Can Snapchat be vibe coded?
Camera-first messenger where snaps, stories and streaks disappear · the app is the friend graph
The mechanics one-shot fine: ephemeral photo messages, 24-hour stories and streak counters are CRUD plus a delete timer. None of that is the product. Snapchat is where your friends already are · the value of a disappearing photo is who is on the other end, and a self-hosted clone with two users is a group chat with extra steps. Add the AR lens stack built on years of face-tracking models, screenshot detection that needs OS-level app privileges, and media infrastructure moving billions of snaps a day, and the honest verdict is that the network is the app. The prompt below is the consolation build: a private snap relay for one friend group that opts in.
Jump to the build brief ↓Checked Aug 2026
What you pay today, before any DIY hosting
high editorial confidence
Buildability by layer
Screens, forms, and focused interactions
The repeatable job the product performs
Availability and legality of required data
Uptime, queues, support, and maintenance
Security, compliance, and user confidence
The achievable core
- Snap a photo with a caption overlay and send it to an invited friend group; each snap deletes after one timed view, with daily streaks and 24-hour group stories.
- Draft, queue, and track content for the few networks you actually use.
- A responsive interface with real empty, loading, success, and error states.
The parts a prompt cannot buy
- the people: everyone you snap with is on Snapchat, not on your server
- AR lenses and filters backed by years of face-tracking models
- screenshot detection · a web app cannot see or stop screenshots
- Snap Map, Discover, Spotlight and the creator ecosystem
- The value comes from the people already using it.
- Model quality and inference operations are part of the product.
Why people still pay
Almost nobody pays for Snapchat itself · the app is free and the subscription sells cosmetics and vanity telemetry: pin a #1 BFF, see who rewatched your story, wear a badge. People pay 3.99 USD because the network underneath is where their friends live, and status inside a graph only matters in a graph with people in it. That is also exactly why a rebuild is pointless: you can clone every feature and you will have cloned none of the value.
The value comes from the people already using it.
Model quality and inference operations are part of the product.
Reliability at the vendor's scale is an operations problem, not a prompt.
The brief
Context, requirements, acceptance criteria, non-goals, and the full production standard — as Markdown, ready for any coding agent.
Build brief — a focused alternative to Snapchat
Context
**Snapchat** — Camera-first messenger where snaps, stories and streaks disappear · the app is the friend graph. It currently costs $3.99/mo.
The mechanics one-shot fine: ephemeral photo messages, 24-hour stories and streak counters are CRUD plus a delete timer. None of that is the product. Snapchat is where your friends already are · the value of a disappearing photo is who is on the other end, and a self-hosted clone with two users is a group chat with extra steps. Add the AR lens stack built on years of face-tracking models, screenshot detection that needs OS-level app privileges, and media infrastructure moving billions of snaps a day, and the honest verdict is that the network is the app. The prompt below is the consolation build: a private snap relay for one friend group that opts in.
This brief describes a focused, single-operator replacement for the part of Snapchat that is genuinely reproducible. It is deliberately narrower than the product it replaces, and it says so in writing. Build the useful core; do not pretend to have rebuilt the rest.
What you are building
Snap a photo with a caption overlay and send it to an invited friend group; each snap deletes after one timed view, with daily streaks and 24-hour group stories.
Draft, queue, and track content for the few networks you actually use.
A responsive interface with real empty, loading, success, and error states.
Requirements
Functional
Friends willing to install the PWA and actually use it.
Data and integrations
A small VPS or free-tier Node host with HTTPS (camera and push APIs require it).
Each of these needs a real account, credential, or quota. Set them up before writing feature code.
Non-functional
Accessibility: semantic markup, labelled controls, visible focus, and reduced-motion support.
Security: server-side secrets, validated input, and no credentials in the client bundle.
Reliability: retries with backoff on external calls, and a clear failure state when a provider is down.
Portability: the operator can export their data and leave without losing it.
Implementation brief
Build me a private ephemeral photo-messaging app, snaps for one friend group that opts in. Requirements:
Node 22 + Fastify + better-sqlite3, and a vanilla-JS installable PWA served from
/public with no build step: manifest, service worker, an offline shell that caches
the UI but never caches snaps.
Core loop: open the camera with getUserMedia, capture a photo, type or draw a
caption overlay on a canvas, send it to one or more friends.
A snap is viewable exactly once for up to 10 seconds; the server deletes the image
file immediately after the view and keeps only a minimal sent/opened log row.
Accounts are invite-code only: the admin seeds codes with a CLI script, signup is
username plus passcode, sessions are httpOnly cookies.
Per-pair daily streaks tracked server-side, shown next to each friend.
Group stories: a snap posted to my story is visible to all members and hard-deleted
after 24 hours by a sweep job.
Media lives as files on disk outside the web root; metadata in SQLite with WAL mode.
Web push for new snaps behind a permission prompt; the app must work fully without
it, and the README says iOS web push is best-effort. VAPID keys and session secret
in .env, with a documented script that generates them and a .env.example.
HTTPS is required for camera and push: document local dev with a self-signed cert
and production behind Caddy on a cheap VPS.
Be honest in the UI: label view-once as deleted from our server, and state plainly
that screenshots cannot be detected on the web.
Tests for delete-after-view, the 24-hour story sweep, and streak day-boundary math
with a fake clock.
Out of scope: AR lenses and face filters, Snap Map, Discover or Spotlight feeds,
video calls, screenshot detection, analytics, and third-party auth.
README: setup, deploying, where data lives, how deletion actually works, and how
to invite the first two friends.
Delivery standard
Inspect the repository first, then write a short implementation plan before writing code.
Deliver the smallest complete end-to-end workflow first; every primary control must work against persisted data.
Use real validation and storage; never substitute fake dashboards, decorative controls, hard-coded success states, or mock integrations.
Include responsive layouts plus genuine empty, loading, success, validation, and failure states.
Keep secrets server-side in environment variables, provide .env.example, and never commit credentials or user data.
Add structured logs around every external call and return actionable errors without leaking sensitive details.
Write unit tests for the core logic and one automated test of the main user journey.
Finish with a README covering setup, architecture, data location, backups, tests, deployment, and known limitations.
Acceptance criteria
A clean install starts the app using only the README and .env.example.
The primary journey works from first visit through saved result, reload, edit, export, and deletion where applicable.
Invalid input, missing configuration, provider failure, and an empty database each have a usable state.
The interface works at 390px and 1440px, is keyboard navigable, and shows visible focus on every control.
Tests, type checking, linting, and a production build all pass with no ignored failures.
No part of the interface implies a live integration, security guarantee, or scale capability that was not actually built and verified.
Non-goals
Do not build these, and do not claim to have replaced them:
The people: everyone you snap with is on Snapchat, not on your server.
AR lenses and filters backed by years of face-tracking models.
Screenshot detection · a web app cannot see or stop screenshots.
Snap Map, Discover, Spotlight and the creator ecosystem.
The value comes from the people already using it.
Model quality and inference operations are part of the product.
What you still own after launch
Secure credentials, rotate secrets, and handle provider rate limits.
Run migrations, backups, restores, and dependency updates.
Test the critical journey after every model, API, or hosting change.
Monitor failures and fix the edge cases a first prompt will miss.
Risk
**Operational risk.** The code is achievable; dependable data, integrations, and ongoing operations are the real cost.
Editorial confidence in this assessment: high. No independent one-shot implementation is linked yet.
Prior art
Working open-source software you can read, fork, or borrow from before starting:
[Signal](https://github.com/signalapp/Signal-Android) — open-source messenger with disappearing messages and view-once media, minus the social layer
[Pixelfed](https://github.com/pixelfed/pixelfed) — federated photo sharing with ephemeral 24-hour stories
Generated by [Can It Be Vibe Coded?](https://www.canitbevibecoded.com) · Full report: https://www.canitbevibecoded.com/snapchat
You still own the product
- Secure credentials, rotate secrets, and handle provider rate limits.
- Run migrations, backups, restores, and dependency updates.
- Test the critical journey after every model, API, or hosting change.
- Monitor failures and fix the edge cases a first prompt will miss.
Open-source prior art
Before you start
Can Snapchat be vibe coded?
Not faithfully. The mechanics one-shot fine: ephemeral photo messages, 24-hour stories and streak counters are CRUD plus a delete timer. None of that is the product. Snapchat is where your friends already are · the value of a disappearing photo is who is on the other end, and a self-hosted clone with two users is a group chat with extra steps. Add the AR lens stack built on years of face-tracking models, screenshot detection that needs OS-level app privileges, and media infrastructure moving billions of snaps a day, and the honest verdict is that the network is the app. The prompt below is the consolation build: a private snap relay for one friend group that opts in.
What can an AI coding agent reproduce from Snapchat?
Snap a photo with a caption overlay and send it to an invited friend group; each snap deletes after one timed view, with daily streaks and 24-hour group stories. Draft, queue, and track content for the few networks you actually use. A responsive interface with real empty, loading, success, and error states.
What will a DIY Snapchat replacement still be missing?
the people: everyone you snap with is on Snapchat, not on your server; AR lenses and filters backed by years of face-tracking models; screenshot detection · a web app cannot see or stop screenshots; Snap Map, Discover, Spotlight and the creator ecosystem; The value comes from the people already using it.; Model quality and inference operations are part of the product.
What do I still own after building a Snapchat alternative?
Secure credentials, rotate secrets, and handle provider rate limits. Run migrations, backups, restores, and dependency updates. Test the critical journey after every model, API, or hosting change. Monitor failures and fix the edge cases a first prompt will miss.