Home › Agent Frameworks › Suna (Kortix)

Suna (Kortix) - AI Agent Frameworks Tool

Overview

Suna (by Kortix) is an open-source platform for building, managing, and training autonomous AI agents. According to the project's GitHub repository (https://github.com/kortix-ai/suna), Suna provides a framework that combines agent orchestration, workflow automation, browser-based automation, and a data layer intended for self-hosted deployments. The project targets teams and developers who need an extensible environment to prototype multi-step agent behaviors, coordinate background workflows, and maintain control over data and infrastructure. The platform emphasizes self-hosting and operational control — enabling deployments on private infrastructure while providing primitives for agent lifecycle management, workflow composition, and integrations with external data sources or tools. Documentation and examples live in the repository; users typically interact with Suna by cloning the codebase, running the included services, and extending the core runtime with custom agent logic and connectors. For up-to-date details on capabilities, configuration, and deployment options, consult the repository and its README at the project URL above.

Installation

Install via docker:

git clone https://github.com/kortix-ai/suna.git
cd suna
docker compose up -d

Key Features

  • Workflow orchestration for composing multi-step agent pipelines and task sequences.
  • Browser automation module for web interaction, scraping, and in-browser task automation.
  • Data layer to store, index, and retrieve agent state and external data for tasks.
  • Agent lifecycle management: create, train, run, and monitor agents in self-hosted environments.
  • Extensible architecture for adding custom connectors, tools, and agent behaviors.

Community

Suna is developed as an open-source project on GitHub (https://github.com/kortix-ai/suna). Community engagement primarily occurs through the repository's issues and pull requests; consult the repo README for contribution guidelines, contact channels, and the latest activity.

Last Refreshed: 2026-01-09

Key Information

  • Category: Agent Frameworks
  • Type: AI Agent Frameworks Tool
Visit Official Website

Related Tools

AG2

AG2 (formerly AutoGen) is an open-source software platform designed for building AI agents and facilitating multi-agent interactions to solve complex tasks. It supports integration with various large language models and provides various orchestration patterns for AI agents, enabling flexible and efficient tool usage and human collaboration.
elizaOS

A framework for creating autonomous agents, featuring connectors for Discord, Twitter, and Telegram, support for various AI models, multi-agent functionality, document ingestion, and memory storage capabilities.
Smolagents

A barebones framework for building AI agents that support multi-modal inputs and tool integration.
SuperAGI

A dev-first open source autonomous AI agent framework designed for building, managing, and running autonomous agents.
SmythOS

SmythOS lets you build and deploy AI agents without manual coding. Describe your needs, and Agent Weaver creates it automatically using the best AI models and APIs. Integrate with OpenAI, Hugging Face, Amazon Bedrock, and more—no manual coding required.
AutoGen

A programming framework by Microsoft for creating and orchestrating multi-agent AI workflows with an extensible design.