Your smart, reliable, and friendly personal AI assistant.
# Joanium
<p align="center">
<picture>
<source media="(prefers-color-scheme: light)" srcset="https://github.com/user-attachments/assets/d238934d-b5cc-4a81-b081-eca743ef30ff">
<img src="https://github.com/user-attachments/assets/d238934d-b5cc-4a81-b081-eca743ef30ff" alt="Joanium" width="200">
</picture>
</p>
<p align="center">
<strong>Think once, Ship more</strong>
</p>
<p align="center">
<a href="https://github.com/joanium/joanium/releases"><img src="https://img.shields.io/github/v/release/joanium/joanium?include_prereleases&style=for-the-badge" alt="GitHub release"></a>
<a href="https://github.com/joanium/joanium/stargazers"><img src="https://img.shields.io/github/stars/joanium/joanium?style=for-the-badge&color=yellow" alt="GitHub Stars"></a>
<a href="https://github.com/joanium/joanium/issues"><img src="https://img.shields.io/github/issues/joanium/joanium?style=for-the-badge&color=red" alt="Open Issues"></a>
<a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-blue.svg?style=for-the-badge" alt="MIT License"></a>
<a href="https://joeljolly.vercel.app/"><img src="https://img.shields.io/badge/Built%20by-Joel%20Jolly-blueviolet?style=for-the-badge" alt="Built by Joel Jolly"></a>
</p>
<p align="center">
<a href="https://joanium.com">🌐 Website</a> ·
<a href="https://joanium.com/docs">📖 Docs</a> ·
<a href="https://joanium.com/marketplace">🛍️ Marketplace</a> ·
<a href="https://www.joanium.com/download">⬇️ Download</a>
</p>
---
Joanium is a local-first desktop app for people who want an AI assistant that can actually work with projects, files, tools, schedules, personal context, and real integrations instead of acting like a thin chat wrapper.
It combines multi-provider chat, workspace-aware assistance, scheduled automations, autonomous agents, MCP, browser tooling, markdown-based skills and personas, and a discovery-driven extension system in one desktop product.
## 🤔 Why not just use Gemini or GeminiGoogle's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.