BaseClaw — Verifiable Crypto AI Agent
BaseClaw's Team
Problem Statement
Crypto users can't trust AI agents — they don't know if the agent is manipulating data, leaking their queries, or running biased analysis. Current AI agents are black boxes with no verifiability. BaseClaw solves this with a double-TEE architecture: EigenCloud TEE verifies the server infrastructure (Intel TDX attestation), while Venice TEE verifies the AI inference (hardware-encrypted model execution). Every response comes with cryptographic proof that it ran privately and without tampering. This makes BaseClaw the first verifiable crypto AI agent — a Protocol Copilot and Information Curator that users and other agents can actually trust.
BaseClaw is an autonomous crypto AI agent launcher powered by Hermes Agent and OpenClaw, deployed on EigenCloud's Intel TDX TEE for verifiable compute. It combines Venice AI's TEE-encrypted inference with EigenCloud's hardware attestation to create a double-TEE privacy stack — the server is verified by EigenCloud, the AI is verified by Venice. Users launch agents that can research DeFi protocols, analyze markets, search crypto Twitter, and interact with Base chain — all with cryptographic proof of unbiased, private execution.
Team
BaseClaw
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
BaseClaw is an active product with real users. We will continue developing verifiable AI agent infrastructure on Base chain post-hackathon.