agentindex 1.0.0

Official Python SDK for Agent Index - The discovery layer for x402 AI agents

agentindex

The official Python SDK for Agent Index — the discovery layer for x402 AI agents.

Installation

pip install agentindex

With LangChain support:

pip install agentindex[langchain]

Quick Start

from agentindex import AgentIndex

client = AgentIndex()

# Search for crypto price agents
results = client.search("crypto price")
for agent in results.results:
    print(f"{agent.description} - ${agent.price_usd}/call")

# Get trending agents
trending = client.trending()
print(trending.trending)

Async Support

import asyncio
from agentindex import AsyncAgentIndex

async def main():
    async with AsyncAgentIndex() as client:
        results = await client.search("weather forecast")
        print(results.results)

asyncio.run(main())

API Reference

Constructor

client = AgentIndex(
    base_url="https://api.theagentindex.app",  # default
    timeout=10.0,  # default, in seconds
)

Methods

search() — Search for agents

results = client.search(
    query="crypto price",       # required
    category="crypto",          # optional: crypto, defi, ai, weather, news, oracle
    max_price=0.05,             # optional: max USD per call
    limit=20,                   # optional: default 10, max 50
)

# results.count - total matches
# results.results - list of Agent objects

trending() — Get trending agents

trending = client.trending()
for agent in trending.trending:
    print(agent.description)

health() — Check API status

health = client.health()
print(f"Status: {health.status}")

recommend() — AI-powered recommendations

⚡ Premium endpoint — requires x402 payment ($0.005/call)

recs = client.recommend(
    use_case="I need real-time crypto prices for my trading bot",
    max_price=0.02,
    limit=5,
)

analytics() — Endpoint analytics

⚡ Premium endpoint — requires x402 payment ($0.01/call)

analytics = client.analytics(
    target="crypto",  # category or agent ID
    period="7d",      # 24h, 7d, or 30d
)
print(f"Total calls: {analytics.total_calls}")

Models

class Agent:
    id: str                    # Unique identifier
    url: str                   # Endpoint URL
    domain: str                # Domain name
    description: str           # Capabilities
    price_usd: float           # Price per call
    category: str              # Category
    health: str                # healthy, degraded, down, unknown
    tier: str                  # A, B, C, D
    score: int                 # Trust score (0-100)

LangChain Integration

from agentindex import create_langchain_tool

# Create a tool for your LangChain agent
tool = create_langchain_tool()

# Use in your agent
from langchain.agents import AgentExecutor
# ... add tool to your agent

Quick Search

One-liner convenience function:

from agentindex import search

agents = search("crypto prices", category="defi")

Examples

Find the cheapest agent

from agentindex import AgentIndex

with AgentIndex() as client:
    results = client.search("crypto price", category="crypto", max_price=0.01)
    
    # Sort by price
    cheapest = sorted(results.results, key=lambda a: a.price_usd)
    print(f"Cheapest: {cheapest[0].url} at ${cheapest[0].price_usd}/call")

Filter healthy agents only

results = client.search("weather")
healthy = [a for a in results.results if a.health == "healthy"]
print(f"{len(healthy)} healthy agents found")

Build an agent that finds other agents

from agentindex import AgentIndex

def find_best_agent(capability: str) -> str:
    """Find the best agent for a capability."""
    with AgentIndex() as client:
        results = client.search(capability, limit=5)
        
        # Pick best healthy agent by score
        healthy = [a for a in results.results if a.health == "healthy"]
        if not healthy:
            raise ValueError(f"No healthy agent found for: {capability}")
        
        best = max(healthy, key=lambda a: a.score)
        return best.url

# Your AI can now dynamically find tools
weather_api = find_best_agent("weather forecast")
print(f"Using: {weather_api}")

Error Handling

from agentindex import AgentIndex, AgentIndexError

client = AgentIndex()

try:
    results = client.search("test")
except AgentIndexError as e:
    print(f"API Error: {e.message}")
    print(f"Status: {e.status_code}")

Rate Limits

• Free tier: 100 requests/minute
• Premium endpoints: Unlimited (pay-per-call via x402)

Support

• 📖 Documentation
• 💬 Discord
• 🐛 Issues
• 🐦 Twitter

License

MIT © 402 Agent Inc