LLM

LLM is an open-source command-line utility and Python library designed to streamline interactions with large language models across multiple providers. It allows developers to execute prompts directly from the terminal, manage local and remote models, store prompt histories, and generate vector embeddings inside SQLite databases. Supporting providers like OpenAI, Anthropic, Google, and Meta, LLM offers extensive plugin architectures to extend functionality, enable custom model integrations, and connect to arbitrary OpenAI-compatible endpoints such as LM Studio. Users can extract structured content from text or images and run local open-weight models without relying on cloud services. The tool installs easily through standard package managers like pip, Homebrew, pipx, or uv, making it adaptable to diverse development workflows and shell environments. By providing unified command syntax and simple Python bindings, LLM simplifies model evaluation, automated scripting, and custom AI tool creation for developers working across diverse infrastructure setups.