llm (Simon Willison)
A CLI and Python library for local LLMs and remote APIs, with SQLite prompt history, embeddings, and support for OpenAI-compatible endpoints.
LLM is an Apache-2.0 command-line tool and Python library for sending prompts to local models and remote APIs. Local model support comes through plugins; cloud providers require their own API access. It can also connect to an arbitrary OpenAI-compatible Chat Completions endpoint, including LM Studio.
You can run prompts and interactive chats, store prompts and responses in SQLite, and generate and save embeddings. LLM also supports extracting structured content from text and images and giving models access to tools. Available capabilities depend on the selected model and plugin.
The CLI fits terminal scripts, while the Python library exposes model access to applications. Prompt history is stored locally, but requests sent to a remote provider are processed by that provider.
