Xpell 2 is an AI-native runtime that lets you modify applications in real time without rebuild loops, refresh loops, or wasted generation cycles.
Runtime Mutation becomes the workflow, not the pitch: prompt the running app, preview the mutation, and keep moving without throwing away state.
Traditional AI: Prompt → Generate → Build → Refresh
Xpell: Prompt → Live Runtime Mutation
Clear, honest status for the current launch build.
Traditional software often requires development, review, staging, QA, and deployment just to see simple UI changes.
As a developer, CTO, and engineering manager, I kept seeing small interface changes turn into expensive delivery cycles.
Days or weeks of work just to see a button move, a form change, or a panel appear.
Xpell started from a simple question:
What if applications could be edited as easily as WordPress pages?
The original idea was "WordPress for applications": live, editable software that can change while it runs.
AI transformed that idea into Xpell 2 - an AI-native runtime for evolving applications in real time.
Open Xpell Vibe Studio, modify a running application, persist the change, refresh the page, and apply a new mutation using AI.
Runtime Mutation works because Xpell 2 can accept targeted changes instead of regenerating the whole app.
Xpell Vibe Studio is the runtime editor for Xpell 2. Type a prompt, preview the result, and apply the mutation while the app keeps running.
Add email field to usersTry this in the starter app -> xpell-vibe-starter
Use the running system as the editing surface instead of regenerating a full source-code project.
The old loop makes you wait for generated code, builds, and refreshes. Xpell turns prompts into runtime changes.
The app usually has to be regenerated, rebuilt, and reloaded before you can judge the change.
The running app receives a targeted mutation, so state can stay intact while the UI evolves.
Xpell treats applications as runtime artifacts the app is already interpreting.
The screens and UI surfaces users see.
The steps and interactions inside the app.
The structured objects the application works with.
The capabilities connected to the runtime.
Instead of regenerating full source-code projects, Xpell updates the runtime artifacts the application is already interpreting. AI helps request the mutation; the runtime interprets and applies it.
Start from the runtime starter, boot the local app, then modify it while it runs.
git clone https://github.com/xpell-ai/xpell-vibe-starter
pnpm install
pnpm devOpen Xpell Vibe Studio (CTRL+E / CMD+E / WIN+E), describe a change, and watch the running app update without leaving its current state.
Starter repo: xpell-ai/xpell-vibe-starter
Recorded walkthroughs for the runtime workflow, focused on live edits inside the running app.
Watch a running application evolve through runtime mutations without rebuilds or refresh loops.
Prompt -> runtime -> persist. Generate the change, preview it in the running app, then save the accepted result into the project.
Move from the quick starter into the step-by-step Xpell 2 Developer Preview flow.
/getting-started/
Inspect focused runtime examples after the starter is running locally.
/examples/
Use the starter repo and package sources as the primary code entry point.
github.com/xpell-ai
Watch the published runtime-editing walkthroughs when they are available.
#videos