What's new.

No more plans. Pay for what you use.

The Free, Maker, Studio and Scale plans are gone. Every account now has a balance: new accounts start with $15 of credit, and each AI task is charged by the tokens it actually used, at the model provider's list price. Apps running on our shared servers are charged once a day for the memory, traffic and disk they used. Builds and deploys themselves cost nothing. See the rates.

Every reply now shows what it cost underneath it, and My Profile → Balance shows four numbers on the web and in both phone apps: your balance, total top-ups, today's spend and this month's. On the web, the usage chart shows messages, tokens and spend day by day.

We changed it because a subscription is the wrong shape for building an app. The work comes in bursts: a heavy first few weeks, then small fixes. Nobody should have to pay a monthly fee to try something for a week, or worry about a charge on a month they didn't use it. Inviting a friend now adds $15 to your balance once they build or deploy for the first time, and chats on your own API key stay free and uncounted.

Talk it through with a voice assistant

In the iOS and Android apps, open a conversation and tap the assistant to talk instead of type. It asks one thing at a time, repeats back anything it didn't catch, turns what you said into a clear request and sends it to the AI. It can also start a build or a deploy for you, so you don't have to hunt for the button.

It knows where the project stands. If a new build is waiting, it asks whether you've tried it yet rather than telling you to install it again. While the AI is still working, it tells you what's being done and won't pile a new request on top. You can add a screenshot mid-call when something on screen looks wrong, and subtitles under the assistant show what each side said.

For now it speaks Mandarin only. Typing works exactly as before.

Conversations open instantly on your phone

Opening a long conversation on a phone used to mean waiting a few seconds. We measured where the time went: not the server and not the screen, but the download. The apps now keep a copy of each conversation on the device, show it immediately and quietly catch up with anything new. The first time you open a conversation they fetch just the latest 20 messages, and scrolling up loads the earlier ones while keeping your place.

Only messages the server has confirmed are kept on the phone, so the copy can never hold something the real conversation doesn't. Each account's copy is stored separately and deleted when you log out.

Redesigned phone apps, and a new mark

Both phone apps were redesigned screen by screen: login, the conversation list, My Profile, MyCloud, charts in Metrics, and Code History. Each conversation in the list now shows its platform and the last version that built successfully, and a small hammering robot marks the ones where the AI is at work.

MyCloud on the phone now shows each machine's CPU, memory and disk as bars, the same as on the web, which now shows disk too. And the app has a new icon: a hammer and a wrench forming an A.

Registering an iPhone for testing, fixed properly

Adding your iPhone or iPad as a test device installs a small profile that tells us its device ID. On real devices that last step never showed as complete, because a whole stage of the exchange was missing. It now finishes cleanly. The icon it leaves on your home screen is labeled ApzUdid and opens a page explaining what it is.

Devices are also named correctly now. An iPad no longer shows up as an iPhone, and the name registered with Apple now includes the device's model instead of a generic label.

Collaborators can do everything, not just watch

People you invite to a project can now attach files to their messages, start and stop Preview, build the iOS and Android apps, and deploy, the same as you. Before, the buttons were there but quietly refused them.

A few things still belong to the owner: deleting the project, inviting people, and connecting or pushing to GitHub.

The console has a new address

The console now lives at vibe.appzentic.com, on its own production machine, separate from the one we develop on. Old links to console.appzentic.com still work: they redirect you, and anything in the link comes along. Nothing changes in your projects or your login.

Point one project at another with #

Type # in a message and pick another of your conversations. The AI can then read that project's documents, code and chat history while it works on this one. Use it to share background knowledge, keep an app and its API in step, or rebuild something in a different technology.

The reference is read-only and one-way: nothing in the other project can be changed from here. Until you send the message, you can remove it with its ×. Renaming a conversation now also sticks every time; before, it silently failed on about half of them.

Your own Apple account: TestFlight uploads and your own app IDs

If you've connected your own Apple Developer account, an iOS build can now go straight to TestFlight: no separate upload tool needed. Each build gets a higher build number automatically, so Apple accepts the second upload as readily as the first.

You can also set your own bundle ID prefix, so new apps are named under your company (com.yourcompany.app) instead of ours. Set it separately for Android, or with your Apple account for iOS. Both live in My Profile, next to your Apple account (in the phone apps, in their own App Signing section).

Use a domain whose DNS lives somewhere else

Your domain doesn't have to be in the same cloud account as your server. If it's managed at Cloudflare, GoDaddy or your registrar, tell the console the name. It sets your apps up under it and shows the DNS record to add, and a one-line script on your server gets the HTTPS certificate. The console then tracks when that certificate expires.

Your keys are encrypted at rest

The secrets you trust us with are now stored encrypted with AES-256: your own AI API keys, your cloud access keys, your App Store Connect key, and the SSH keys for the servers we open for you. Reading the files on our disk, or on a backup of it, no longer gives anyone a usable key.

The screen still shows only the first and last few characters of each key, and your own keys keep working exactly as before.

One app, more than one server

An app used to be pinned to a single machine — wherever it first deployed was where it stayed. The console now keeps a record of every server an app is running on, so the same app can live on our shared infrastructure and on your own machine at the same time, and the deploy screen asks which one you mean.

The old rule existed to stop an app being split across two places. It turned out the danger was never the second machine — it was only remembering one of them.

Your own domain, with a real certificate

Point a domain you own at your server and we issue the HTTPS certificate for it — a real Let’s Encrypt certificate, so browsers show the padlock instead of a warning. Renewal happens on its own, and the certificate and key are downloadable from the same card if you want a copy.

Changing your mind is safe: switching to a new domain no longer breaks the apps still answering on the old one, since each domain keeps its own certificate until nothing references it any more. And if you don’t have a domain yet, the server still works — your apps are reachable over plain HTTP at its IP address until you add one.

MyCloud: launch a server in your own cloud account

Open My Profile → MyCloud, save your AWS or Alibaba Cloud credentials, choose a region (North America, Europe or Asia-Pacific) and a size, and we open the machine, install everything it needs and connect it — nine steps you can watch happen.

The machine is created in your cloud account and billed to you from the moment it starts. The SSH private key is yours to download. Terminating it is one button in the same place. One machine per account for now, and its health — CPU, memory, disk, and how many apps it’s serving — shows on the card next to the hostname you see in your own cloud console.

This is the part of “AI Builds, Your Own” that used to be a promise. Your app can now run somewhere we have no say over.

See your live data, not just the test database

Once your app moved to a deploy server, the Database view was still showing the console’s local test database — the data your real users were creating was invisible. There is now a Preview / Production switch in the database view, on the web and in both mobile apps.

Production queries travel over a pinned, encrypted connection and run as a read-only account created just for that app, so looking at live data cannot change it.

Or bring a server you already have

Already have a VPS, a box at a small hosting provider, or a machine in your own rack? Then we don’t need your cloud credentials at all. The console gives you a one-line install command; you run it on your machine and it introduces itself.

The connection is outbound-only — your machine polls us, we never dial into it. There is no SSH access to hand over, no inbound port to open, and no credential of yours sitting on our side.

Room for more test devices

Apple allows 100 registered test devices per developer account per year. Appzentic can now hold several developer accounts and remembers which one each device was registered under, so that ceiling no longer stops you handing your app to the next tester.

The free plan got twice as big

Every limit on the free plan doubled: 20 AI messages a day, 12 builds, 12 deploys, 6 apps, and 6 new apps a day.

The 30-day trial bundle doubled with it — 60 messages, 36 builds and 36 deploys — because raising the daily allowance without raising the lifetime one would only have moved the wall closer.

Read your code on your phone

The Code Browser is now in the iOS and Android apps: the whole file tree, files with syntax highlighting, and Markdown that renders instead of showing its own punctuation.

Same reason it exists on the web. Being able to look at what was written for you is the difference between owning it and renting it.

Preview, metrics and your database, on mobile

Three more panels reached the phone apps. Preview opens your running app in the phone’s browser, with a card that shuts the test server down when you’re finished. Metrics is reachable straight from the chat list. Database lets you ask in plain language — “how many orders yesterday?” — then shows you the query it wrote before running it.

Typing raw SQL on a phone keyboard is not something anyone asked for, so on mobile the query itself is there to read, not to write.

Build and deploy from your phone

You can now start a build and a deploy from the mobile apps and watch both run as live messages in the chat, instead of waiting on a silent screen for a result. Tapping a build or deploy message opens the full log.

Chasing this turned up an older bug: anyone watching a teammate’s deploy saw “pending” for the entire run, because only the final state was ever recorded. Collaborators now see it move.

Collaborate from your phone

Invite people, see who is in a project, and @-mention a teammate or the AI — all from iOS and Android.

Until now mobile could send messages into a shared project but never received them: the app only listened while an AI task was running, so anything a teammate said while you weren’t building simply never arrived. Collaboration on a phone was write-only. Now it listens.

Install a build on the phone in your hand

Build results in the mobile apps now lead with Install on this iPhone / Install APK, with the QR code tucked into “install on another device” — a QR code on your screen cannot install anything onto that same screen.

iOS also gained a My UDID row in the profile, so the phone you are holding can register itself for testing. Where we can’t tell whether this particular phone is the one already registered, it says so plainly rather than guessing — one tap fixes it for good.

Your account, notifications and feedback on mobile

Tap your avatar in the mobile apps and you get what the web has: today’s usage, your plan, your referral code and credits, your avatar, chat text size, and the privacy and terms links.

Notifications and the feedback thread came with it, screenshots included, plus a local app log you can switch on when something misbehaves — so a bug report can carry evidence instead of a description.

Your first sentence survives the trip

Type an idea into the box on this site and it now travels with you: after you sign up or log in, the console has it waiting in the new-project box.

It is filled in, not sent. You get to read it once more before anything happens.

Use your Claude subscription instead of an API key

If you already pay for Claude, you can now connect that subscription directly rather than buying API credits separately. Add it in My Profile → Build. As with any key you bring yourself, those messages don't count against your daily allowance.

Kimi joins the model lineup

Kimi is now selectable in the chat, bringing the list to six: Claude, GPT, Gemini, DeepSeek, GLM and Kimi. You can switch between them mid-project without losing your work — the new model picks up the conversation and the code where the last one left off.

Interrupted tasks now pick themselves back up

When we restart the console for a deployment, any task running at that moment used to leave the page sitting with a blinking cursor forever. Now the interruption is detected and the task is re-run automatically, once, with a clear message explaining what happened.

We also stopped charging your quota for that re-run. It was our restart, not your request.

Live streaming, without opening a cloud account

Apps can now publish and play a live video stream using shared streaming infrastructure that's already running. Ask for it and the AI wires it up.

A deliberate limit worth stating plainly: this is sized for demos and a handful of viewers. Live video is bandwidth-hungry, and if your stream finds a real audience you'll need to move to a dedicated provider. The point is that you can prove the idea works before spending a cent on that.

Your Android signing key and GitHub key are now downloadable

We generate an Android upload key for every app that needs one, because creating it by hand involves command-line tooling most people never touch. Until now there was nowhere to actually get it.

My Profile now has Android and GitHub tabs. The Android tab gives you the keystore as a zip including its passwords — you need both halves if you ever publish outside Appzentic. Keep it somewhere safe: an upload key can't be replaced on an existing Play listing.

GLM added, and Codex is now called GPT

GLM is available as a coding model. Separately, we renamed Codex to GPT in the interface — more people recognise the name, and nothing changed underneath.

Password reset

Forgetting your password used to be a dead end. There's now a reset link on the login page.

Apps can send email

Verification codes, notifications, scheduled reports — your app can now send email through shared infrastructure, with no provider account or domain setup on your side.

Tighter isolation for scheduled jobs and stored credentials

Scheduled jobs now run inside the same locked-down sandbox as everything else rather than directly on the host. The code browser also no longer displays real credential files — you see example configs instead, so secrets can't leak through a shared screen or an exported project.

Usage credits, and email verification at signup

Invite someone and you both earn usage credits, which are spent before your plan's own quota. Signup now confirms your email with a code first — which is also what makes password reset possible.

Voice and video calling

Apps that need real-time calls now get the relay infrastructure that makes them actually connect. Without it, calls fail for a large share of users on home and mobile networks — it's the unglamorous piece that decides whether a call app works at all.

See how your app is actually doing

A metrics panel now shows what's happening with a deployed app — traffic, response codes, memory and disk. Mobile apps can opt in to usage analytics covering opens, active users by platform, and next-day return rate. For web apps, there's a performance check that scores real page-load quality.

Analytics is off unless you turn it on. Your app, your call.

Notifications and a feedback channel

Announcements now arrive in My Profile → Notifications, with anything urgent shown directly. You can also report problems from your profile and attach a screenshot — we reply on the same thread, so you're not hunting through email for an answer.

Every app runs in its own sandbox

Apps built on the platform run isolated from each other, with their own memory and CPU ceilings. One app misbehaving can't reach another app's files or drag down the platform for everyone else.

React and Vue for web apps

Web apps were limited to plain HTML, CSS and JavaScript, which capped how much you could build. React and Vue are now supported, so more ambitious interfaces are possible — and the resulting code is standard enough that any web developer can pick it up later.

More backend languages, and a third database

• Backends can now be built in Go or Java (Spring Boot), alongside Python — the AI picks what suits your app, or uses whatever you ask for
• Redis is available for caching, sessions and counters, joining MySQL and MongoDB
• MySQL and MongoDB were upgraded to current versions, unlocking modern query features

Build together in one conversation

You can now invite someone into a project — a colleague, your boss, a client. Everyone sees the same chat, code and build results as they happen, and can talk to the AI directly.

Actions with consequences stay with you: only the owner can build, deploy, connect databases, export code or delete the project. Use @ to direct a message at a specific model, or at a person when you want to talk among yourselves without the AI joining in.

Export your code, or push it straight to GitHub

Download the complete source as a zip, or connect a GitHub account and sync your project to a repository you own. Projects also get a README and CHANGELOG generated automatically, so the repo looks presentable instead of like machine output.

Credentials are stripped from exports. You get your code, not our secrets.

iOS testing moved to direct install

iOS test builds now install directly on devices you've registered, via a QR code, instead of going through TestFlight.

The reason: TestFlight makes every build wait for Apple's review and requires you to have already created the app record in App Store Connect. For someone trying to see their idea running on their own phone, that's a discouraging first experience. Direct install is ready in minutes. If you'd rather sign under your own Apple developer account, you can now add your credentials and builds will use your team instead of ours.

Building and fixing without leaving the chat

Builds used to happen in a separate panel you had to go watch. Now the whole cycle runs in the conversation: you ask, the build starts, progress appears as a message, and the result comes back with install links.

If a build fails, the log is read and classified automatically and the problem is handed back to the AI as if you'd reported it yourself — so in many cases the fix and the rebuild happen before you've finished reading what went wrong.

Install an iOS build by scanning a QR code

Getting a test build onto an iPhone was the roughest edge on the platform. Apple requires every device to be registered before it can run an app from outside the App Store, and collecting that device ID normally means plugging into a Mac.

Now you scan a QR code, tap once, and your device registers itself. From then on every iOS build produces a code you scan to install — no cable, no Mac, no store.

Apps that run on a schedule

Not everything needs a screen. You can now build something that just runs — scrape a page every morning, total yesterday's orders, email a weekly summary — with no interface at all. Describe the job and when it should happen.

Shared storage and CDN — the start of "no cloud account required"

Apps could now store uploaded files and serve them fast worldwide, using infrastructure already provisioned and waiting. This was the first piece of what became the platform's shared services: the answer to "I want to build this, but first I have to go open three cloud accounts."

Everything that followed — databases, email, calling, live streaming — is the same idea extended.

Real databases for your app, and a way to look inside them

Apps got their own dedicated database — created, credentialed and wired up automatically when the AI decides your app needs one. MySQL and MongoDB to begin with.

A browser landed alongside it, so you could actually see what your app had stored. Being able to look at your own data turns out to matter enormously for trusting that the thing works.

The first real mobile builds

The moment the whole thing was pointed at. Android and iOS build pipelines came together within a day of each other, and for the first time a conversation produced an actual installable app — signed, packaged, and ready to put on a phone.

Everything before this was a chat interface that wrote code. This is where it became a way to make apps.

One-click deploy, with versions that track themselves

Publishing your backend and web app became a single action instead of a sequence of server steps. Every deploy and build bumps a version number automatically, so you can always tell which build is on your phone and which one is live.

Console v2 — conversations became projects

The biggest structural change in the platform's life. Until now a chat was just a chat. From here, the moment the AI writes code, the conversation becomes a project: it has a name, a file tree you can browse, a build history and a deployment target.

A code browser arrived with it, so you could read everything the AI had written — not because you need to, but because being able to look is the difference between owning something and renting it.

"AI Builds. You Own."

The line that ended up defining the product showed up on the login screen. It has since become AI Builds, Your Own. — but the commitment behind it hasn't moved: whatever gets made here belongs to the person who asked for it.

Start on your laptop, keep going on your phone

If the AI was mid-answer and you switched devices, the second device used to show nothing at all. Now the work in progress follows you — open the same project anywhere and you see the response still arriving, live, rather than a blank screen and a guess about whether anything is happening.

Show, don't describe

File attachments and screenshot paste. Instead of explaining what looked wrong, you could paste a picture of it — which remains the single fastest way to get a precise fix out of the AI.

iOS and Android apps for the console itself

Two days after the first working version, the console got native mobile apps — so you could start an app from a phone, on a sofa, without a laptop anywhere nearby.

They were built the same way everything here is built, which made them the first honest test of whether the idea held up.

Day one

The first working version: a chat window, three AI models wired up and answering, accounts, and a workspace per person that nobody else could reach.

No builds, no deploys, no databases. Just the bet that describing what you want should be enough — and a lot of unglamorous work getting three different command-line tools to stream their output into the same box.