Open-source framework to build, manage and run useful Autonomous AI Agents
Follow SuperAGI
Connect with the Creator
Share SuperAGI Repository
What are we ?
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.
💡 Features
- Provision, Spawn & Deploy Autonomous AI Agents - Create production-ready & scalable autonomous agents.
- Extend Agent Capabilities with Toolkits - Add Toolkits from our marketplace to your agent workflows.
- Graphical User Interface - Access your agents through a graphical user interface.
- Action Console - Interact with agents by giving them input and permissions.
- Multiple Vector DBs - Connect to multiple Vector DBs to enhance your agent’s performance.
- Performance Telemetry - Get insights into your agent’s performance and optimize accordingly.
- Optimized Token Usage - Control token usage to manage costs effectively.
- Agent Memory Storage - Enable your agents to learn and adapt by storing their memory.
- Models - Custom fine tuned models for business specific usecases.
- Workflows - Automate tasks with ease using ReAct LLM's predefined steps.
🛠 Toolkits
Toolkits allow SuperAGI Agents to interact with external systems and third-party plugins.
⚙️ Installation
You can install superAGI using one of the following three approaches.
☁️ SuperAGI cloud
To quickly start experimenting with agents without the hassle of setting up the system, try Superagi Cloud
-
Visit Superagi Cloud and log in using your github account.
-
In your account settings, go to "Model Providers" and add your API key.
You're all set! Start running your agents effortlessly.
🖥️ Local
- Open your terminal and clone the SuperAGI repository.
git clone https://github.com/TransformerOptimus/SuperAGI.git
- Navigate to the cloned repository directory using the command:
cd SuperAGI
-
Create a copy of config_template.yaml, and name it config.yaml.
-
Ensure that Docker is installed on your system. You can download and install it from here.
-
Once you have Docker Desktop running, run the following command in the SuperAGI directory:
a. For regular usage:
docker compose -f docker-compose.yaml up --build
b. If you want to use SuperAGI with Local LLMs and have GPU, run the following command:
docker compose -f docker-compose-gpu.yml up --build
- Open your web browser and navigate to http://localhost:3000 to access SuperAGI.
🌀 Digital Ocean
Deploy SuperAGI to DigitalOcean with one click.
🌐 Architecture
SuperAGI Architecture
SuperAGI Architecture
Agent Architecture
Agent Architecture
Agent Workflow Architecture
Agent Workflow Architecture
Tools Architecture
Tools Architecture
ER Diagram
ER Diagram
📚 Resources
📖 Need Help?
Join our Discord community for support and discussions.
Join us on Discord
If you have questions or encounter issues, please don't hesitate to create a new issue to get support.
💻 Contribution
We ❤️ our contributors. We’re committed to fostering an open, welcoming, and safe environment in the community.
If you'd like to contribute, start by reading our Contribution Guide.
We expect everyone participating in the community to abide by our Code of Conduct.
To get more idea on where we are heading, checkout our roadmap here.
Explore some good first issues to start contributing.
👩💻 Contributors
TransformerOptimus Cptsnowcrasher vectorcrow Akki-jain Autocop-AgentCOLONAYUSHluciferlinx101mukundans89Fluder-ParadynenborthynihirrTarraannneelayan7Arkajit-Dattaguangchen811juanfpo96iskandarrezajpenalbaepallasite99xutpuualexkreidlerhanhyalex123ps4vseltociear shaiss AdityaRajSingh1992 namansleeps2 sirajperson hsm207 unkn-wn DMTarmey Parth2506 platinaCoder anisha1607 jorgectf PaulRBerg boundless-asura JPDucky Vibhusha22 ai-akuma rounak610 AdarshJha619 ResoluteStoic JohnHunt999 Maverick-F35 jorgectf AdityaSharma13064 lalitlj andrew-kelly-neutralaiz sayan1101
⚠️ Under Development!
This project is under active development and may still have issues. We appreciate your understanding and patience. If you encounter any problems, please check the open issues first. If your issue is not listed, kindly create a new issue detailing the error or problem you experienced. Thank you for your support!