A GNOME desktop app for chatting with AI models, with a focus on running models locally on Linux.
hecrj/icebreaker
A local AI chat app built with Rust and the iced GUI toolkit, running models through llama.cpp and Hugging Face.
Open-source alternative to:ChatGPT
- Stars
- 468
- Forks
- 36
- Open issues
- 7
- Last commit
- 2 months ago
What is it?
Icebreaker is a desktop chat application that runs large language models locally rather than sending conversations to a hosted service. It is written in Rust and uses the iced GUI toolkit for its interface, with llama.cpp handling inference and Hugging Face as the source for models.
The project is distributed as a Rust crate and can be installed with cargo, or built from the master branch. Pre-built binaries are not yet provided, so users need a Rust toolchain to try it.
The project is a small, focused example of a native Rust AI application, combining an iced desktop UI with a local inference backend.
Key features
- 01Runs chat models locally on the user's machine.
- 02Built with Rust and the iced cross-platform GUI toolkit.
- 03Uses llama.cpp for model inference.
- 04Loads models from Hugging Face.
- 05Installable via cargo, or buildable from source.
Use cases
- Chatting with an LLM without sending conversations to a cloud service.
- Studying how to build a native Rust desktop app around a local inference engine.
- Experimenting with open models on a personal computer.
Quick start
- 1
Install the latest release from crates.io with cargo
cargo install icebreaker
Things to know
- No pre-built binaries are provided, so you must build it with Rust and cargo.
- The README does not document the project's stability or current status.
In collections
Topics
FAQ
- What is icebreaker?
- A local AI chat app built with Rust and the iced GUI toolkit, running models through llama.cpp and Hugging Face. Icebreaker is a desktop chat application that runs large language models locally rather than sending conversations to a hosted service. It is written in Rust and uses the iced GUI toolkit for its interface, with llama.cpp handling inference and Hugging Face as the source for models.
- Is icebreaker free to use? What license does it have?
- icebreaker is open source under the MIT license. Check the license terms before using it in commercial products.
- Is icebreaker still maintained?
- Updated within 6 months. The last commit to icebreaker was on Aug 28, 2026.
- What can I use icebreaker for?
- Chatting with an LLM without sending conversations to a cloud service. Studying how to build a native Rust desktop app around a local inference engine. Experimenting with open models on a personal computer.
- How do I install icebreaker?
- Install the latest release from crates.io with cargo: cargo install icebreaker
- Where can I get icebreaker?
- The source code and installation instructions are on GitHub: https://github.com/hecrj/icebreaker
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A browser-based chat interface for local LLMs served by Ollama, with chats stored in IndexedDB on your own machine.
Cherry Studio is a cross-platform desktop AI client that connects to many LLM providers, local models and 300+ preset assistants.
A free, open source desktop AI studio for Windows and Linux that combines local chat, image and video generation, and a coding agent in one app.
Single-file local runner for GGUF language models with a built-in KoboldAI web UI, supporting text, image, speech and music generation.
Guide and chatbot web app for running a small local LLM with an OpenAI-compatible API on consumer-grade hardware via Ollama, vLLM or llama-cpp-python.