The agent-first browser

Tell your browser what to do. Watch it do it.

Pickle Browser searches, opens real pages, reads them, and reports back with its sources. It runs on your machine, in a window you can watch, so you see every step and can take the wheel at any point. Use a model that runs locally for free, or bring the Claude or ChatGPT you already pay for.

Free · runs locally with no account · your pages never leave your device

See it work

Give it a goal. Watch it go.

Unedited screen capture: it searches, opens real pages, reads them, and writes up what it found, while you watch every step and can take over at any point.

Real run, at real speed. Nothing staged, edited, or re-enacted.

Bring your own brain

You choose where the thinking happens.

Pickle Browser is not tied to one AI company. Three ways to power it, and you can switch at any time in Settings.

On your machine
Free, no account

The Ollama engine ships inside the app. On first run it downloads one open model sized to your hardware (about 1 GB), then works offline.

  • Good at summarizing the page you're on, pulling out data, answering questions about what's in front of you
  • Models Qwen2.5, Llama 3.2, Phi-3, Mistral and other Ollama models
  • Page content never leaves your device

Straight answer: small local models are far less reliable on long multi-step research. They can lose the thread and go off topic. The app labels them and warns you, and you can switch mid-task.

Free hosted models
Free, no card

Want more capability without paying? Two routes are free today, and both are one-time setup.

  • Ollama Cloud gpt-oss 20B and 120B, qwen3-coder 480B, after a free sign-in
  • NVIDIA Build 100+ hosted models with a free API key
  • Fast enough for real multi-step research on any laptop

These run on someone else's servers, so the page text for that task is sent to them. Your history, notes and logins still stay local.

What you already pay for
Your existing plan

Already subscribed to Claude or ChatGPT? Use it. Nothing new to buy.

  • Your API key for Claude, GPT or Gemini
  • Or connect over MCP from Claude Desktop, Claude Code, Cursor or VS Code and drive this browser with 72 tools
  • Your credits go further: it sends a clean page summary instead of raw HTML

Connected agents get the same approval gates. Buying, sending and anything irreversible still asks you first.

fewer tokens than sending raw HTML, measured live in-app
$0
API cost when it runs on the bundled local model
0%
of your browsing leaves the device, because it all runs local
Why this and not the rest

Most agent browsers run somewhere you can't see.

Cloud agent browsers are infrastructure for developers shipping automation: headless, remote, and starting from a blank session every time. Pickle Browser takes the opposite bet. It's a browser you use, that an agent drives while you watch. It does cost less to run, but that's a side effect of being efficient, not the reason to switch. The reason is that the work happens in front of you, on your hardware, and you can stop it mid-step.

Cheaper to run

$0 per run on the built-in model

Instead of piping raw page source into the model, it sends a compact structured summary. Measured across ten real sites: a median 156× fewer tokens than raw HTML (range 4×–663×), or about against already-extracted page text. Tools that read an accessibility tree land in a similar range. The saving that always holds is that the bundled local model costs nothing per run.

Private by default

Runs on your computer, not a cloud

It uses your real browser and logins, and page content never leaves your device. No hosted browser, no account to create. And because a model ships in the box, it even works offline.

Yours to control

Your model, your window, your call

Connect any MCP agent. You choose the model, Pickle Browser is just the browser. You see every tab it opens, can grab the wheel any time, and it always asks before it buys.

Why not just use…

The honest comparison.

There are four common ways to give an agent a browser today. Here's where each one leaves you, and where Pickle Browser is different.

Pickle Browser Chrome+ extension Cloud AI browsere.g. hosted assistants Dev automationPlaywright MCP / scripts
The browser you already browse in, with the logins you already have their cloud ~ separate profile
A model is included, so it works with no cloud account bundled their model bring your own
Page content never leaves the device on the local model ~ per extension ~ depends on your model
Watch it work and take the wheel mid-task native tabs ~ ~ headed, separate window
Asks before buying or anything destructive ~
Token-efficient page reads measured raw HTML ~ opaque accessibility tree
Use any model you want any MCP ~ locked in any MCP client
Works with your agent, no code ~ config
No per-use or subscription cloud fees local subscription ~ needs a model

✓ built in · ~ partial or depends on setup · ✗ not without giving something up

The measurable edge

Reading a page shouldn't cost 40,000 tokens.

A single modern web page is often 30–60k tokens of raw HTML. Pickle Browser gives the agent a structured read (headings, links, and interactive elements with stable ids) that's a small fraction of that, and logs exactly what it saved. The savings aren't a slogan; they're a number in the toolbar.

observeextract_markdown named elementstab digest per-step token meter
Connect an agent

Bring the agent you already use.

Pickle Browser speaks the Model Context Protocol, so any MCP client, like Claude Desktop, can drive your real browser. Add one server entry and the agent gets a full set of browse, read, and shop tools.

  1. Install Pickle Browser. The local runtime and MCP server come bundled.
  2. Add the Pickle Browser server. One entry in your agent client's MCP config.
  3. Ask your agent to browse. It drives the tab you're watching.
// claude_desktop_config.json
{
  "mcpServers": {
    "pickle": {
      "command": "pickle-mcp"
    }
  }
}

The app shows a copy-paste config on its Connect screen, matched to your client.

Shopping, done right

One cart across every store.

Pickle Browser Search reads real product catalogs over the Universal Commerce Protocol when a store supports it, and clean web results when it doesn't. Your agent fills one cart across merchants; checkout splits it into a real cart at each store.

UCP catalogsglobal cartagent checkoutyour approval to buy
What's inside

Everything the agent needs, in one place.

Not a chat box bolted onto a browser, but a full toolkit for you and your agent, all running on your machine.

Local AI

Runs on your machine

The engine is built in and pulls an open model on first run. After that: no keys, no account, works offline, $0 per run.

SOUL.md

Give your agent a personality

One editable Markdown file sets its tone, rules, and boundaries.

Skills

Reusable playbooks

Deep Research, Compare Prices, Fill Form… built in, and you can add your own.

Plan mode

Research → a cited report

Decompose a goal, watch each step, get a structured deliverable with sources.

Playback

Replay any run

Step through what the agent did, screenshot by screenshot.

Token meter

See what you save

Every step shows tokens saved vs sending raw HTML. Measured, not promised.

Global cart

One cart across stores

Shop over UCP + the web, checkout splits into a real cart per merchant.

Connect apps

Your tools, via MCP

Plug in Gmail, Slack, Notion, or your own MCP server for the agent to use.

Get Pickle Browser

Download and hand your agent the keys.

Free, no account. Set up local AI in one click on first run, or connect the model you already use.

One codebase, all three platforms · ~120 MB · early build

The bundled local model is best for quick single-page work: summarizing, extracting, and answering about the page you are on. Small models are far more error-prone on long multi-step research, so connect a larger or cloud model when accuracy matters.

Get in touch

Questions, bugs, or want early access?

We read everything. Tell us what broke, what you wish it did, or what you are trying to automate.

launch@picklebrowser.com

If you are reporting a problem, include your OS and the app version from Settings. Please do not paste API keys or page content.