OpenSource-Hub
T

thunderbolt

SHA-256
4.7k stars·AI Productivity·SHA-256 checksum verified

An 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

AI clientself-hostedprivacycross-platformOpenAI-compatiblelocal inferenceenterprise

Getting Started

1

Download installer

Click the button above to download the installer for your system

2

Install the software

Install the appropriate package for your distro (dpkg / rpm / AppImage)

3

Run 'make doctor' to verify tools and get install commands for anything missing

4

Run 'make setup' to install frontend and backend dependencies and wire up symlinks

5

Run 'make up' to start Postgres + PowerSync in Docker

Install Guide
  1. Run 'make doctor' to verify tools and get install commands for anything missing
  2. Run 'make setup' to install frontend and backend dependencies and wire up symlinks
  3. Run 'make up' to start Postgres + PowerSync in Docker
File Integrity

SHA-256 checksum verified

Checksum extracted from GitHub official Release page

SHA256 Checksum

bc6cd75b759f7031a40339a36655878587357f16db7c13d08e4ef10377a8298a

This 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 Source
Environment Guide

Uninstall 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.

Project Info
LicenseMPL-2.0
Last Updated2026-07-16T06:14:50Z
GitHub RepositoryOfficial Website

Similar Projects