What it does
LLM lets you send prompts to AI models straight from the command line, the text window programmers use to type instructions. It works with models from OpenAI, Anthropic, Google and many others.
Plugins add more models, including ones that run on your own computer through tools like Ollama. Every prompt and reply can be saved in a small database so you can look back at them later.
It can also pull structured information out of text and images, create embeddings (number codes that help search by meaning), and let models use tools. It also works as a Python library.
Who it's for
Developers, data people and curious terminal users who want one simple tool to try many AI models.
Can I use it without coding?
With some setup. You install it with a package manager and use it by typing commands. New to this? Start here.
Can I run it?
- Cost
- Free, but needs an AI accountThe software is free, but it uses an online AI service (like OpenAI or Anthropic), which usually charges for use.
- Computer
- An ordinary computer is fine
- Privacy
- Your choice: run it on your device or use an online service
- API key
- Not needed
Try it
- Install LLM with Python's package installer or with Homebrew.
- Add an API key for a service like OpenAI, or install a plugin to use a model on your own computer.
- Type a prompt in your terminal, or start an interactive chat.
Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?
Before you install
- Only download from the official GitHub page. Copies with similar names exist for many popular projects.
- License (Apache-2.0): Permissive: free to use, change and share, including for business.
- More on staying safe