E
Engrami
Documentation/Quick Start

Quick Start Guide

Get up and running with Engrami in under 10 minutes. This guide will walk you through creating your first AI agent with persistent memory.

Prerequisites

Before you begin, ensure you have the following:

New Account Bonus

New accounts automatically receive 5,000 Engrami tokens to get started. This is enough to create several agents and run thousands of interactions.

Step 1: Install the SDK

Choose your preferred programming language and install the Engrami SDK:

Python

pip install engrami

TypeScript / JavaScript

npm install @engrami/sdk

Step 2: Configure Authentication

Set your API key as an environment variable or pass it directly to the client. We recommend using environment variables for security.

Using Environment Variables

# Add to your .env file or shell profile
export ENGRAMI_API_KEY="your-api-key-here"

Python Configuration

from engrami import EngramiClient

# The client automatically reads ENGRAMI_API_KEY from environment
client = EngramiClient()

# Or pass the API key directly
client = EngramiClient(api_key="your-api-key-here")

TypeScript Configuration

import { EngramiClient } from '@engrami/sdk';

// The client automatically reads ENGRAMI_API_KEY from environment
const client = new EngramiClient();

// Or pass the API key directly
const client = new EngramiClient({ apiKey: 'your-api-key-here' });

Keep Your API Key Secure

Never commit your API key to version control or expose it in client-side code. Always use environment variables or a secrets manager in production.

Step 3: Create Your First Agent

Now let's create an AI agent. Agents in Engrami are intelligent entities that can remember context, learn from interactions, and perform tasks.

Python Example

from engrami import EngramiClient

client = EngramiClient()

# Create a customer support agent
agent = client.agents.create(
    name="Support Assistant",
    description="A helpful customer support agent",
    type="support",
    memory_types=["semantic", "episodic"],
    config={
        "personality": "friendly and professional",
        "knowledge_base": "product_docs",
        "response_style": "concise",
        "language": "en"
    }
)

print(f"Created agent: {agent.id}")

TypeScript Example

import { EngramiClient } from '@engrami/sdk';

const client = new EngramiClient();

// Create a customer support agent
const agent = await client.agents.create({
  name: 'Support Assistant',
  description: 'A helpful customer support agent',
  type: 'support',
  memoryTypes: ['semantic', 'episodic'],
  config: {
    personality: 'friendly and professional',
    knowledgeBase: 'product_docs',
    responseStyle: 'concise',
    language: 'en',
  },
});

console.log(`Created agent: ${agent.id}`);

Step 4: Interact with Your Agent

Once your agent is created, you can start having conversations. The agent will automatically store interactions in its memory for future context.

Python Example

# Get a reference to your agent
agent = client.agents.get("agent-id-here")

# Start a conversation
response = agent.chat("Hello! I need help with my account.")
print(response.content)

# The agent remembers the conversation
response = agent.chat("I forgot my password.")
print(response.content)

# Access conversation history
history = agent.get_conversation_history(limit=10)
for message in history:
    print(f"{message.role}: {message.content}")

TypeScript Example

// Get a reference to your agent
const agent = await client.agents.get('agent-id-here');

// Start a conversation
let response = await agent.chat('Hello! I need help with my account.');
console.log(response.content);

// The agent remembers the conversation
response = await agent.chat('I forgot my password.');
console.log(response.content);

// Access conversation history
const history = await agent.getConversationHistory({ limit: 10 });
history.forEach((message) => {
  console.log(`${message.role}: ${message.content}`);
});

Step 5: Add Knowledge to Memory

Enhance your agent's capabilities by adding documents, FAQs, or other knowledge to its semantic memory.

Python Example

# Add documents to the agent's knowledge base
agent.memory.add_documents([
    {
        "content": "To reset your password, go to Settings > Security > Reset Password.",
        "metadata": {"category": "account", "topic": "password"}
    },
    {
        "content": "Subscription plans: Free (5 agents), Pro ($49/mo, 50 agents), Enterprise (custom).",
        "metadata": {"category": "billing", "topic": "pricing"}
    }
])

# The agent can now answer questions about these topics
response = agent.chat("What are the pricing plans?")
print(response.content)  # Will reference the pricing information

Step 6: Deploy and Scale

Once you're happy with your agent, you can deploy it to production and scale as needed. Engrami handles the infrastructure automatically.

Deploy to Production

# Deploy the agent
deployment = agent.deploy(
    environment="production",
    replicas=3,  # For high availability
    config={
        "rate_limit": 1000,  # requests per minute
        "timeout": 30,  # seconds
    }
)

print(f"Deployed at: {deployment.endpoint}")

Integration Options

Connect your agent to various platforms:

Slack Integration

Deploy your agent as a Slack bot for team collaboration.

Microsoft Teams

Integrate with Microsoft Teams for enterprise deployments.

Webhooks

Receive real-time notifications about agent activity.

REST API

Direct API access for custom integrations.

Next Steps

Congratulations! You've created your first Engrami agent. Here's what to explore next:

IntroductionInstallation Guide