Quick Start

Build and run your first AI agent in 5 minutes.

1. Install the CLI

Terminal

curl -fsSL https://install.sekuire.ai | sh

Verify installation:

sekuire --version

---

2. Create an API Key

Go to your dashboard and create an API key. Then configure the CLI:

Terminal

sekuire login
# Paste your API key when prompted

---

3. Create a Project

Terminal

sekuire init --name my-agent --language typescript
cd my-agent

This creates:

my-agent/

my-agent/
├── sekuire.yml       # Agent configuration
├── system_prompt.md  # LLM system prompt
├── .sekuire/         # Keys (never commit secret.key!)
└── package.json      # For TypeScript projects

---

4. Configure Your LLM

Set your LLM API key:

export OPENAI_API_KEY="sk-..."

The default sekuire.yml uses OpenAI GPT-4 Turbo. Edit to change providers.

---

5. Install SDK & Run

TypeScript

npm install @sekuire/sdk

// main.ts
import { getAgent } from '@sekuire/sdk';

async function main() {
  const agent = await getAgent('assistant');
  const response = await agent.chat('Hello! What can you do?');
  console.log(response);
}

main();

Python

pip install sekuire-sdk

# main.py
import asyncio
from sekuire_sdk import get_agent

async def main():
    agent = await get_agent('assistant')
    response = await agent.chat('Hello! What can you do?')
    print(response)

asyncio.run(main())

Rust

# Add to Cargo.toml
[dependencies]
sekuire-sdk = "0.1"
tokio = { version = "1", features = ["full"] }

// main.rs
use sekuire_sdk::get_agent;

#[tokio::main]
async fn main() -> anyhow::Result<()> {
    let mut agent = get_agent(Some("assistant"), None).await?;
    let response = agent.chat("Hello! What can you do?", None).await?;
    println!("{}", response);
    Ok(())
}

---

6. Push to Registry

Terminal

sekuire push

This publishes your agent as a draft. You can verify it:

sekuire verify

tip

Use sekuire run for production deployments with automatic bootstrap and heartbeat.

Next Steps

• Concepts - Understand the architecture
• SDKs - TypeScript, Python, Rust
• CLI - Full command reference
• Deployment - Production options