llms.py

Lightweight OpenAI compatible CLI, server gateway and OSS Open WebUI alternative for Local and Cloud LLMs

530+ Models
24 Providers
Extensible
Get StartedView on GitHub

Quick Install

pip install llms-py

šŸ’¬ Simple Chat

Ask questions directly from the command line

terminal
$ llms "What is the capital of France?"
Paris is the capital of France. It's located in the north-central part of the country and is known for its art, fashion, gastronomy, and culture. The city is home to iconic landmarks like the Eiffel Tower, the Louvre Museum, and Notre-Dame Cathedral.

Run Server

llms --serve 8000

šŸ’¬ ChatGPT-like Interface

Modern, fast, and privacy-focused web UI for all your local and remote LLMs

llms.py main chat interface showing conversation with AI

What's New in v3

Major release focused on extensibility, expanded provider support, and enhanced user experience

530+ Models from 24 Providers

Powered by models.dev integration with automatic daily updates

Extensions System

Add features, providers, and customize the UI with flexible plugins

Gemini File Search

RAG workflows with document stores, categories, and contextual chat

Tool Support

First-class Python function calling for LLM interactions with your environment

MCP Support

Connect to Model Context Protocol servers for extended tool capabilities

Calculator & Run Code UIs

Beautiful UIs to evaluate math and execute Python, JS, TS & C# code

Media Gallery

Browse and manage all your generated images and audio in one place

Image & Audio Generation

Built-in support for Gemini, OpenAI, OpenRouter, Chutes, and Nvidia

KaTeX Math Rendering

Beautiful LaTeX math typesetting for equations and formulas

Powerful Model Selector

Smart search, advanced filtering, sorting, and favorites system

Learn more ā†’
Model Selector with search and filtering

Gemini File Search & RAG

Build knowledge bases with document stores and contextual AI chat

Learn more ā†’
Document Upload with Categories
Filestore Management
Bidirectional Sync
Search All Documents
Search by Category
Gemini RAG chat with document context

Tools & Function Calling

First-class Python function calling for LLM interactions

Learn more ā†’
Tools Page
Tool Selector UI
File System Tools
Time Tools
Tool Call Example
Python Code Execution Tool
JavaScript Code Execution Tool
C# Code Execution Tool

MCP Support

Extend LLM capabilities with Model Context Protocol servers

Learn more ā†’
MCP Servers with registered tools
Gemini image generation via MCP
Add MCP Server
Execute MCP Tools
Tool Execution Results
Interactive HTML results from MCP tools

Calculator UI

Beautiful interface for evaluating Python math expressions

Learn more ā†’
Calculator UI with Python math support

Run Code UI

Execute Python, JavaScript, TypeScript, and C# code with syntax highlighting

Learn more ā†’
Run Python Code with syntax highlighting

KaTeX Math Typesetting

Beautiful rendering of LaTeX math expressions

Learn more ā†’
Popular math expressions
Basic math expressions

Image & Audio Generation

Seamless media generation through UI and CLI

Image Generation ā†’Audio Generation ā†’
Image Generation with aspect ratio selection
Audio Generation with TTS

System Prompts Library

200+ curated system prompts for every use case

Learn more ā†’
System Prompts Library

Runtime Provider Management

Enable or disable providers on the fly without configuration changes

Learn more ā†’
Provider management interface

Ready to Get Started?

Install llms.py and start chatting with 530+ AI models in minutes

View DocumentationView on GitHub