Quick Start

Get up and running with Aphelion in under 5 minutes.

Step 1: Create an Account

Step 2: Get Your API Key

After signing up, you'll receive an API key:

ap_live_a1b2c3d4e5f6g7h8i9j0k1l2m3n4o5p6

⚠️Keep your API key secure

Save this key securely. You won't see it again. Never commit it to version control.

Step 3: Install the SDK

Python

pip install aphelion

Node.js

npm install aphelion

Step 4: Execute Your First Tool

Python

from aphelion import Aphelion

client = Aphelion(
    api_key="ap_live_...",
    agent="my-first-agent"
)

# Execute a tool
result = client.execute(
    "stripe.customers.create",
    {
        "email": "jane@example.com",
        "name": "Jane Doe"
    }
)

print(result)
# {"id": "cus_abc123", "email": "jane@example.com", ...}

Node.js

import { Aphelion } from 'aphelion';

const client = new Aphelion({
  apiKey: 'ap_live_...',
  agent: 'my-first-agent'
});

const result = await client.execute(
  'stripe.customers.create',
  {
    email: 'jane@example.com',
    name: 'Jane Doe'
  }
);

console.log(result);

Step 5: Check the Console

Open console.aphl.ai to see:

Your agent was created automatically
The execution was logged
Memory was stored

That's it. You've executed your first tool with Aphelion.

Environment Setup

We recommend storing your API key in environment variables:

.env

APHELION_API_KEY=ap_live_a1b2c3d4e5f6g7h8i9j0k1l2m3n4o5p6

Python

import os
from dotenv import load_dotenv
from aphelion import Aphelion

load_dotenv()

client = Aphelion(
    api_key=os.getenv("APHELION_API_KEY"),
    agent="my-agent"
)

Node.js

import 'dotenv/config';
import { Aphelion } from 'aphelion';

const client = new Aphelion({
  apiKey: process.env.APHELION_API_KEY,
  agent: 'my-agent'
});

API Key Types

Key Type	Prefix	Use Case
Live	`ap_live_`	Production
Test	`ap_test_`	Development (sandbox mode)

Test keys execute against sandbox/test versions of tools where available.

Using the REST API Directly

If you prefer to use the REST API directly:

Execute a Tool

POST/v1/execute

curl -X POST https://api.aphl.ai/v1/execute \
  -H "Authorization: Bearer ap_live_..." \
  -H "Content-Type: application/json" \
  -d '{
    "tool": "stripe.customers.create",
    "params": {
      "email": "jane@example.com",
      "name": "Jane Doe"
    },
    "agent": "my-agent"
  }'

Response

{
  "data": {
    "id": "cus_abc123",
    "object": "customer",
    "email": "jane@example.com",
    "name": "Jane Doe",
    "created": 1704326400
  },
  "meta": {
    "request_id": "req_xyz789",
    "execution_id": "exec_def456",
    "latency_ms": 142,
    "memory_id": "mem_ghi789"
  }
}

Working with Memory

Every execution is automatically summarized and stored. Search across your agent's memory:

Python

# Search agent memory
memories = client.memory.search(
    query="customer jane",
    limit=10
)

for memory in memories:
    print(f"{memory.summary} - {memory.created_at}")

Complete Example

A customer support bot that remembers past interactions:

support_bot.py

from aphelion import Aphelion

client = Aphelion(
    api_key="ap_live_...",
    agent="support-bot"
)

def handle_inquiry(user_message: str, user_email: str):
    # Check if customer exists in memory
    memories = client.memory.search(f"customer {user_email}")

    if memories:
        customer_id = memories[0].result_preview.get("id")
    else:
        # Create customer in Stripe
        customer = client.execute("stripe.customers.create", {
            "email": user_email
        })
        customer_id = customer["id"]

    # Create support ticket in Jira
    ticket = client.execute("jira.issues.create", {
        "project": "SUP",
        "summary": f"Support request from {user_email}",
        "description": user_message,
        "issuetype": {"name": "Support"}
    })

    # Send confirmation via Slack
    client.execute("slack.messages.post", {
        "channel": "#support",
        "text": f"New ticket {ticket['key']} from {user_email}"
    })

    return ticket["key"]

Next Steps

Agents & Sessions

Learn about agents, sessions, and execution context

→

Tools Catalog

Browse 200+ available tools and publish your own

→

Memory System

Understand persistent memory and context

→