SuperAGI is an open-source platform providing infrastructure to build autonomous AI agents. Designed to run multiple agents concurrently, SuperAGI's diverse set of features and tools allows developers to spawn, deploy, and manage AI agents with ease.
This article will walk you through the initial setup and configuration of SuperAGI. By the end, you will have a working SuperAGI environment ready to run your autonomous AI agents.
⭐️ Key Features of SuperAGI
- Extend Agent Capabilities with Tools: You can add capabilities to your agents by selecting tools from an ever-growing library or build your own custom tool.
- Run Concurrent Agents Seamlessly: SuperAGI allows you to run multiple agents simultaneously, maximizing efficiency and achieving parallel processing.
- Open Source: As an open-source platform, SuperAGI encourages developers to join its community and contribute to making the platform better.
- GUI: With a user-friendly graphical interface, managing and interacting with your agents becomes a breeze.
- Action Console: This feature lets you interact with agents by providing input, permissions, and more.
- Multi-Modal Agents: You can customize your agents using different models to tailor their behavior to specific tasks.
💻 Screenshots
GUI
🧰 Prerequisites
SuperAGI requires Docker and Pinecone setup. Before proceeding, ensure you have installed and configured Pinecone. Along with this, you will need Python installed on your system.
🛠 Setting Up SuperAGI
-
Download the repo using
git clone https://github.com/TransformerOptimus/SuperAGI.gitin your terminal or directly from the GitHub page in zip format.
-
Navigate to the directory using
cd SuperAGI, and create a copy ofconfig_template.yaml; name itconfig.yaml.
-
Enter your unique OpenAI API Key, Google key, Custom search engine ID, and Pinecone API key without any quotes or spaces in
config.yamlfile. Follow the links below to get your keys:
|
Keys |
Accessing the keys |
|---|---|
|
OpenAI API Key |
Sign up, and create an API key at OpenAI Developer |
|
Google API key |
Create a project in the Google Cloud Console, and enable the API you need (for example, Google Custom Search JSON API). Then, create an API key in the "Credentials" section. |
|
Custom search engine ID |
Visit Google Programmable Search Engine to create a custom search engine for your application, and obtain the search engine ID. |
|
Pinecone API key |
Sign up at Pinecone, and create an API key in your account dashboard. |
If you're on the Pinecone free plan, you only have 1 pod and 1 index available. As a workaround, change the index name used in test.py where
memoryis defined:memory = VectorFactory.get_vector_storage("PineCone", "my-current-indexname", OpenAiEmbedding())
-
Ensure that Docker is installed in your system; if not, install it from here.
-
Once you have Docker Desktop running, run command :
docker-compose up --buildin the SuperAGI directory. Open your browser and go tolocalhost:3000to see SuperAGI running.
🤝 Conclusion
You're all set! You now have a functional SuperAGI environment ready to provision, spawn, and deploy autonomous AI agents. Keep in mind that SuperAGI is currently under active development.
Leave a ⭐ on GitHub Roadmap Website
Also published here
