Suna: Your Open Source AI Agent for Real-World Tasks - Complete Guide

Tired of juggling multiple tools for research, automation, and data analysis? Suna, the open-source generalist AI agent, handles real-world tasks with ease. This guide uncovers how Suna is your digital companion, and how to get running with it right away.

What is Suna? An Open Source AI Assistant

Suna is more than just a chatbot. It's a fully open-source AI assistant designed to execute complex tasks through natural language. Imagine having a digital helper that understands your needs and delivers tangible results – that's Suna.

• Fully Open Source: Complete transparency and community-driven development.
• Generalist AI Agent: Capable of handling a wide range of tasks.
• Natural Conversation: Interact with Suna using simple, everyday language.

Suna's Powerful Capabilities: Automate Your Life

Suna boasts a robust toolkit designed to streamline workflows and solve complex problems. Forget tedious manual processes – Suna automates them through simple conversations.

• Browser Automation: Seamlessly navigate the web and extract crucial data.
• File Management: Create, edit, and organize documents effortlessly.
• Web Crawling: Discover information with extended search capabilities.
• Command-Line Execution: Execute system tasks directly.
• Website Deployment: Deploy websites with ease.
• API Integration: Connect with various services for limitless possibilities.
• Data analysis: Suna can analyze data and present it in a way that is easy to understand.

Suna Architecture: How it Works

Suna's architecture is designed for modularity and scalability. It comprises four key components working harmoniously:

• Backend API: A Python/FastAPI service managing REST endpoints, thread management, and integration with LLMs like OpenAI and Anthropic via LiteLLM.
• Frontend: A Next.js/React application providing a responsive user interface with chat and dashboard functionality.
• Agent Docker: An isolated execution environment for each agent, offering browser automation, a code interpreter, file system access, tool integration, and security features.
• Supabase Database: Handles data persistence, user management, conversation history, file storage, agent state, analytics, and real-time subscriptions.

Real-World Suna Use Cases: See Suna in Action

Suna isn't just theory, it's practical. Here are examples showcasing Suna's diverse applications:

• Competitor Analysis: "Analyze the market for my next company in the healthcare industry, located in the UK..."
• VC List Generation: "Give me the list of the most important VC Funds in the United States based on Assets Under Management..."
• Insurance Policy Research: "Find me the best insurance policy per pricing for my house, located in Milan, Italy..."
• Candidate Sourcing: "Go on LinkedIn, and find me 10 profiles available - they are not working right now - for a junior software engineer position, who are located in Munich, Germany..."
• SEO Analysis: Generate an SEO report analysis, find top-ranking pages by keyword clusters, and identify topics I'm missing."

Suna: Self-Hosting Guide

Want full control and privacy? Self-hosting Suna is straightforward. Here's a step-by-step guide:

Requirements

Make sure you have these components ready:

• Supabase project (database and authentication)
• Redis database (caching and session management)
• Daytona sandbox (secure agent execution)
• Python 3.11 (API backend)
• API keys (OpenAI or Anthropic)
• (Optional) EXA API key (enhanced search)

Prerequisites

1. Supabase: Create a new project, save API keys, and install the Supabase CLI.
2. Redis: Set up a Redis instance (Upstash recommended) or install locally. Save connection details.
3. Daytona: Create an account, generate an API key and add the adamcohenhillel/kortix-suna:0.0.13 image, using /usr/bin/supervisord -n -c /etc/supervisor/conf.d/supervisord.conf as the entrypoint.
4. LLM API Keys: Obtain an API key from OpenAI or Anthropic.
5. API Services: Obtain a RapidAPI key to enable API services, and subscribe to the individual services you wish to use.

Installation Steps

1. Clone the Repository:

   git clone https://github.com/kortix-ai/suna.git
   cd suna
   

   Copy

2. Configure Backend Environment:

   cd backend
   cp .env.example .env
   

   Copy

   Edit the .env file with your credentials.

3. Set up Supabase Database:

   supabase login
   supabase link --project-ref your_project_reference_id
   supabase db push
   

   Copy

4. Configure Frontend Environment:

   cd ../frontend
   cp .env.example .env.local
   

   Copy

   Edit the .env.local file.

5. Install Dependencies:

   cd frontend
   npm install
   cd ../backend
   pip install -r requirements.txt
   

   Copy

6. Start the Application:

   In separate terminals:

   • Frontend: npm run dev
   • Backend: python main.py

7. Access: Open your browser and navigate to http://localhost:3000.

Get Started with Your Open Source AI Agent Today

Suna empowers you to automate tasks, analyze data, and streamline your digital life. With easy self-hosting and an active community, Suna is your gateway to unlocking the power of open-source AI.