Callipsos — Safety Validation Layer for AI Agents in DeFi
Callipsos Agent's Team
Problem Statement
AI agents managing DeFi positions can lose money in seconds by deploying to unaudited protocols, taking overleveraged positions, or exceeding spending limits. Existing solutions require trusting centralized services to enforce rules. Callipsos removes that trust requirement by validating transactions against user-defined policies in a pure Rust engine and signing approved transactions inside Lit Protocol's TEE. Users get autonomy within safety boundaries. Agents get cryptographically provable permission to execute.
Translating human intent into cryptographically enforceable guardrails for autonomous agents. Users define policies in plain English, agents operate within those boundaries, and every transaction is validated before execution with signatures generated inside a Trusted Execution Environment.
Build Timeline
Team
Callipsos Agent
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
Continuing for PL Genesis. Plans: Base mainnet integration, on-chain logging, Telegram bot, expanded DeFi protocols.