LLM (Simon Willison)
CLI and Python library for interacting with any LLM.
Overview
llm is a command-line tool and Python library by Simon Willison for prompting models, logging every interaction to SQLite and working with embeddings. Plugins add support for virtually every provider and local runtime.
- SQLite logging
- Plugin system
- Embeddings
- Templates
- Tool calling
Our verdict
What we like
- Unix-friendly piping
- Huge plugin ecosystem
Watch out for
- Command-line only
Works with these providers
Keys from these providers work in this app. Usage is billed by the provider at its list price.
BYOK Key Safety Score
Key handling in LLM (Simon Willison)
Grade A
Your key is stored on your device and requests go directly to the provider.
- Key storage40/40
Key stays on your device; requests go direct to the provider.
- Auditable code25/25
Open source: anyone can verify how keys are handled.
- Self-hosting8/15
Runs as a local app, but not as a self-hosted service.
- Offline option10/10
Supports local models, so no key is needed at all for private work.
- Provider choice10/10
13 provider options, which lets you pick the provider whose data terms you trust.
Whatever the score, give each app its own key, set a monthly spend limit with your provider, and revoke keys you no longer use. Read the key-safety checklist.
LLM (Simon Willison) FAQ
- Does LLM (Simon Willison) support bring your own key?
- Yes. LLM (Simon Willison) accepts your own API key from OpenAI, Anthropic, Google Gemini, OpenRouter, Mistral, Groq, DeepSeek, xAI, Ollama, Perplexity, Together AI, Cohere and OpenAI-compatible. Usage is billed by the provider at its API rates.
- Where does LLM (Simon Willison) store my API key?
- On your device. Requests go directly from LLM (Simon Willison) to the provider. Its BYOK Tools Key Safety Score is 93/100.
- Is LLM (Simon Willison) free?
- Open source: Free & open source. API usage is billed separately by your model provider.
- Is LLM (Simon Willison) open source?
- Yes. The source code is at https://github.com/simonw/llm.
- Can LLM (Simon Willison) run local models?
- Yes. It can connect to local runtimes such as Ollama or LM Studio, so no API key is needed for private or offline use.
- Which platforms does LLM (Simon Willison) support?
- CLI, macOS, Windows, Linux.
Community reviews
No reviews yet.
Alternatives to LLM (Simon Willison)
All command line →AIChat
Command Line
All-in-one LLM CLI with chat REPL, RAG, agents and a local server.
Fabric
Command Line
Open-source framework of crowdsourced AI prompts for the CLI.
gptme
Command Line
Personal AI agent in your terminal with code execution.
Open Interpreter
Command Line
Let language models run code on your computer from a terminal.
Mods
Command Line
AI on the command line from Charm, built for pipelines.
Wave Terminal
Command Line
Open-source terminal with inline AI chat and graphical widgets.