browser-relay

Browser Relay lets an AI agent join the Chrome browser you already use through an agent-native Skill + CLI. It does not launch a blank automation profile, keep pulling another browser window to the foreground, or make you log in again. You and the agent work in the same everyday browser — locally or across multiple machines.

Use it when the task lives in a browser that already has the right login, extensions, device trust, or network access: operate your desktop browser from an agent on your phone, reach an internal system through the already-authenticated browser on your work computer, or let one agent work across browsers on several machines.

Real Chrome, not a throwaway profile

Most browser automation spins up a fresh, empty browser profile. That is fine for testing, but useless for agents that need your authenticated web apps — SaaS dashboards, admin panels, internal tools, documents, private sessions — where a headless browser or a fresh profile simply is not logged in.

Browser Relay is that missing layer:

• Your actual Chrome session — cookies, localStorage, extensions, and login state, shared as-is.
• No pop-up automation browser — it never spawns a separate window or opens tabs behind your back; navigation reuses an attached tab.
• Local or remote — one agent can drive browsers on this machine or several other machines through an outbound relay connection, with no public browser port exposed.
• Agent-first — install the bundled Skill so Claude Code, Codex, Cursor, Windsurf, and other agents know when and how to use the inspectable CLI.
• Local-first boundary — the relay binds to 127.0.0.1 by default.

Provenance

Based on chengyixu/openclaw-browser-relay, with auto-attach behavior inspired by blakesabatinelli/openclaw-chrome-relay. Repackaged as a general-purpose local browser bridge for AI agents, without the OpenClaw-specific gateway, token auth, or platform bindings.

Architecture

Local
  AI Agent ──Skill + CLI──▶ Relay server (Node, 127.0.0.1)
                                        │ WebSocket
                                        ▼
                                 Chrome extension ──chrome.debugger / CDP──▶ your Chrome tabs

Remote (Remote Relay)
  AI Agent ──HTTPS──▶ public relay (relay.linso.ai) ◀──WSS── Chrome extension ──▶ your Chrome tabs

Local mode is the default: the agent talks to a relay server on 127.0.0.1, which forwards Chrome DevTools Protocol commands to the extension.

Remote mode exposes nothing. When you turn on Remote Relay, the extension connects out to a public relay service; a remote CLI reaches that same service, which routes each command down to your browser over the existing connection — no open ports, no local server on the network. Use the default hosted relay, or run your own on Cloudflare in one click (see below).

Quick Start

Use Browser Relay in four steps. You need desktop Chrome plus Node.js/npm. The Chrome extension is loaded manually from its installed directory.

1. Install

npm install -g @linsoai/browser-relay

The package attempts to register a user-level background service. If your environment has no supported service manager, the verification step below gives the exact foreground command instead of failing with a stack trace.

2. Load the Chrome extension

Print the extension directory:

browser-relay path

Then open chrome://extensions, enable Developer mode, click Load unpacked, and select the extension directory printed by browser-relay path.

3. Verify the browser connection

Run one complete read-only diagnosis, then list the attached tabs:

browser-relay doctor
browser-relay tabs

doctor should report a healthy relay and connected extension. tabs should print at least one tab ID, title, and URL:

t_A7k2Pm9QxL    Example Domain    https://example.com/

If doctor says the service manager is unavailable, start the relay in another terminal and keep it running:

browser-relay

Then retry browser-relay doctor. If the relay is healthy but no tabs appear, reload the unpacked extension and retry browser-relay tabs. doctor never installs, restarts, or changes anything; add --json for automation.

The global install uses launchd on macOS, systemd-user on Linux, and a current-user Task Scheduler task on Windows. The service starts when you sign in. The Windows task uses your existing interactive login token with least privilege: it does not store a password, elevate itself, or run as SYSTEM. Organization policy can still block standard-user task registration.

browser-relay install safely refreshes a Browser Relay-owned service definition, starts it, and verifies the HTTP endpoint and installed version. Run it after an nvm upgrade or when doctor recommends it. It refuses to overwrite a same-name Windows task without Browser Relay's ownership marker. If a managed environment has no usable service manager, foreground mode (browser-relay) remains available.

Upgrade with browser-relay update. It installs @linsoai/browser-relay@latest globally, attempts to refresh the service, and prints a status check; the extension reloads itself on its next relay reconnect (within about 30 seconds).

4. Install the Agent Skill and run the first task

Browser Relay ships with an agent-friendly Skill. Choose the Agent explicitly so installation never opens an interactive selector:

browser-relay skill install --agent codex

# Claude Code, or both agents at once:
browser-relay skill install --agent claude-code
browser-relay skill install --agent codex claude-code

The command uses the standard skills CLI non-interactively, then reads every target SKILL.md back to verify it. Use --agent universal for agents that consume the standard ~/.agents/skills directory, browser-relay skill path to inspect the bundled source, or plain browser-relay skill to print an install command for all agents (--agent "*"). Printing the command does not install anything. After installation, your agent can operate your own browser without opening a separate automation browser.

Give the agent a small read-only task first:

Use Browser Relay to tell me the title and URL of my current Chrome tab. Do not navigate.

The first successful response proves the full path works: Agent Skill → CLI → relay → extension → your existing Chrome tab.

If Browser Relay solves a workflow you actually have, starring the repository helps other agent builders find it.

Agent Friendly by Default

Version 1.5.0 adds complete content reading, managed tab sessions and explicit handoff. See the release notes and upgrade steps and implementation and validation. Development pushes do not publish npm packages; publication requires a manual workflow run with an explicit version and channel.

Version 1.5 also adds a persistent JavaScript runtime, accessibility references and ordered action groups. Inspect with browser-relay observe --tab <id>, then execute a known sequence with browser-relay actions --tab <id> --file actions.json. One group runs inside the extension and returns the resulting state. Independent tabs may run concurrently; groups on one tab are serialized and cancellable.

For scripts, use browser-relay exec --file workflow.js, or the MCP browser_exec tool to retain variables between calls. MCP screenshots are image content blocks. Visual click, drag and hover support screenshot coordinate mapping; background semantic clicks preserve the user's foreground tab. Visual mouse input reports needs_foreground when a visible tab is required.

See the runtime and SDK reference and Codex comparison and measured results. Local scripts are trusted code with the agent's OS permissions; their separate process provides timeouts and reset, not a security sandbox. Remote devices only receive browser operations, never the agent's local JavaScript source.

Browser Relay is designed to be comfortable for agents, not just low-level automation scripts.

• The included Skill tells agents when to use Browser Relay and how to interact safely.
• Page snapshots are annotated with links, buttons, inputs, and other interactive elements so agents can plan before acting.
• Actions target existing attached tabs, keeping the user's browser context visible and predictable.
• Stable CSS waits let agents wait for an element to attach or become visible instead of guessing with fixed sleeps.
• Console and network capture record console.*, page exceptions, log entries, and request/response activity for debugging real-page behavior.

CLI

The CLI is the primary interface. For agents that can run shell commands, it is faster and less error-prone than hand-writing curl JSON:

browser-relay tabs
browser-relay console --tab t_A7k2Pm9QxL --limit 50
browser-relay network --tab t_A7k2Pm9QxL --type response --status 500
browser-relay snapshot --tab t_A7k2Pm9QxL --max-length 20000
browser-relay wait 'button[type=submit]' --state visible --timeout 10000 --tab t_A7k2Pm9QxL
browser-relay click 'button[type=submit]' --tab t_A7k2Pm9QxL
browser-relay type 'hello world' --selector 'input[name=q]' --clear --submit
browser-relay key Control+L
browser-relay scroll down --amount 1000
browser-relay screenshot /tmp/page.png --full-page
browser-relay eval 'document.title'

For long text or JavaScript, avoid shell escaping by reading from stdin:

printf 'hello\nworld' | browser-relay type --selector textarea --stdin
browser-relay eval --stdin < script.js