Fogar
A new tab for Chrome

Ask your new tab.
Nothing leaves the room.

Fogar answers from a language model that runs inside your browser. No account, no key, no server. When you want a bigger brain, bring your own key and it uses that instead. Either way the choice is yours, and visible.

Free. Open source. One model download, 533 MB to 2.7 GB, sized to your machine and cached for good.

chrome://newtab
Fogar
Focus
Device Cloud
Ready · Qwen3 0.6B · WebGPU
network 0 requestsmodel cached on this devicekey none
The network ledger

Three modes. You can see exactly what each one sends.

Most "private AI" claims are a paragraph in a policy. This one is a table you can verify in the Network panel.

ModeWhat leaves your browserWhere it goesCost
On this device 0 requests once the model is cachedThe model file is fetched once from Hugging Face. Your questions never go anywhere. Nowhere Free
Cloud, your key Your prompt and your keySent only to the OpenAI-compatible endpoint you typed. OpenAI, OpenRouter, Groq, or Ollama on localhost. The address you chose Your provider's rates
Web grounding Your question, as a search queryOff until you tick “Search the web first”. Then DuckDuckGo’s instant answers and Wikipedia, with no key, or full web results with your own Brave Search or Tavily key. The model answers from what comes back, with citations. DuckDuckGo and Wikipedia, or the search API you chose Free

No analytics. No telemetry. Nothing to opt out of.

Your corner

A new tab you would keep even without the model.

Recipes

Prompt forms you can share

Draft and rewrite, reply to a message, summarize, explain simply. Make your own with a small form builder, then share it as a link. Recipes are data, never code.

Reminders

"Call the dentist tomorrow at 9"

Plain words in, a confirmed time out. Fires as a Chrome notification. One click adds it to Google Calendar, with no account connection needed.

Agenda

Today and tomorrow, from any calendar

Paste your calendar’s private iCal address. Google, Outlook, iCloud, anything. Recurring events included, no account connection.

Widgets

Pin the panels you want

Todos, links, notes, weather with no API key, a favorite recipe. Order them, hide them, or hit Focus and keep only the ask box.

Bookmarks

Search as you type

Start typing in the ask box and matching bookmarks appear underneath. Open one, or remove it.

Right-click

"Ask Fogar about …"

Select text on any page, right-click, and get an explanation in a new tab. The page comes along: its title, address, and the text around your selection, so the model answers from what you were reading.

Dig deeper

When the first answer is not enough

One menu on every answer: search the web and answer again with sources, let the model think longer, or ask your cloud model the same question. The better answer replaces the first one in the conversation.

Grounding

Facts, when you ask for them

A small local model is a good writer and a poor encyclopedia. Tick “Search the web first” for the questions where that matters: DuckDuckGo’s instant answers and Wikipedia with no key, or full web results with your own Brave Search or Tavily key. Sources are shown. Arithmetic is computed, not guessed.

Recipes

The prompt is a form. The form is a file.

A recipe declares its inputs and a template. Fogar draws the form, fills the template, and hands it to whichever model you are using. Because a recipe is plain JSON, you can paste one to a friend, post it on a blog, or open a share link and add it in one click. Copy the one below and paste it into Recipes → Import to see.

Rewriting is the thing a small local model does best, so the first built-in recipe is for exactly that.

{
  "name": "Draft & rewrite",
  "inputs": [
    { "key": "text",   "label": "Your text", "type": "textarea" },
    { "key": "tone",   "label": "Tone",   "type": "select",
      "options": ["Neutral", "Friendly", "Formal", "Direct"] },
    { "key": "length", "label": "Length", "type": "select",
      "options": ["Shorter", "About the same", "Longer"] }
  ],
  "template": "Rewrite the text below.\nTone: {{tone}}. Length: {{length}}.\n\n{{text}}"
}

✍️ Draft & rewrite

Your text or notes
cant make 3pm, thurs instead? sorry
Tone
Friendly
Length
Longer
Format
Chat message
Output · Qwen3 0.6B · on this deviceSorry, I can't make 3 pm today after all. Would Thursday work instead? Happy to fit around whatever time suits you.
How it works

One download. Then it is just a file on your disk.

Pick how it answers

On this device, cloud with your own key, or just a search box for now. You can change your mind any time.

Fetch the model once

Qwen3.5, quantized, from Hugging Face, in the size your machine can carry: 0.8B, 2B, or 4B. It lands in your browser's private file storage and never downloads again.

533 MB · 1.3 GB · 2.7 GB

Open a new tab

The model wakes from disk, runs on your GPU through WebGPU or on your CPU across all its cores, and starts answering. Follow-ups keep the thread.

warm start 1.3 to 3.2 s · 44 to 92 tok/s · Apple silicon, WebGPU
Straight talk

Free, and here is how it pays for itself.

  • Fogar is free and stays free. No tiers, no trial, no lifetime deal.
  • The footer of the new tab rotates links to the other things its author builds. That is the business model.
  • If enough people use it, one small sponsor line may appear there. It will say "Sponsored". It will never be an ad network.
  • The code is open, so you can read exactly what the page does.

Built by Dylan Roy, who also makes UseSQL, TickerPal, and Kumkuat.

Questions

Fair questions, short answers.

Does it work offline?

Yes, in local mode, once the model is cached. Turn off Wi-Fi and it keeps answering. Web grounding and cloud mode need a connection, by definition.

How good is a small model, honestly?

Depends on the size. In our tests the 0.8B and 2B models rewrite and summarize well but stumble on facts and arithmetic. The 4B gets the president, the percentage, and the sorting task right and still runs at 44 tokens a second on an Apple laptop. Fogar recommends the largest size your machine can run well, computes arithmetic itself, and offers web grounding for facts.

Where is my API key stored?

In Chrome's extension storage on this profile, and it is sent only to the endpoint you typed. Fogar has no server that could see it.

What permissions does it ask for?

Storage, alarms and notifications for reminders, bookmarks for search, context menus for right-click, favicons for site icons, and access to huggingface.co to fetch the model. Cloud endpoints, search keys, and calendar addresses are requested one at a time, when you add them. The full list with reasons is in the privacy policy.

Will it slow down my browser?

The model loads only on the new tab page and is released when you navigate away. Loading takes about a second from disk. On a machine without WebGPU it falls back to the CPU and is slower but works.

Firefox? Safari?

Chrome and Chromium browsers first. Firefox builds, but its extension pages lack the shared-memory feature the multi-threaded engine needs, so it would be much slower. Not shipping it half-baked.

Install

Add to Chrome

Fogar is on its way to the Chrome Web Store. Until the listing is live, it installs from source in two commands and a drag-and-drop. This page will update the moment the store link exists.

git clone https://github.com/dylanroy/fogar && cd fogar
npm install
npm run build
# chrome://extensions → Developer mode → Load unpacked
# → pick .output/chrome-mv3, then open a new tab