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
License
MIT © 402 Agent Inc
Metadata
Release files for agentindex 1.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agentindex-1.0.0.tar.gz | 6.6 kB | Without provenance | Details for agentindex-1.0.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentindex-1.0.0-py3-none-any.whl | Python 3 | none | any | Details for agentindex-1.0.0-py3-none-any.whl |
Total release size: 14.6 kB
Release files / agentindex-1.0.0.tar.gz
| Download URL | agentindex-1.0.0.tar.gz |
|---|---|
| Size | 6.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
a9c68d785464e8e19f3fb386655e722556698a703ec40590c38223c048cb8c12
|
|
BLAKE2b-256 checksum How to use checksums |
280fedac31b08efc9f76637489bca659c1d60901fb1b878fd240b1dc594ea5e2
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.2
|
Release files / agentindex-1.0.0-py3-none-any.whl
| Download URL | agentindex-1.0.0-py3-none-any.whl |
|---|---|
| Size | 8.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
69d82e8ca6b25e9abdd55f99e5a3b9a7fda0d49dfc28908d8d56a535f3e0d498
|
|
BLAKE2b-256 checksum How to use checksums |
7a5fcdde388447357a4016738c0adc351e9bd34f1d7fb4af948367a82ca201c5
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.14.2
|
Security for agentindex 1.0.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.