LLM (CLI Tool)

LLM is a command-line tool and Python library for interacting with language models, created by Simon Willison — one of the most respected voices in the developer community and co-creator of the Django web framework. LLM provides a clean, Unix-philosophy interface for working with Claude, GPT-4, and dozens of other models through a consistent command-line interface.

What makes LLM special is Willison's design philosophy. The tool follows Unix conventions — it reads from stdin, writes to stdout, and plays nicely with pipes and other command-line tools. This means you can integrate LLM into shell scripts, data pipelines, and automation workflows in ways that GUI-based AI tools cannot match.

LLM also includes a plugin ecosystem that extends its capabilities to support local models, custom providers, and specialized workflows. The tool stores conversation logs in a SQLite database, enabling analysis of past interactions and systematic evaluation of model outputs. This combination of simplicity, extensibility, and observability makes LLM the power tool for developers who live in the terminal.