LLM
A command-line tool and Python library for prompting remote and locally installed language models.
These buttons open the developer's own site, repository or store listing in a new tab. wares.gg does not host downloads.
1 more ways to get LLM
Package managers
- Homebrew
brew install llm
About LLM
LLM runs prompts from the command line against OpenAI, Claude, Gemini, Mistral, DeepSeek, Qwen and dozens of other models. Some run through remote APIs and others run on your own machine. Every prompt and response is logged to a SQLite database, so you can search your history later.
It also generates and stores embeddings, extracts structured data with schemas, supports tools, templates and fragments, and gains new models through plugins. The same features are available as a Python library for scripting.
Strengths
- One interface for many remote and local models
- Logs all prompts and responses to SQLite
- Plugin system for adding models and embeddings
- Usable as a CLI or a Python library
Limitations
- Command-line only, with no graphical interface
- Local models need an extra plugin
Details
- Pricing
- FreeFree to install; remote model providers charge for their own APIs.
- License
- Proprietary
- Developer
- Simon Willison
- Platforms
- Command line
- How it runs
- Downloadable app
- Best suited for
- Developers who want to prompt language models from the terminal and scripts
- Categories
- Local AI tools, Developer tools, AI assistants
- Last verified
- Added
- Provenance
- Facts checked against the developer's own pages and store listings, 1 sources on file.
Alternatives to LLM
Compare allSoftware that can replace LLM for an important use case, and what changes if you switch.
AIChat
A command-line tool for chatting with language models, with a shell assistant, RAG and agents.
AIChat is an MIT or Apache licensed terminal tool for many providers that adds a shell assistant, RAG and agents, configured through YAML files instead of a Python library.
Fabric
A command-line tool for running a crowdsourced library of reusable AI prompts against language models.
Fabric runs a crowdsourced library of reusable prompt patterns in shell pipelines against local or remote models, focusing on repeated text tasks rather than logging prompts to SQLite.
Ollama
The simplest way to pull down an open language model and run it on your own machine, from one command or a desktop app.
Ollama provides a command line and localhost REST API for running open models locally, but it focuses on local models rather than one interface for many remote providers.
llama.cpp
The C++ engine most local AI apps are built on, running language models on ordinary hardware.
llama.cpp runs models from the command line with a built-in server and no Python, but it handles local models only and has no SQLite prompt logging or plugin system.
RamaLama
Command-line tool that pulls AI models from any source and serves them locally in containers.
RamaLama pulls models from many sources and serves them locally in containers from the command line, requiring a container engine and focusing on local models only.
llamafile
Packages a language model and the code to run it into one executable file that works on several operating systems without installation.
llamafile runs a local model packaged as one executable from the terminal, dropping llm's remote providers, plugins and prompt logging in exchange for no installation.
LLM as an alternative
Listings that name LLM as an alternative.
Google AI Studio
A web workspace for trying Google's Gemini models and getting API keys for the Gemini API.
LLM is a command-line tool and Python library for prompting many remote and local models, logging everything to SQLite instead of a web playground.
MLX LM
A Python package and command-line tool for running and fine-tuning language models on Apple silicon.
LLM is a command-line tool and Python library for prompting remote and local models with SQLite logging, but local models need a plugin.
Similar software
Related functionality, not necessarily a direct replacement.
Open Interpreter
A command-line coding agent built to work with open language models such as Kimi and GLM.
Crush
Terminal coding agent that works with whichever large language model you point it at.
Aider
AI pair programming in a terminal, working directly on your git repository and committing as it goes.
Chatbox
A desktop and mobile chat client for AI models, where you supply your own API keys or point it at a local model.
Jan
An open-source ChatGPT replacement that runs entirely offline, and can also front cloud providers when you want them.
LM Studio
A polished desktop app for downloading, running and chatting with local language models, with an OpenAI-compatible server built in.
