Chef
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.
The open-source alternatives to Bolt are Chef, Dyad, Onlook and Llama Coder. Chef is the closest relation: Convex forked the stable branch of Bolt's open-source version and added a generated backend, so every app comes with a database, sign-in, file uploads and background jobs. Dyad runs the prompt-to-app loop on your own machine, Onlook adds visual editing for Next.js projects, and Llama Coder builds small apps from a single prompt on an open model.
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, 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.
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 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.
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 |
|---|---|---|---|---|---|---|
| Chef | A database and sign-in generated too | OSI | Apache-2.0 | Hosted app, Run locally (pnpm, Convex) | Yes | 4,610 |
| Dyad | On your own computer, with your own keys | OSI | See LICENSE | Desktop app | Yes | 21,576 |
| Onlook | Editing the result visually | OSI | Apache-2.0 | Hosted app, Run locally (Bun, Docker, Supabase) | Yes | 26,756 |
| 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.
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.
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.
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.
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.
Chef, which forked Bolt's open-source code and added a Convex backend.
Dyad is local on Mac and Windows; Chef and Onlook run in a browser, hosted or self-hosted.
Chef takes Anthropic, Google, OpenAI or xAI keys; Onlook routes through OpenRouter; Llama Coder uses Together AI.
Bolt, in the vendor's own words, is a tool to "build and scale high-performing websites & apps using your words", by StackBlitz's own description. bolt.new. 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 Bolt. A price for anyone. A user count. A roadmap. If a fact is not on this page, it was not in the source.
Chef, which its README says is a fork of the stable branch of bolt.diy, Bolt's open-source version, with full-stack generation on Convex added. Dyad is the local desktop option, Onlook the visual editor for Next.js, and Llama Coder the small-app generator.
bolt.diy is the open-source version of Bolt, and Chef's README says Chef is a fork of its stable branch. bolt.diy itself is not listed in this directory because its repository had no commit within the 90 days before it was checked, which is the activity bar this directory applies.
Chef. Its README describes full-stack web apps with a built-in database, zero-configuration authentication, file uploads, real-time interfaces and background workflows, all running on Convex, the reactive database Chef is built around and which is itself open source.
Yes. Chef takes Anthropic, Google, OpenAI or xAI keys, set in the environment or in its settings. Dyad asks you to bring your own API keys. Onlook routes models through OpenRouter. Llama Coder uses Llama 3.1 405B through Together AI.
The software is, under Apache-2.0 or MIT. Model use costs whatever your provider charges. Chef and Onlook also run hosted versions, with Chef's README mentioning a free tier; neither states prices in its README.
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.