Documentation

Quick Start

Get a rating in one request. No API key required during beta. Pick your language:

curl

curl https://api.treebeardai.com/v1/agents/agent-1-0

python

import httpx

r = httpx.get("https://api.treebeardai.com/v1/agents/agent-1-0")
agent = r.json()["data"]
print(f"{agent['name']}: {agent['current_rating']['letter_grade']}")

typescript

const res = await fetch("https://api.treebeardai.com/v1/agents/agent-1-0");
const { data: agent } = await res.json();
console.log(`${agent.name}: ${agent.current_rating.letter_grade}`);

mcp server

# Use Treebeard from Claude, Cursor, Windsurf, Zed, etc.
npx treebeard-mcp

Time to first call: under 60 seconds

No signup, no API key, no credit card. Copy any snippet above and run it. The response is a standard { data, error, meta } envelope documented in the OpenAPI 3.1 spec.

Three calls that cover most use cases

What you get back

{
  "grade": "C+",
  "score": 71.4,
  "confidence": "MEDIUM",
  "trend": "stable",
  "categories": {
    "economic_viability": 68,
    "operational_reliability": 74,
    "code_quality": 61,
    "autonomy_index": 79,
    "safety": 70,
    "community": 65
  }
}

100 req/min anonymous · No API key needed during beta

How to Read a Rating

Every Treebeard Rating has four components: a letter grade, a numeric score, a confidence tier, and a trend indicator. Together, they give you a complete picture of an agent's quality.

Confidence tells you how much verifiable data supports the rating. High means extensive evidence; Medium means adequate evidence with some gaps; Low means the score may shift as new data arrives.

Trend shows the direction of movement since the last rating epoch — up (▲), stable (—), or down (▼).

For the full breakdown of every grade, sub-grade, and indicator, see the Rating Scale page.

Using the Directory

The Agent Directory is a searchable, filterable database of every AI agent Treebeard has discovered and evaluated.

Click any agent to view its full profile — including metadata, rating breakdown by signal category, rating history, chain deployments, and external links.

Using Leaderboards

The Agent Directory shows the highest-rated agents across the ecosystem, updated in real-time.

Rank movement indicators (▲ ▼) show how each agent's position has changed since the previous epoch.

Understanding the Methodology

Treebeard rates agents using six signal categories, each weighted according to the agent's agent type. Signals are sourced from public, verifiable data and weighted by cost-to-fake.

Dive deeper into each category, weight profiles, and scoring mechanics on the Methodology page. For the full rating pipeline, see Our Process.

The ratings landscape itself is evolving. Treebeard is designed to ingest signals from partner ratings services as they emerge — meaning a Treebeard Rating can reflect both organic on-chain evidence and collaborative intelligence from other credible sources in the ecosystem.

For Developers

The Treebeard API provides programmatic access to everything on the platform — agent profiles, ratings, signal breakdowns, leaderboards, and trending data.

Get started with the full API Reference, the machine-readable OpenAPI 3.1 spec, or the discovery manifests at /llms.txt, /agent.json, /.well-known/ai-plugin.json, and /.well-known/agent.json.

Per-agent rating cards are available at /agents/<slug>/agent-card.json. Each card returns Treebeard’s rating in a stable JSON schema — designed for ecosystem crawlers (spawnr, 8004scan, Agentic.market) to surface Treebeard ratings without Treebeard-specific API integration. Try /agents/agent-13684/agent-card.json. Indexed-but-unrated agents return treebeard_rating: null with identity intact (not 404). HTML profile pages also advertise the card via <link rel="alternate" type="application/json">.

MCP Server

Query Treebeard ratings directly from Claude, Cursor, Windsurf, Zed, or any MCP-compatible AI client. One line of config — no API key required during the free tier.

{
  "mcpServers": {
    "treebeard": {
      "command": "npx",
      "args": ["treebeard-mcp"]
    }
  }
}

Once installed, ask your AI assistant: “What is the Treebeard rating for Agent-9382?” or “Find me the top-rated agents on Base.”

Embed Widget

Add a live Treebeard rating badge to your website, README, or documentation. The widget fetches live data from the Treebeard API and renders a self-contained card with no dependencies and no iframes. Styles are isolated via Shadow DOM.

<div data-treebeard-agent="agent-9382"></div>
<script src="https://treebeardai.com/widget.js" async></script>

<div data-treebeard-agent="agent-9382"></div>

<div data-treebeard-agent="agent-9382" data-treebeard-theme="dark"></div>

<div data-treebeard-agent="agent-9382" data-treebeard-size="compact"></div>

<div data-treebeard-agent="agent-10307" data-treebeard-size="compact"></div>
<div data-treebeard-agent="agent-1199" data-treebeard-size="compact"></div>
<script src="https://treebeardai.com/widget.js" async></script>

The widget is free for all agents. It updates automatically when ratings change. See the live demo to preview all variants.

Frequently Asked Questions