Skip to content

For people running serious AI workloads

Stop babysitting your AI tabs.

You pay $200+ a month so the best models on earth work for you. Then a run finishes — or stalls on a question — and sits there, unseen, while you grind through something else. AI Tab Switch is a radar for every AI tab you have open. The second one needs you, you know.

7-day free trial · Local-first · No API keys · Never spends your tokens

The most expensive minute in your day is the one where the model is done — and you don’t know it.

The silent stall

Claude Code has been waiting on one permission click for 20 minutes. It isn’t working. It isn’t failing. It’s waiting for you — and nothing on your screen says so.

The tab patrol

Five sessions across three providers, so you alt-tab through all five to find the one that moved. Attention researchers put the cost of refocusing after an interruption at roughly 23 minutes. You run that loop a dozen times a day.

The expiring window

Max-tier quota windows reset on the clock, used or not. Every hour a finished session sits unnoticed is capacity you paid for and never harvested.

The community has a word for this: babysitting. You solved the model bottleneck with money. What’s left is the handoff — the gap between “it needs you” and “you noticed.” That gap is the product.

29
AI surfaces watched — chat, code, and image tools
12
states detected — from the page itself, plus an optional LLM triage
0
bytes sent anywhere by default. The only exception is the opt-in LLM triage — and you hold its key.

Know the second any tab needs you

One row per tab. Red while it generates, green the moment it lands, amber when it's your move. Read from the page itself — no API keys, no polling some vendor status endpoint, no lag.

generatingfinishedasked a questionneeds permissionundone workwork on your siderate limitlogged outmodel unavailableerrornewidle

Interrupt-aware, not just done-aware

“Finished” is the easy case. The radar also catches the states that silently eat your day: a trailing “want me to continue?”, a permission card, a rate limit, a logout, a model that went down mid-run, an error banner.

Understands agent surfaces

Claude Code keeps its spinner running while it waits on a question card — most eyes read that as “still working.” The radar reads the card, flags it asked a question, and stops you from losing 20 minutes to a spinner.

Knows thinking from stalling

ChatGPT’s long “Pro thinking” phases hide the stop button and stream nothing. Cheap detectors call that finished. This one doesn’t.

Notifications on your terms

Desktop notifications for Finished, Blocked (questions, errors, limits, permissions), or both. Optional chime. A ready-delay filter kills sub-second false finishes so you’re never pinged into a blip.

Batch mode for deep work

Running six agents? Tell the radar to stay quiet until, say, three of them are done — blocked states still break through immediately. One interruption instead of six.

The badge is the count

The toolbar badge shows how many sessions are ready right now. Zero means keep working. That’s the whole glance.

Keep runs moving while you're somewhere else

Noticing faster is half the win. The other half: not being needed at all.

Auto-continue paused Claude runs

Long Claude turns pause behind a “Continue” button when they run out of tool calls. The radar clicks it for you — with a cooldown and a safety valve — and the run keeps going. Turn it off, and the tab honestly shows needs permission instead of pretending to be done.

Queue prompts against a busy tab

Draft the next three follow-ups while the model is still generating. They fire automatically, in order, the moment the tab reaches finished. Your thinking doesn’t wait for its typing.

Broadcast one prompt to many tabs

Select five sessions, write once, send everywhere. Compare Claude’s answer against ChatGPT’s and Gemini’s without pasting three times.

Screenshots ride along

Paste or drop up to four images into a staged prompt. They’re delivered with it, into the target tab’s own composer.

Steer mid-generation

On ChatGPT, steer mode injects while the model is still generating when the composer allows it. Everywhere else, prompts queue safely instead.

Reorder on the fly

Queued prompts are a drag-and-drop list per tab. Priorities changed? Reorder or delete before they fire.

Jump back without the reload cost

The real price of checking a tab isn't the click — it's rebuilding the mental state you dropped. So the radar carries it for you.

One key to the next ready session

Ctrl/Cmd+Shift+. jumps straight to the next tab that finished. No hunting through window strips. Ctrl/Cmd+Shift+→ cycles sessions; Ctrl/Cmd+Shift+K opens a command palette over everything.

Context overlay on landing

The moment you land on a session, a brief overlay shows its workspace, your last prompt, and your notes. Your brain reloads in two seconds instead of twenty.

Radar where you want it

Popup for a glance, side panel (Chrome/Edge) or sidebar (Firefox) to keep it pinned next to your work, full-page dashboard when you’re running a fleet.

Seen is seen

Jump to a finished tab and it clears back to idle automatically. The ready count only ever means “things you haven’t looked at.”

Hold focus while generating

Don’t want to be pulled anywhere until something is actually ready? DND mode holds auto-jumps while models are still working. It never closes or moves a tab.

Pins and notes per session

Pin the run that matters most to the top. Leave yourself a note — “auth refactor, branch v2” — and it’s there on the card and in the overlay when you return.

One radar for your whole stack

High-volume usually means multi-provider: Claude for code, ChatGPT for reasoning, an image tool on the side. The radar treats them as one fleet.

29 surfaces, one list

ChatGPT · Claude · Gemini · AI Studio · Grok · Perplexity · Copilot · DeepSeek · Poe · Vibe · HuggingChat · Kimi · Qwen · You.com · Phind · Meta AI · Groq · OpenRouter · Pi · LMSYS · NotebookLM · Cursor · Blackbox · Z.ai · MiniMax · Duck.ai · Manus · Genspark · T3 Chat.

Workspace lanes, auto-detected

Sessions sort themselves into Build, Write, and Image lanes from what the page is doing — your coding agents never mix with your image runs.

Search and slice the fleet

Full-text search across titles and prompts, one-tap filters by state — show me everything waiting on me, everything rate-limited, everything still cooking.

Private sessions respected

Temporary and incognito chats are flagged as private, kept visually distinct, and left untinted unless you choose otherwise.

Mute what you don't run

Muted providers leave the radar and never notify. Their tabs stay open — the radar just stops caring so you can.

Rate-limit aware across vendors

Usage caps, quota resets, “come back later” banners — surfaced as their own state, so you can rotate work to the provider that still has headroom.

Private by architecture, not by promise

You're pasting proprietary code and unreleased plans into these tabs all day. The last thing you need is a middleman.

Everything stays in your browser

Statuses, previews, queues, notes, screenshots, settings — extension storage on your device. No telemetry, no analytics, no external servers. The Firefox listing declares data collection: none.

No API keys, no accounts

It reads the pages you already have open. Nothing to connect, nothing to leak, nothing that bills you twice for tokens you already pay for.

Optional cloud presets

Want your setup on two machines? An optional account syncs presets — just the settings payload, on infrastructure in Western Europe. Skip it entirely and lose nothing else.

Make it yours

Light, dark, or system theme. Recolor every state to match how your eyes triage. Export your whole configuration as JSON and import it anywhere.

Chrome, Edge, Firefox

One extension, both engines — Chromium and Firefox (Android included), with a Safari path via Apple’s converter. Same features, same files, same radar.

Open the hood anytime

No minified blob: the download is plain, readable code. Verify the privacy claims yourself — that’s the point of local-first.

Fair questions

Another subscription on top of $200/month?

A tenth of one. $20 a month — or $297 once, forever — to stop the subscriptions you already pay for from idling. Every plan starts with a 7-day free trial, there are no API keys, and it never spends your tokens. See pricing.

Will it slow my tabs down?

It’s a content script that reads the page about once a second and only speaks up when something changes. No network calls, no heavy frameworks injected into your tabs.

What happens to my prompts and previews?

They stay on your machine, in your browser’s extension storage. Read the privacy policy — it’s short because there’s so little to disclose.

Detection sounds fragile. What if a provider redesigns?

Detection is heuristic by design — it reads what’s on the page, with layered fallbacks per provider, and it’s updated fast when interfaces shift. When something ever reads wrong, the tab is one click away; you’ve lost nothing.

Your models are fast. Be the operator who keeps them busy.

Install takes about a minute. The next time a run finishes or stalls, you’ll know before the spinner does another lap.