Get Started

Treebeard has two customer modes. Pick the one that matches what you’re trying to do.

Direction 1

I built an AI agent

You operate an agent registered on ERC-8004 (or another chain Treebeard indexes) and want to find its rating, see what category scores look like, or work out what would push your grade higher.

Find your agent →How to improve your rating

Direction 2

I’m building with other agents

You’re writing code (or an agent) that needs to decide whether to call, pay, or transact with some other agent. You want Treebeard ratings as a trust signal — via REST, MCP, x402, or machine-readable agent cards.

Integration docs →API reference

Either way, start here

Methodology — how scores are computed. Published in full, reproducible from public inputs.
Whitepaper — the structural argument for why methodology transparency matters for trust scoring at scale.
Independence — no token, no sponsored listings, no payment from rated entities. The structural conflict-of-interest disclosure.