Chatbox is a cross-platform desktop, web, and mobile AI copilot that unifies access to multiple LLM providers under a single interface. It stores user data locally on the device while requiring users to connect their own external or local model services for inference.
Project overview
It consolidates interactions with various language model providers into a single cross-platform interface while applying a local-first approach to user data storage.
Project type
Model Runtime · Prompt Engineering
Use cases
Chat Assistants · Coding & Development
Deployment
Refer to project documentation
License
GPL-3.0
Best for
General users and developers who need a unified, cross-platform desktop client to interact with various external APIs or local servers while retaining conversation data on their local device.
Key capabilities
Connects to various language model providers, including OpenAI, Azure OpenAI, Claude, Google Gemini Pro, Ollama, and ChatGLM.
Stores user data locally on the device during operation to support privacy and prevent data loss.
Ready for Windows, Mac, and Linux users via downloadable installation packages.
Allows users to create images using Dall-E-3.
Provides rapid responses with immediate, progressive replies.
Generates messages with Markdown and Latex formatting coupled with syntax highlighting.
Allows saving and organizing prompts for reuse and quoting messages for context.
Offers native iOS and Android applications for on-the-go access.
Limitations and risks
While client operation is local and data is stored on the device, chat interactions rely on optional external APIs such as OpenAI, Claude, Azure, or Google Gemini Pro for remote inference, unless connected to a local server like Ollama.
Download the appropriate installer for your platform from the releases page, install and launch Chatbox, configure an AI provider in settings, and begin interacting.
Alternatives and comparisons
A privacy-preserving AI writing companion supporting multiple engines, including WebLLM and Ollama, for users who need note-taking rather than a multi-provider chat interface.
An efficient API for fine-tuning and running personalized open-source LLMs locally or in a private cloud, intended for users who need to build models rather than use a chat client.
Open-source Chinese LLaMA and Alpaca models and tools for improving Chinese semantic understanding, for users needing underlying models rather than a frontend client.