# Chatbox

> A desktop and web chat client for ChatGPT, Claude, Gemini, Ollama and other LLMs

- Category: App UIs & Builders / Chat UIs
- Language: TypeScript
- Licence: GPL-3.0
- Repository: https://github.com/chatboxai/chatbox
- Website: https://chatboxai.app
- Canonical page: https://ai-tldr.dev/tools/chatbox/

## In short

Chatbox is a cross-platform chat client for large language models. It sits in the Chat UIs category of the App UIs & Builders tools and is open-source, written in TypeScript and licensed GPL-3.0. To get started: install the app.

## Overview

Chatbox is a cross-platform chat client for large language models. Instead of opening a separate web app for each provider, you connect your own API keys (or a local Ollama instance) and talk to OpenAI, Claude, Google Gemini, Azure OpenAI and others from one window. It runs as a native desktop app on Windows, macOS and Linux, with a web version and mobile apps as well.

It is aimed at people who already have model API access and want a single, self-hosted-feeling front end rather than juggling multiple browser tabs and subscriptions. Your conversation history is stored locally on your device, so chats stay private and don't get lost.

As a chat UI, Chatbox focuses on the front-end experience: streaming replies, Markdown, LaTeX and code highlighting, a prompt library, dark theme and keyboard shortcuts. The Community Edition is open-sourced under GPLv3 and built with Electron and React.

## What it does

- Connect to many providers: OpenAI (ChatGPT), Azure OpenAI, Claude, Google Gemini, Ollama for local models, and ChatGLM-6B
- Local data storage keeps your chat history on your own device
- Streaming replies with Markdown, LaTeX and syntax-highlighted code blocks
- Image generation through DALL-E-3
- Prompt library and message quoting to save and reuse context
- Available on Windows, macOS and Linux desktop, plus web and native iOS/Android apps

## Getting started

Most users just install the prebuilt app and add an API key. Developers can also clone the repo and run it from source.

1. Install the app

   Download the installer for your platform from the GitHub releases page (Setup.exe for Windows, the macOS Intel/Apple Silicon builds, or the Linux AppImage), then install and launch it.

2. Configure a provider

   Open Settings, pick a provider such as OpenAI or Claude, and paste in your API key. For local models, point Chatbox at a running Ollama instance. Then start chatting.

3. Run from source (optional)

   Chatbox is built with Electron and React. With Node.js 20-22 and pnpm 10+, clone the repo and install dependencies.

```bash
git clone https://github.com/chatboxai/chatbox.git
cd chatbox
pnpm install
```

4. Start the dev server

   Launch the app in development mode with hot-reload.

```bash
pnpm run dev
```

## When to use it

- Use one app to switch between ChatGPT, Claude and Gemini with your own API keys instead of separate browser tabs
- Chat with local models through Ollama for offline or private workflows
- Keep a searchable, locally stored history of your AI conversations
- Build and reuse a prompt library for repeated coding, writing or research tasks