OpenCode
Lets you hand coding tasks to an open source AI agent that works with many model providers
by Anomaly
LLM
Lets you ask many AI models questions from the terminal and keeps a log of every answer
What it does
LLM is a command-line tool and Python library by Simon Willison for using AI models from your terminal. You type a prompt or pipe in a file, image or command output, and it replies with the model you choose, from OpenAI, Anthropic, Google and others through plugins, or a model on your own machine. Every prompt and response is saved in a local SQLite database you can search later. It suits people who like working in the terminal and want one tool for many models.
It works with dozens of models through plugins and keeps a searchable history of everything you asked, all from one small command.
Before you start
- 1A computer with macOS, Windows or Linux.
- 2Python 3.10 or later
- 3An API key from an AI model provider, or a model running on your own computer
- !Pay per use. The AI service it calls charges for what you use.
How to start
- Install itPaste the install request into an AI agent you already use, or run the official command yourself or follow the official guide.macOS, Windows, Linux
pip install llmmacOS, Windows, Linuxpipx install llmmacOS, Windows, Linuxuv tool install llm - Set it upFollow the first-run steps in the official guide.
- Give it a first taskDescribe what you want in your own words, and check the first result before relying on it.
Steps follow the creator's instructions.
Stuck setting it up?
Tell us what happened. We confirm scope and price before any paid work.
