LLM
Command-line tool and Python library by Simon Willison for running prompts against many models through plugins.
0 members list LLM, unchanged over the last 12 weeks, data as of 15 October 2026
Members who list LLM in their Stack, by week.
Be the first to add LLM
Nobody on Stackness runs LLM yet. Add it to your stack and you're the first member running it.
About LLM
LLM is a command-line tool and Python library for running prompts against large language models through a plugin system. It supports models from OpenAI, Anthropic, Google, and many others, both through remote APIs and models that run locally on your machine. The tool can store prompts and responses in SQLite, generate embeddings, extract structured content from text and images, and grant models the ability to execute tools. It's developed by simonw and released under the Apache 2.0 license.
LLM can be installed via pip, Homebrew, pipx, or uv. Users can run prompts from the command-line, start interactive chats, and configure API keys for different model providers. The tool supports OpenAI-compatible endpoints and includes plugins for accessing specific model providers like Gemini and Claude. Models capable of running on local machines can be accessed through plugins like Ollama, allowing developers to work with language models without relying on external APIs.
Checked 15 October 2026.
Nobody on Stackness runs LLM yet.
Sign up and add itPosts about LLM
- OpenAI Decisions API vs Jev: price per decision, latency, images and what switching costs
OpenAI Decisions costs 1.6 times Jev per decision and answers slower, but takes images without an experimental flag and comes with OpenAI's data terms.