Living devlopment workspace for agents: Nabi Station
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle What I Built I work on multiple projects and with several AI coding agents in parallel every day. The problem is visibility. It is easy to lose track of which agent is still working, which one is waiting for input, which project has failing tests, or which repository needs attention—especially when my screens…
This submission is for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle What I Built. The author works on multiple projects and AI coding agents simultaneously daily. The challenge lies in keeping track of agent activity, project statuses, and ensuring engineering standards are met. To address this, they built Nabi Station, a visual control room for AI-assisted development.
Repositories become buildings in a miniature city, while AI agents turn into workers. Nabi Station uses Gemma, a local open-weight model running through Ollama, to analyze project structure and documentation. It summarizes activity and recommends improvements, all without sending code to an external AI provider. This tool targets developers who manage several agents and projects, freelancers, and small agencies.
The demo, accessible at http://127.0.0.1:5173, showcases the control room, which can be run locally using Node.js 22.13+ and pnpm 9.9.0.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
