LWE (LLM Workflow Engine) is a command-line interface and workflow manager designed for interacting with large language models (LLMs) like ChatGPT and GPT-4. It enables users to leverage LLMs directly from their terminal, integrate them into shell workflows, and extend functionality through a plugin architecture supporting multiple LLM providers and tool use.

How It Works

LWE provides a shell-native experience for LLM interaction, allowing direct API calls to OpenAI endpoints and supporting various LLM providers via plugins. Its core advantage lies in its workflow integration capabilities, particularly with tools like Ansible, and its extensible plugin system for custom functionality and LLM provider support.

Quick Start & Requirements

• Install via pip: pip install llm-workflow-engine
• Requires Python 3.7+ and an OpenAI API key.
• Docker image available (experimental).
• Documentation: https://github.com/llm-workflow-engine/llm-workflow-engine

Highlighted Details

• CLI and shell integration for LLM interaction.
• Supports multiple LLM providers (OpenAI, Cohere, Hugging Face, etc.) via plugins.
• Enables LLM integration into workflows, including Ansible Playbooks.
• Offers a Python API for programmatic use.

Maintenance & Community

The project is a successor to the original ChatGPT Wrapper project. Contributions are welcomed via GitHub issues.

Licensing & Compatibility

• MIT License.
• Permissive license suitable for commercial use and integration into closed-source projects.

Limitations & Caveats

The Docker image is noted as experimental. The project's history indicates it evolved from previous projects, suggesting potential for breaking changes or API shifts.