Anyone juggling multiple AI coding agents across different terminals and ticket trackers knows the friction: context lives in one place, execution happens in another, and switching between them burns time. Mozzie is a new open-source desktop app that tries to fix that by putting work items and their AI agents in the same window.
The concept is straightforward. Each task in Mozzie gets its own workspace that can spawn a terminal or an AI coding agent. Instead of alt-tabbing between your issue tracker, your IDE, and three terminal windows running different agents, you manage everything from one local interface. Tasks carry their context with them, so when you come back to something you paused yesterday, the relevant files, terminal history, and agent state are still attached.
Mozzie runs entirely on your machine with no cloud dependency, which matters if you're working with proprietary code or just prefer keeping your workflow local. It's built as a desktop app rather than a browser-based tool, and it's designed around the assumption that developers increasingly run multiple AI agents in parallel rather than one at a time.
The tool is early-stage and available on GitHub. It fills a gap that's been widening as AI coding assistants multiply. Right now, if you use Cursor for one task, Claude Code for another, and Aider for a third, there's no unified way to track what each agent is doing or switch between them without losing context. Mozzie is a bet that this orchestration layer is a real need, not just a nice-to-have.
For solo developers and small teams running multiple agents daily, it's worth a look. The local-first approach means there's minimal setup friction, and since it's open source, you can inspect exactly what it does with your data.