The open-source alternatives to v0 are Onlook, Dyad, Chef and Llama Coder. Onlook is the closest for design work: a visual-first editor that builds Next.js and Tailwind interfaces with AI and lets you drag, click and edit on the live page while the code stays in sync. Dyad runs the same prompt-to-app loop on your own computer. Chef generates a backend with the interface, and Llama Coder produces small apps from one prompt. A designer switches to keep the code and the model choice.
4 of 4 carry an OSI licence. 4 of 4 run on your own machines. Figures read from GitHub on September 17, 2026.
One project per need, with the reason from its own README and the one thing to know before you choose it.
Apache-2.0 visual-first editor for Next.js and Tailwind, with a Figma-like interface, layers, branching and checkpoints, synced to real code.
Know firstNext.js and Tailwind only for now, and running it yourself needs Bun, Docker, Supabase and OpenRouter.
A desktop app for Mac and Windows whose README compares it to Lovable, v0 and Bolt running locally, with no sign-up and your own API keys.
Know firstIts README does not name the models, framework or deployment targets, and there is no Linux build.
Apache-2.0, forked from bolt.diy, building full-stack apps with a database, authentication, file uploads and background jobs on Convex.
Know firstEvery app it builds runs on Convex, and self-hosting uses Convex's hosted control plane.
MIT, generating a small app from a single prompt with Llama 3.1 405B through Together AI and previewing it in a sandboxed frame.
Know firstSmall single apps with no backend or deployment, tied to Together AI for inference.
The facts that decide most choices. Each project's page carries the full panel.
| Project | Best for | Openness | Licence | Runs as | Own machines | Stars |
|---|---|---|---|---|---|---|
| Onlook | Editing the result visually | OSI | Apache-2.0 | Hosted app, Run locally (Bun, Docker, Supabase) | Yes | 26,756 |
| Dyad | On your own computer, with your own keys | OSI | See LICENSE | Desktop app | Yes | 21,576 |
| Chef | A database and sign-in generated too | OSI | Apache-2.0 | Hosted app, Run locally (pnpm, Convex) | Yes | 4,610 |
| Llama Coder | Small apps from one prompt | OSI | MIT | Web app (Next.js) | Yes | 7,131 |
Licence and star figures read from GitHub on September 17, 2026. Stars are shown as a dated fact and were not used to rank this page.
An Apache-2.0 visual-first code editor for building Next.js and Tailwind sites and prototypes with AI, editing the page directly in the browser with a Figma-like interface while the code stays in sync.
Apache-2.0 visual-first editor for Next.js and Tailwind, with a Figma-like interface, layers, branching and checkpoints, synced to real code.
Know firstNext.js and Tailwind only for now, and running it yourself needs Bun, Docker, Supabase and OpenRouter.
A local, open-source AI app builder for Mac and Windows that its README compares to Lovable, v0 and Bolt running on your own machine, with your own API keys and no sign-up, under Apache-2.0 apart from a fair-source pro directory.
A desktop app for Mac and Windows whose README compares it to Lovable, v0 and Bolt running locally, with no sign-up and your own API keys.
Know firstIts README does not name the models, framework or deployment targets, and there is no Linux build.
Convex's Apache-2.0 AI app builder, a fork of bolt.diy, that builds full-stack web apps with a built-in database, authentication, file uploads, real-time interfaces and background jobs on the Convex backend.
Apache-2.0, forked from bolt.diy, building full-stack apps with a database, authentication, file uploads and background jobs on Convex.
Know firstEvery app it builds runs on Convex, and self-hosting uses Convex's hosted control plane.
An MIT open-source take on Claude Artifacts that generates small apps from one prompt with Llama 3.1 405B on Together AI and previews them in a sandboxed in-browser renderer.
MIT, generating a small app from a single prompt with Llama 3.1 405B through Together AI and previewing it in a sandboxed frame.
Know firstSmall single apps with no backend or deployment, tied to Together AI for inference.
The questions that settle it, in the order they usually come up.
Onlook for visual editing on the rendered page; the rest start from a prompt and give you code.
Onlook is Next.js and Tailwind only. Chef builds full-stack apps on Convex. Dyad's README does not say.
Dyad and Llama Coder run locally; Onlook and Chef offer hosted versions as well as self-hosting.
v0, in the vendor's own words, is "your collaborative AI assistant to design, iterate, and scale full-stack applications for the web", by Vercel's own description. v0.app. The cases below are where that still wins.
Stars, licence, last commit and last release are read from the GitHub API by a script every week and carry the date they were read. Nobody types them.
What each project does is written from its own README and LICENSE, read in full on the date shown, and phrased as the project's claim. The sources are listed at the end.
That a project is faster, better or cheaper than v0. A price for anyone. A user count. A roadmap. If a fact is not on this page, it was not in the source.
Onlook, an Apache-2.0 visual-first code editor that builds Next.js and Tailwind apps with AI and lets you edit the rendered page directly, with the code in sync. Dyad is the local desktop option, Chef adds a generated backend, and Llama Coder handles small one-prompt apps.
In Onlook, yes: it edits the browser DOM directly with a Figma-like interface, layers, branching and checkpoints, and right-clicking an element opens its exact place in the code. The other three generate code you edit in an editor.
Onlook targets Next.js with Tailwind CSS and says support for other frameworks is not done yet. Llama Coder generates small apps previewed in the browser. Chef builds full-stack apps on Convex. Dyad's README does not name the framework it generates.
Dyad is a desktop app for Mac and Windows that runs the whole loop locally with your own keys. Llama Coder runs as a Next.js app on your machine. Onlook and Chef can be self-hosted, with services such as Supabase, Docker or Convex behind them.
Nothing for the software: Onlook, Chef and Dyad's core are Apache-2.0 and Llama Coder is MIT. You pay for model use through your own API key, or for the hosted versions Onlook and Chef offer, whose prices their READMEs do not state.
Running one of these inside your own environment, with your own data and your own security rules, is the kind of work Reveneau does. Read how a forward deployed engagement works.