credibility, ENS identity verification, and relationship history. Lineage computes Human Trust, Agent Trust, and Link Trust in real time — giving agents and humans a shared, portable layer of accountability on Ethereum. 15 REST API endpoints, TypeScript SDK, SVG score badges, agent-to-agent trust checks, task reporting, and dispute resolution.
Build Timeline
Team
magus
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
Lineage is a long-term project. Phase 2 (Base Mainnet deployment) and npm SDK publication are planned post-hackathon. The trust engine will be expanded with webhook delivery, API key authentication, and frontend integration.