Self-hosted ChatGPT-style chat platform that unifies many AI providers, with Agents, MCP support, Artifacts, and multi-user auth.
- Stars
- 1,269
- Forks
- 149
- Open issues
- 10
- Last commit
- 29 days ago
What is it?
GPT Mobile is a native Android chat client built with Kotlin, Jetpack Compose and Material 3. You supply your own API keys for OpenAI, Anthropic, Google Gemini, Groq or a local Ollama server, and can ask several models the same question in one session to compare their answers. Each provider profile supports custom API URLs and custom model names, along with temperature, top p and system prompt settings.
Chat history is stored only on the device. Credentials are encrypted with the Android Keystore and excluded from backup and export. Requests go only to the model providers and tools you select. Optional agent tools can be assigned per profile, including native tool calling, web search and URL reading through Firecrawl, Perplexity or Exa, and MCP Streamable HTTP servers. Profiles stay chat-only until tools are explicitly assigned.
The app is distributed through F-Droid, Google Play and GitHub Releases, and includes a Material You interface with dark mode and dynamic theming.
Key features
- 01Send one prompt to OpenAI, Anthropic, Gemini, Groq and Ollama models in parallel
- 02Custom API URLs, model names, temperature, top p and system prompt per profile
- 03Optional agent tools with native tool calling and web search via Firecrawl, Perplexity or Exa
- 04MCP Streamable HTTP server support with public, bearer or OAuth authentication
- 05Local-only chat history with credentials encrypted by Android Keystore
Use cases
- Comparing answers from several LLM providers to the same question on a phone
- Chatting with a self-hosted model on a local Ollama server from Android
- Using your own API keys instead of a paid subscription to a single chat service
- Giving a mobile chat assistant access to web search or MCP tools with explicit opt-in
Quick start
- 1
Download the app from F-Droid, Google Play, or GitHub Releases
- 2
Open the app and add your own API key for a supported provider
Things to know
- Android only; there is no iOS or desktop version.
- Licensed under GPL-3.0, a copyleft license that requires derivative works to remain open source.
- You need your own API keys from each model provider to use the chat features.
In collections
Topics
FAQ
- What is gpt_mobile?
- Android chat app that sends one prompt to multiple LLM providers at once, using your own API keys. GPT Mobile is a native Android chat client built with Kotlin, Jetpack Compose and Material 3. You supply your own API keys for OpenAI, Anthropic, Google Gemini, Groq or a local Ollama server, and can ask several models the same question in one session to compare their answers. Each provider profile supports custom API URLs and custom model names, along with temperature, top p and system prompt settings.
- Is gpt_mobile free to use? What license does it have?
- gpt_mobile is open source under the GPL-3.0 license. Check the license terms before using it in commercial products.
- Is gpt_mobile still maintained?
- Actively maintained. The last commit to gpt_mobile was on Oct 10, 2026.
- What can I use gpt_mobile for?
- Comparing answers from several LLM providers to the same question on a phone Chatting with a self-hosted model on a local Ollama server from Android Using your own API keys instead of a paid subscription to a single chat service Giving a mobile chat assistant access to web search or MCP tools with explicit opt-in
- How do I install gpt_mobile?
- Download the app from F-Droid, Google Play, or GitHub Releases Open the app and add your own API key for a supported provider
- Where can I get gpt_mobile?
- The source code and installation instructions are on GitHub: https://github.com/Taewan-P/gpt_mobile
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
An Android AI chat client, forked from RikkaHub, with partner chats, remote computer control over SSH and screen streaming, and cross-app translation.
Android app for chatting with GGUF models running locally via llama.cpp, or with remote providers like OpenAI, Anthropic, Ollama and DeepSeek.
A terminal chat client for Ollama, OpenAI, Anthropic and other pydantic-ai-supported LLM providers.
An Android voice assistant app that lets you chat with OpenAI and other LLMs using speech input, image recognition and image generation.
A command-line tool and Python library for running prompts and chats against remote and locally installed large language models.