Self-hosted AI operating system that runs a workforce of AI agents on your own machine, with any model, 1,000+ tool integrations and a Knowledge Graph.
kortix-ai/suna
Open-source, self-hostable AI operating system where agents run in isolated cloud sandboxes and deliver work through approved change requests.
Open-source alternative to:Claude Cowork
ChatGPT Work
- Stars
- 20,290
- Forks
- 3,438
- Open issues
- 76
- Last commit
- 1 hour ago
What is it?
Kortix is an open-source AI operating system for running a team's agents. Agents, their shared skills, company memory, connectors and triggers are defined as files in a single git repository, so their configuration is versioned, diffable and reviewable like code.
Each agent session runs on its own isolated cloud sandbox on a dedicated branch. Work reaches the main branch only through a change request that a person approves. Agents can be reached from the web app, Slack, Microsoft Teams or a CLI, and can run on demand, on a cron schedule, or from a signed webhook.
The project supports any model provider through your own API keys and can be self-hosted with Docker Compose or deployed to your own VPC, or used through the managed Kortix Cloud.
Key features
- 01Agents run in isolated cloud sandboxes, one per session, on their own branch.
- 02Changes reach main only through change requests that a person approves.
- 03Slack and Microsoft Teams integration lets agents reply in threads.
- 04Cron schedules and signed webhooks trigger agent sessions automatically.
- 05Connectors reach thousands of apps and support MCP, OpenAPI, GraphQL and HTTP.
- 06Per-tool Allow, Ask or Block rules control what agents can do.
Use cases
- Running background coding agents that reproduce bugs, write fixes and open change requests for review.
- Replacing scheduled Zapier-style automations with agents that act on a cron schedule or webhook.
- Giving a team a shared AI assistant reachable from Slack or Microsoft Teams.
- Self-hosting an agent platform inside a private network with your own model keys.
Quick start
- 1
Run the official install script from the README to install the Kortix CLI
- 2
Scaffold a project with kortix.yaml, agents, skills and runtime config
kortix init - 3
Push the repo and bring the project live in the cloud
kortix ship
Things to know
- The license is not clearly identified in the metadata, so check the repository's license terms before use.
- Self-hosting pulls images from Docker Hub and needs integration credentials for managed git, GitHub access and Pipedream connectors.
Topics
FAQ
- What is suna?
- Open-source, self-hostable AI operating system where agents run in isolated cloud sandboxes and deliver work through approved change requests. Kortix is an open-source AI operating system for running a team's agents. Agents, their shared skills, company memory, connectors and triggers are defined as files in a single git repository, so their configuration is versioned, diffable and reviewable like code.
- Is suna free to use? What license does it have?
- suna is open source under the Other license. Check the license terms before using it in commercial products.
- Is suna still maintained?
- Actively maintained. The last commit to suna was on Oct 22, 2026.
- What can I use suna for?
- Running background coding agents that reproduce bugs, write fixes and open change requests for review. Replacing scheduled Zapier-style automations with agents that act on a cron schedule or webhook. Giving a team a shared AI assistant reachable from Slack or Microsoft Teams. Self-hosting an agent platform inside a private network with your own model keys.
- How do I install suna?
- Run the official install script from the README to install the Kortix CLI Scaffold a project with kortix.yaml, agents, skills and runtime config: kortix init Push the repo and bring the project live in the cloud: kortix ship
- Where can I get suna?
- The source code and installation instructions are on GitHub: https://github.com/kortix-ai/suna
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A self-improving AI agent that creates and refines skills from experience, runs on many model providers, and works through CLI and messaging apps.
Open-source infrastructure for running AI-generated code in isolated cloud sandboxes, with JavaScript and Python SDKs.
Open-source AI coworker for your desktop that completes everyday tasks and security reviews, using your own model keys and approval-gated actions.
Open-source workspace where teams build AI agents by chatting, share them, and run them in Slack, Telegram or WhatsApp.
Fair-code workflow automation platform for building AI agents and workflows, combining a visual canvas with custom code and 1500+ integrations.