Free · runs in your browser

The AI that codes in your browser.

Open Frame writes it, runs it, and ships it — a coding AI with persistent memory that builds real apps live in a browser tab. No setup, no login.

$0 to useNo loginWrites + runs codeRuns in your browserShip to GitHub · Railway
Overview

What Open Frame is

Open Frame is a free-to-use AI that writes and runs code: a chat that remembers you, and a coding agent that builds working apps in the browser and ships them to your own GitHub and Railway. It comes with persistent memory, an agentic build loop, and real tools for reading and writing your project.

There’s no account and no paywall. Identity is an anonymous device_id in your browser. The bill is meant to be paid by a crypto token’s buy/sell tax, so people pay nothing — which makes the two design rules non-negotiable: keep it simple, keep it cheap. The agent runs in a WebContainer (Node in your own browser), so heavy compute stays $0.

Architecture

How it works

Three moving parts — chat, memory, and the agent — over one anonymous identity. The server never touches a filesystem.

1

Chat

A stable prompt prefix keeps Open Frame’s cache warm, streaming the first token in about 1.4s. Every call sends data_collection: deny — your chats are never used for training.

browser→/api/chat→rate-limit→memory + knowledge + history→Open Frame (stream)→save + re-summarize
2

Memory

One plain-text rolling summary per device — no vectors, no RAG. It’s rewritten by the cheap model every 10 turns, plus a “knowledge” block of custom instructions injected into every call.

3

The agent

Open Frame streams its thinking and calls tools; the browser runs each one in a WebContainer, feeds the result back, and loops (up to 12 steps, then resumable). You get a live preview iframe and a one-click .zip.

/api/agent→tool call→WebContainer exec→result back→loop→live preview
4

Ship it

Push the build to your own GitHub via the OAuth device flow (token stays in your browser, never on our servers), then deploy to your own Railway — in-app with a token, or by deep-link. Your account, your bill.

Capabilities

What you can do

Streaming chat

Talk to Open Frame with persistent memory across sessions. ~1.4s to first token.

Coding agent

Writes files, runs a dev server, fixes its own errors, hands back a live preview — all in your browser.

Templates

Start from a landing page, REST API, Telegram bot, scraper, React app, or “explain a repo”.

Ship to GitHub

One click or a chat command creates a repo on your account and pushes the build in one commit.

Deploy on Railway

Deploy to your own Railway account in-app, with an env-var editor. Deep-link path too.

Share a build

Publish any build to a public read-only link — a showcase page with the code and a “build your own” CTA.

Edit & re-run

Tweak any file in the Code tab and save — it writes to the WebContainer and reloads the preview.

Knowledge & memory

Set custom instructions once; Open Frame always sees them. Memory keeps the thread across sessions.

Image & video

Generation is built in and gated behind a key — flips on when the treasury is ready.

Soon
Under the hood

The stack

Deliberately small. Every piece was chosen to stay simple and cheap.

AppNext.js (App Router)
ModelOpen Frame · chat + deep
Agent runtimeWebContainer (in-browser)
DatabaseSupabase (Postgres)
HostingVercel
Identityanonymous device_id
DownloadJSZip
Reference

API routes

Thin server routes — mostly proxies and persistence. The heavy lifting happens client-side.

RouteMethodPurpose
/api/chatPOSTStreaming chat (deep:true = V4-Pro)
/api/agentPOSTOne agent step, streams NDJSON (deltas + tool calls)
/api/projectsGET · POSTSave / list / load agent project file trees
/api/shareGET · POSTPublish a build; public read of a shared project
/api/githubPOSTGitHub device-flow proxy (no secret stored)
/api/railwayPOSTRailway GraphQL proxy (token pass-through)
/api/memoryGETRead the rolling summary
/api/knowledgeGET · POSTUser custom instructions
/api/mediaPOST · GETImage / video via Fal (off until keyed)
/api/usageGETOperator cost summary
/api/healthGETConfig + which keys are wired
The business model

Free, on purpose

Cost control isn’t a feature here — it is the business. Compute lives on the user’s machine; Open Frame is cheap to run; caps bound the rest.

$0.00004
cost of one chat
$0
server compute — the agent runs in your browser
12
agent steps per run, then resumable
What’s next

Roadmap

Shipped is live today. Next is queued. Later is architecture-level and weighed against “keep it cheap.”

Shipped

  • Streaming chat + memory
  • Coding agent + live preview
  • Templates
  • Ship to GitHub
  • Deploy on Railway + env vars
  • Share a build
  • In-preview file editing

Next

  • Fork / remix a shared build
  • Static-host deploy (Vercel / Netlify)
  • Agent memory of past builds
  • Streaming diff view
  • Image & video generation on
  • Lock the brand

Later

  • Cloud terminal (token-funded)
  • The agent’s own browser
  • Accounts & cross-device sync