luc4t/agentcloud

Agent Cloud is like having your own GPT builder with a bunch extra goodies. The GUI features 1) RAG pipeline which can natively embed 260+ datasources 2) Create Conversational apps (like GPTs) 3) Create Multi Agent process automation apps (crewai) 4) Tools 5) Teams+user permissions. Get started fast with Docker and our install.sh

agentcloud

https://www.agentcloud.dev/ Watch our Intro video here https://youtu.be/POLdnrjsy9c

Welcome to agentcloud repository! This project comprises three main components:

1. Agent Backend: A Python application running crewai, communicating LLM messages through socket.io
2. Webapp: A UI built using next.js, tailwind, and an express custom server.
3. Vector Proxy: A Rust application which communicates with Qdrant vector Database

Getting Started

To run this project up locally, clone this repo and run Docker. For now there is a reliance on GCP for Bucket storage to store files. (We will add AWS S3, Local Disk in future releases.) Follow the steps below to get started:

1. Start Services: Simply run the following command:

Mac & Linux:

chmod +x install.sh && ./install.sh

The script will prompt for some details, or you can pass them as command line arguments:

~$ ./install.sh --help
Usage: ./install.sh [options]
Options:
    --project-id ID                  Specify the GCP project ID.
    --service-account-json PATH      Specify the file path of your GCP service account json.
    --gcs-bucket-name NAME           Specify the GCS bucket name to use.
    --gcs-bucket-location LOCATION   Specify the GCS bucket location.
    --openai-api-key KEY             Specify your OpenAI API key.
    -h, --help                       Display this help message.

Windows:

(Coming soon...)

License

This project is licensed under the GNU Affero General Public License, version 3 only.

Changelog

See CHANGELOG.md.

Contributions & Feedback

If you wish to contribute or provide feedback, please follow the contribution guidelines in CONTRIBUTING.md.

Thank you for exploring agentcloud!