Skip to main content

AI-driven task automation system

Project description

AgentForge

AgentForge - is an advanced AI-driven task automation system designed for generating, prioritizing, and executing tasks based on a specified objective.

The primary goal of this project is to establish a user-friendly, low-code framework that empowers users to rapidly iterate on cognitive architectures. Simultaneously, the framework is designed to accommodate developers with a seamless integration process for incorporating new logic modules as the AI landscape continues to evolve. By fostering a collaborative and accessible environment, AgentForge seeks to contribute to the advancement of AI research and development across various domains.

Salience.py

Installation

To install AgentForge, follow these steps:

Set your environment variables:

Claude: ANTHROPIC_API_KEY OpenAI: OPENAI_API_KEY Google: GOOGLE_API_KEY

Install AgentForge:

pip install agentforge

Navigate to where you want your bot's project folder:

cd c:\bot\folder

Run the initialization script:

agentforge init

Additionally, if you just want to try our demo agent, run the following command to copy our bot script to your project folder:

agentforge salience

Devbuild installation

If you want to install the build from the dev branch and help with development, follow these instructions instead:

Clone the GitHub repository:

git clone https://github.com/DataBassGit/AgentForge.git

Install the required dependencies:

pip install -e .

Navigate to /tests/examples/.agentforge, and use the .env.example to create a .env file that contains your api keys.

Usage

Modify the agent prompts in /tests/examples/.agentforgedefault.json. At the top of the file you will edit the name, objective, and tasks. This should be enough to start.

Navigate to /tests/examples/ in your console and run

python salience_old.py

You will be asked if you would like to run in manual mode or auto mode. Choose manual mode for now. Before each round of execution, you will be asked to continue. The agent will automatically provide feedback after each execution. This will add the feedback to the execution prompt. You can also type whatever feedback you would like to provide to the bot manually.

Contributing

Feel free to open issues or submit pull requests with improvements or bug fixes. Your contributions are welcome!

License

This project is licensed under the GNU General Public License. See LICENSE for more details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agentforge-0.1.2.tar.gz (45.6 kB view hashes)

Uploaded Source

Built Distribution

agentforge-0.1.2-py3-none-any.whl (56.7 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page