DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5

How to use LLM: what you can do with it

What is LLM? LLM is a CLI tool and Python library for interacting with OpenAI, Gemini, Qwen, DeepSeek, Mistral and dozens of other large language models, through remote APIs or models installed on your own machine. It can run prompts from the command line, store prompts and responses in SQLite, generate embeddings, extract structured content, and let models execute tools.

How do I use it? Install with pip install llm; then Store your key with llm keys set openai; run llm "Ten fun names for a pet pelican". Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

3 use cases

Quick start with LLM

  1. Check you have what it needs: Python with pip, or Homebrew, pipx or uv; An API key for a hosted model, or a local model server such as Ollama or LM Studio; Plugins for providers such as Gemini.
  2. Open simonw/llm on GitHub and read the README and license.
  3. Install with pip install llm
  4. Store your key with llm keys set openai
  5. Run llm "Ten fun names for a pet pelican"
  6. Pipe a file in with cat myfile.py | llm -s "Explain this code"

These steps come from our top use case, Run prompts from the command line, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for simonw/llm

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Best AI repos for Software and DevOps

About this repo

  • Who it is forDevelopers and tinkerers who want to script LLM prompts from the shell and keep a log of them.
  • Why it is hot13k stars, talked about in 2 AI sources we track
  • LanguagePython
  • Sourcegithub.com/simonw/llm ยท Back to Hot repos

Requirements

  • Python with pip, or Homebrew, pipx or uv
  • An API key for a hosted model, or a local model server such as Ollama or LM Studio
  • Plugins for providers such as Gemini

Add this badge to your README

Maintain LLM? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/simonw/llm.svg)](https://dedupedai.com/use-cases/simonw-llm/?utm_source=github&utm_medium=badge&utm_campaign=simonw-llm)

HTML 

<a href="https://dedupedai.com/use-cases/simonw-llm/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=simonw-llm"><img src="https://dedupedai.com/badge/simonw/llm.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about LLM

What is LLM?

LLM is a CLI tool and Python library for interacting with OpenAI, Gemini, Qwen, DeepSeek, Mistral and dozens of other large language models, through remote APIs or models installed on your own machine. It can run prompts from the command line, store prompts and responses in SQLite, generate embeddings, extract structured content, and let models execute tools. It is an open-source project on GitHub: https://github.com/simonw/llm.

How do I use LLM?

Install with pip install llm; then Store your key with llm keys set openai; run llm "Ten fun names for a pet pelican". The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is LLM for?

Developers and tinkerers who want to script LLM prompts from the shell and keep a log of them.

What can I do with LLM?

3 use cases so far, for example: Run prompts from the command line; Chat with a local model through LLM and Ollama; Point LLM at any OpenAI-compatible endpoint. Each has steps and a copy-paste agent prompt.

What do I need to run LLM?

Python with pip, or Homebrew, pipx or uv; An API key for a hosted model, or a local model server such as Ollama or LM Studio; Plugins for providers such as Gemini.

What are alternatives to LLM?

Other hot AI repos in Software and DevOps: ECC, Thinkrail, Superpowers, Deep Infer, Instructor.

Is LLM safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.