Open-source ai app builders
Tools that turn a description into a working web app: some run on your own computer, some in a browser, and one generates a database and sign-in along with the interface. All of them let you keep the code.
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.
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.
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.
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.
An AGPL-3.0, self-hosted web platform that builds and runs AI-generated apps inside your own Kubernetes cluster, with per-project pods, persistent workspaces, HTTPS routes and multiple environments.
An MIT browser-based AI coding workspace with an editable chat agent, a Sandpack live preview, runtime diagnostics the agent reads to repair itself, and a Tauri option to package the project for desktop or mobile.
Questions people ask
What is the best open-source alternative to Lovable?
Dyad (Apache-2.0 core) if you want the prompt-to-app loop on your own computer with your own API keys. Onlook (Apache-2.0) if you want to edit the result visually in the browser. Chef (Apache-2.0) if you want a database and sign-in generated with the app. Llama Coder (MIT) for small single-prompt apps.
Can an open-source app builder generate a backend?
Chef does: its README says it builds full-stack apps with a built-in database, zero-configuration authentication, file uploads, real-time interfaces and background workflows, all on Convex. The others generate front-end code, with Onlook targeting Next.js and Tailwind.
Do these run on my own machine?
Dyad is a desktop app for Mac and Windows and runs locally with your own keys. Onlook and Chef can be self-hosted or used through their makers' hosted versions. Llama Coder is a Next.js app you run yourself with a Together AI key.
Which licence should I check first?
Dyad's: everything outside its src/pro directory is Apache-2.0, while src/pro is under the Functional Source License, which forbids competing commercial use until each version turns Apache-2.0 two years after release. Onlook, Chef and Llama Coder are Apache-2.0 or MIT throughout.
Paying for an AI tool you would rather own?
Reveneau sets up the replacement on your own servers, connects it to your product, and builds the software around it.