Meet Gnito: Your AI. Your Machine. Your Rules.
Meet Gnito: Your AI. Your Machine. Your Rules. What if you could run your own AI workspace locally, choose your AI provider, and keep control of your data? That's what I'm building with Gnito . Gnito is an open-source, local-first, self-hosted AI workspace built with React, TypeScript, Node.js and SQLite. It doesn't bundle an AI model. Instead, it uses BYOK (Bring Your Own Key), allowing you to…
Gnito is an open-source, self-hosted AI workspace that puts you in control of your data and AI provider choices. Built with React, TypeScript, Node.js and SQLite, Gnito doesn't come with an AI model of its own. Instead, it allows you to connect your favorite AI services or run local model endpoints via BYOK (Bring Your Own Key).
The platform supports multi-provider AI, enabling connections to OpenAI, Gemini, Anthropic, Groq, Ollama, LM Studio and more. It offers features like AI chat with streaming conversations, attachments, projects and chat history. Gnito also provides local memory storage on your machine, incognito mode for temporary, non-persistent conversations, a Docker terminal for AI-assisted commands, web search with configurable search providers, and automation center to schedule AI tasks using cron or one-time schedules.
Contributions, feedback and suggestions are welcome as Gnito is still actively developing. Some upcoming features like voice pipelines and MCP integration haven't been implemented yet. For installation, you need Node.js 20.19 or later. Clone the GitHub repository, run npm install, start the development server locally, and open http://localhost:5173. Docker is optional for most features, but it's required for the Terminal feature.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
