LLM Workflow Engine
A command-line power tool and workflow manager for talking to ChatGPT and other LLMs from the terminal, with a plugin architecture, multiple provider support and Ansible-based workflow integration.
LLM Workflow Engine (LWE) is a command-line power tool and workflow manager for large language models, evolved from the earlier ChatGPT Wrapper project. It lets a user call and interact with ChatGPT or GPT-4 directly from a shell, using the official ChatGPT API to reach any model available on the user's OpenAI account.
A plugin architecture extends its functionality, and provider plugins let it talk to other LLMs such as GPT-3, Cohere or Hugging Face models in addition to OpenAI's own. It can integrate LLM calls into larger automated workflows through Ansible Playbooks, supports tool use for providers that offer it, ships a Docker image, and includes a Python library for using ChatGPT or GPT-4 from Python scripts.
It is licensed under MIT.