Browsentic connects Claude Code, Codex, Cursor or another agent CLI to your real, signed-in browser. You type or say the job in the side panel. The agent works in your tab and asks before it submits, uploads or leaves the site.
For example: every weekday at 9, summarise the PRs waiting on me
One line, about two minutes
On macOS
curl -fsSL https://browsentic.com/install.sh | sh
On Windows, in PowerShell (experimental)
irm https://browsentic.com/install.ps1 | iex
Anywhere, with Node.js 20 or newer
npx browsentic@latest setup
Setup asks which browser you use and opens the extension’s store page there. Press Add, and the extension connects to Browsentic Bridge by itself; if it asks for a code, enter the one setup shows. Install guide
Runs on your machine
nothing hosted, no cloud browser
No API key
it runs the agent you are already signed in to
Your logged-in session
your cookies, your two-factor, your extensions
Free and open source
Apache 2.0 licensed, no account, no subscription
What it does
Scheduled jobs, recorded jobs, several tabs at once, site maps and voice, all on the sites you are already signed in to.
Every weekday at nine, every Friday evening, once tomorrow morning. Each run works in a background tab of its own and leaves you a one-line result. A recorded job replays without an agent, so it spends no tokens.
Scheduled tasks →Press record and do the job yourself. Next time, “do it like last time” is the whole instruction, and every step is checked against the live page before it runs.
Record and replay →Start a job in one tab, then another. Each keeps its own conversation and keeps working in the background while you read something else.
Orchestration →Point the agent at a web app and it explores the site, then saves notes that every later visit to that site starts from.
Site maps →Close the panel and speak. A mic floats on the page, and a short pause sends what you said. In Chrome and Edge.
Hands-free →New in v0.8.9
Switch on Android in the side panel and a desktop tab shows the phone’s Chrome live. Ask for the job as you would in any tab: the agent taps, scrolls and types on the phone, and you can take over from the same picture.
Taps are touches, typing is keyboard input and scrolling is a real scroll, so the agent sees the page the site serves to that phone.
Browsentic Bridge reaches Chrome on the phone through adb over USB or Wi-Fi. No app, no account, no cloud device.
Approvals and blocked sites apply on the phone, and a phone run is offered only the tools that work there.
Point at an element on the phone’s picture, or approve a tool the agent writes for the phone’s page.
How it works
The side panel passes your instruction to Browsentic Bridge, a small program on your computer, which starts the agent CLI you already use. The agent talks to its own model provider as usual. Browsentic adds no server.
Your computer
Safety
An agent in your browser can reach your email, your bank and your work. Browsentic connects to nothing until you pair it, and the agent must ask before it submits, uploads or leaves the site.
Only Browsentic’s own extension can pair with Browsentic Bridge, and web pages are refused. Have it ask you before each new browser if you like.
Sending a form, uploading a file or leaving the site it was sent to waits for your OK.
Your agent talks to its own provider, as it always does. Browsentic has no cloud of its own.
Read every line. Code the agent writes for itself is shown to you in full before it runs.
Two limits. Other programs running as you could drive a browser you have already paired. A hostile page can still try to mislead the agent, as it could any agent that reads the web.
FAQ
Run one line. On a Mac, curl -fsSL https://browsentic.com/install.sh | sh installs the Mac app; on Windows, irm https://browsentic.com/install.ps1 | iex installs the Windows app (experimental); anywhere with Node.js 20 or newer, run npx browsentic@latest setup. Each installs Browsentic Bridge on your computer, asks which browser you use and opens the extension’s store page there (the signed add-on for Firefox). Add it, and the two pair by themselves; if the extension asks for a code, enter the one setup shows. Both parts update themselves from then on.
No. Browsentic runs on the agent CLI login you already have: Claude Code, Codex, Antigravity, Mistral Vibe, Grok Build, Cursor CLI, Qwen Code or OpenCode. There is no API client in the repository and nothing to paste into a settings field. Browsentic Bridge starts your CLI locally, as you.
Yes. In the side panel’s Schedules tab, set an instruction or a recording to run once at a set time, on chosen days, or every so often. Each run opens its own background tab, does the job, closes the tab and leaves a one-line result on the page you are looking at. A recording replays without an agent and spends no tokens, unless a step no longer fits the page. Runs need the browser open; one that falls due while it is closed runs once when the browser is back. Anything that needs your approval shows a card on the page you are on.
No. It drives the real tab in front of you, with your sessions, cookies, extensions and two-factor state. Nothing is re-authenticated in a throwaway profile.
Yes, on Android, as an experimental feature. Plug the phone in or pair it with adb over Wi-Fi, switch on Android in the side panel, and a desktop tab shows the phone’s Chrome live. The agent works on the phone with real taps, scrolls and typing. Nothing is installed on the phone: Browsentic Bridge reaches it through adb. iPhones are not supported.
Free and open source under Apache 2.0, with no API key, subscription or account. One line installs Browsentic Bridge and opens the extension’s store page. Nothing connects until you pair the two.
Available in the Chrome Web Store
Available on Edge Add-ons
Firefox add-on, signed by Mozilla
