Open-source framework to build, manage and run useful Autonomous AI Agents
Follow SuperAGI
Connect with the Creator
Share SuperAGI Repository
Not sure how to setup? Learn here
Deploy SuperAGI to DigitalOcean with one click.
A dev-first open source autonomous AI agent framework enabling developers to build, manage & run useful autonomous agents. You can run concurrent agents seamlessly, extend agent capabilities with tools. The agents efficiently perform a variety of tasks and continually improve their performance with each subsequent run.
- Provision, spawn & deploy autonomous AI agents
- Tools/Toolkits for extended agent capabilities
- Concurrent agent runs
- Schedule agents
- Action console
- Multiple vector DBs
- Agent trajectory fine-tuning
- Performance monitoring
- Tool memory
- Resource manager
- Knowledge embeddings
- Agent workflows
Click here to checkout the latest roadmap 🔗
-
Download the repo using
git clone https://github.com/TransformerOptimus/SuperAGI.git
in your terminal or directly from github page in zip format. -
Navigate to the directory using
cd SuperAGI
and create a copy ofconfig_template.yaml
, naming itconfig.yaml
(take note of the file extension.yaml
, not.yml
). -
Ensure that Docker is installed in your system, if not, Install it from here.
-
Once you have Docker Desktop running, run the command:
docker-compose up --build
in the SuperAGI directory. Open your browser and navigate tohttp://localhost:3000
to access SuperAGI.
- If you wish to change the port it's running on, open the
docker-compose.yml
file and update theproxy
container port forwarding, for example:"3000:80"
We wholeheartedly welcome contributions in the form of bug reports, feature ideas, or pull requests. For contribution guidelines, see CONTRIBUTING.md
For more information, please check out:
We're absolutely delighted to answer any questions you may have! Don't hesitate to drop your inquiries or simply say hi and join our lively Discord community
This project is under active development and may still have issues. We appreciate your understanding and patience. If you encounter any problems, please first check the open issues. If your issue is not listed, kindly create a new issue detailing the error or problem you experienced. Thank you for your support!