AIAny
AI Client2024
Icon for item

Onlook

Visually edit Next.js + Tailwind projects in the browser like Figma, with every change written straight back to your real React code. Pairs a DOM-level visual canvas with AI chat that scaffolds and edits components, plus branching and one-click deploy.

Introduction

Most visual "AI website builders" make you choose: design fast inside a closed canvas, or own real code you can keep editing. Onlook refuses the trade-off — its canvas manipulates the actual Next.js + Tailwind source, so dragging an element in the browser rewrites the component that renders it, and editing the code updates the canvas. Design and codebase stop being two artifacts to keep in sync and become the same thing seen two ways.

What Sets It Apart
  • The editing surface is the live DOM of your real app, not a mockup — selections map to React components, and style tweaks land as Tailwind classes in the source.
  • AI chat sits inside that loop: it scaffolds a Next.js app from a prompt, image, or template and edits components in place, while you correct it visually instead of re-prompting.
  • Branching lets you fork a design direction the way you'd fork code, so experiments don't overwrite the main layout.
  • It markets itself as an open-source alternative to Bolt.new, Lovable, v0, and Figma Make, but unlike them you walk away with an exportable, framework-standard codebase.
Who It's For

Great fit if you're a designer comfortable with web concepts, or a developer who wants design-speed iteration on a real React app you'll keep shipping. Look elsewhere if you need a pure no-code tool, work outside the Next.js + Tailwind stack, or want production-grade stability — it moves fast and is still in active early development.

Information

  • Websitegithub.com
  • OrganizationsOnlook
  • Authorsonlook-dev
  • Published date2024/06/25

More Items

GitHub
AI Agent2026

Runs persistent, self-hosted AI teammates that retain conversation, memory, routines and a sandboxed browser/shell. Supports bring-your-own models, local or remote sandbox providers, voice, team computers and integrations for auditable, controllable agent workflows.

GitHub
AI Client2024

Unifies visual creator tools, reusable Skills, and a Codex-powered Agent to handle video translation, image/video generation, voiceovers, and editing in one local multimodal workspace. Desktop and web clients share a synchronized state machine and keep data local by default.

GitHub
AI Client2025

Private, local-first desktop assistant for voice and text conversations that runs models on your hardware. Uses local model servers (Ollama or OpenAI-compatible endpoints), offers personal memory, dictation, TTS/STT, MCP integrations and automatic redaction; free for personal use.