thunderbolt
SHA-256An open-source, cross-platform AI client that gives you full control: choose any model, own your data, and avoid vendor lock-in. Self-host or use with local/frontier models. Enterprise-ready with security audit in progress.
Smart Download
Download Download Version
v0.1.107 · 129.1 MB
An open-source AI client that gives you full control over models, data, and avoids vendor lock-in. Self-host or use locally.
Core Features
- Cross-platform: web, iOS, Android, Mac, Linux, Windows
- Model flexibility: works with local (Ollama, llama.cpp) and cloud API (OpenAI-compatible)
- Data ownership: self-hosted backend keeps your data on-prem or local
- Enterprise features: security audit, FDE, on-prem deployment support
What It Can't Do
- •Still in early development; requires a running backend for authentication and search (can be disabled)
- •You must configure your own model provider (e.g., Ollama, llama.cpp, or OpenAI API key)
- •Designed for internal or local use; public cloud deployment needs careful security consideration
Use Cases
- Enterprise teams using AI internally with data staying on company servers for compliance
- Privacy-conscious individuals running local open-source models without relying on third-party APIs
Detailed Introduction
Thunderbolt is an open-source AI client from the Mozilla Thunderbird team, designed for users who want complete control over their AI experience. It runs on all major desktop and mobile platforms (web, iOS, Android, Mac, Linux, Windows) and supports any OpenAI-compatible model provider, including local engines like Ollama and llama.cpp. Unlike other AI clients (e.g., Jan or Ollama WebUI), Thunderbolt offers broader platform coverage, enterprise-grade features (on-prem deployment, security audit, FDEs), and a privacy-first approach that eliminates vendor lock-in. Note: the project is still under active development; it currently requires a backend for authentication and search (can be disabled), and you must provide your own model API keys or run local inference.
Tags
Getting Started
Download installer
Click the button above to download the installer for your system
Install the software
Install the appropriate package for your distro (dpkg / rpm / AppImage)
Run 'make doctor' to verify tools and get install commands for anything missing
Run 'make setup' to install frontend and backend dependencies and wire up symlinks
Run 'make up' to start Postgres + PowerSync in Docker
- Run 'make doctor' to verify tools and get install commands for anything missing
- Run 'make setup' to install frontend and backend dependencies and wire up symlinks
- Run 'make up' to start Postgres + PowerSync in Docker
SHA-256 checksum verified
Checksum extracted from GitHub official Release page
SHA256 Checksum
bc6cd75b759f7031a40339a36655878587357f16db7c13d08e4ef10377a8298aThis checksum is extracted from the GitHub Release page. Verify file integrity after download.
All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.
Open Source Transparency
View GitHub SourceUninstall Info
Delete the project directory; for Docker deployment, run 'docker-compose down -v' to remove containers and volumes.
No Extra Dependencies
Ready to use after download. No additional runtime required.
Similar Projects
Chatbox
Chatbox Community Edition is an open-source desktop client for interacting with multiple large language models. It supports OpenAI (ChatGPT), Azure OpenAI, Claude, Google Gemini Pro, Ollama (local models like Llama 2, Mistral), and ChatGLM-6B. All your chat data is stored locally on your device, ensuring privacy and preventing data loss. The app features a clean, ergonomic UI with dark mode, keyboard shortcuts, streaming replies, and full Markdown/LaTeX rendering with code highlighting. It also includes a prompt library, message quoting, and team collaboration for sharing API resources. Available on Windows, macOS, Linux, Web, iOS, and Android. The community edition is fully functional but may lack some advanced features from the pro version.
ollama
Ollama lets you download, run, and manage large language models locally. One command, multiple platforms, endless possibilities.
llama.cpp
High-performance LLM inference engine in C/C++ with minimal dependencies, supporting quantized models (1.5–8 bit) and diverse hardware (Apple Silicon, CUDA, Vulkan, etc.).