Welcome to the afaas: Agent Framework as a Service project! This project is a fork AutoGPT it aims to facilitate developments of AI Agents & AI Autonomous Agents by providing a more simple, modular & extendable architecture.
This is a Project Presentation & a product presentation will be released soon.
Warning
🚧 This is a preview of a Work in progress 🚧
Follow these simple steps to get started with afaas:
-
Clone the Repository:
git clone https://github.com/ph-ausseil/afaas.git cd afaas
-
Configure Environment Variables:
Rename the .env.template file to .env:
mv .env.template .env
Open the .env file in a text editor and set your OPENAI_API_KEY:
# Add your OpenAI API key here OPENAI_API_KEY=your-openai-api-key Replace your-openai-api-key with your actual OpenAI API key.
-
Install dependencies:
pip install poetry poetry install
-
Run the Agent
poetry run demo
Autonomous Agent are experimental initiative aiming to set inteligent systems with more or less human involvement. We will try to push research and knowledge beyond current boundaries.
Note
The product will come as a web-app to play & a framework anyone can extend.
- v0.0.2 - Reduce Technical debt (Planned on 31/01/2024)
- Improving & automating tests coverage
- Improve general thinking & planning performances
- Sets a Proxy between the PlannerAgent & the User #54
- v0.0.3 - Provide basic coding capacities (Planned on 15/02/2024)
- Namely implement a first Pipeline/Workflow for code
- v0.0.4 - Serve the agent via an API (TBD)
- Serve the Agent via API
- v0.1.0 - User & Technical documentation, CI/CD Pipeline, GUI (TBD)
- 100% Test Coverage for API
- 50% Test Coverage for Core
- A Web Interface (If we receive help 🪄 )
- Capacity to create own tools #134
The project warmly welcome contributions ! We need maintainers & contributor with knowledge in CI/CD (Pytest expert, NodeJS/GitHub Action professional, Docker, AWS... 🧙♂️ ) and React expert 🥷 , doctorant/researcher 🧑🔬 to publish papers !
Tip
Check out our issues board to find tasks that need your help. We have a variety of issues suitable for different skill levels and areas of interest.
-
Pick an Issue: Choose an issue that interests you. Feel free to open your own issue or work on an existing one.
-
Comment on the Issue: Let us know you're interested in working on the issue by leaving a comment. This helps prevent multiple people from working on the same issue simultaneously.
-
Fork and Clone the Repository: Fork the repository to your GitHub account and clone it to your local machine. This will be your private workspace for the project.
-
Create a New Branch: Create a branch in your forked repository for the issue you are working on. Naming it relevantly to the issue can be helpful.
-
Make Your Changes: Work on the issue in your branch. Be sure to stick to the project's coding standards and guidelines.
-
Test Your Changes: Ensure that your changes do not break any existing functionality. Add any necessary tests if applicable.
-
Submit a Pull Request: Once you're satisfied with your work, commit your changes, push them to your fork, and submit a pull request to the main repository. Please provide a clear description of your changes and reference the issue number.
-
Code Review: Wait for a project maintainer to review your pull request. Be open to feedback and make any necessary adjustments.
-
Get Merged!: Once your pull request is approved, it will be merged into the project. Congratulations, you've contributed to the project!
For any questions, feedback, or inquiries related to the afaas project, don't hesitate to contact the project owner, Pierre-Henri AUSSEIL, at [email protected].