Chrome Relay：让 Claude Code、Codex、Cursor 等编码智能体在真实 Chrome 后台标签页中操作

Website: https://agent-chrome-relay.aindeev.com

Lets your coding agents (Claude Code, Codex, Cursor, Paseo) use your everyday Chrome, with your real logins, from the command line, in background tabs: nothing takes focus, no dialogs, ~0.15s per command.

agent-browser --cdp "$(chrome-relay url you@company.com)" open https://app.example.com/
agent-browser snapshot -i          # the page's buttons, links and fields, each with a ref like @e5
agent-browser click @e5
agent-browser close

It's opt-in: nothing installs the extension for you, and it only runs on Macs whose owner set it up.

How it works

agent-browser (CLI) ──ws──▶ relay (127.0.0.1:9333, LaunchAgent) ──ws──▶ Chrome Relay extension ──chrome.debugger──▶ agent tab

Extension (extension/, MV3, one per Chrome profile you load it in): opens each agent tab inactive in a collapsed "Agents" tab group and runs DevTools commands in it via chrome.debugger. No remote-debugging port, so Chrome never shows "Allow remote debugging?". Chrome does show "Chrome Relay started debugging this browser" while agents work.
Relay (relay/relay.mjs): a DevTools endpoint per agent. Each agent sees and controls only the tabs it opened; commands that could raise or focus the browser are swallowed.
CLI (bin/chrome-relay): setup, the connection URL, diagnostics, audit trail.

Setup (once per Mac, ~2 minutes)

Fastest: paste this prompt into Claude Code, Codex or Cursor and let your agent do it. By hand:

Needs macOS, Google Chrome, Node.js 20+ and agent-browser (npm i -g agent-browser).

git clone https://github.com/aindeev/agent-chrome-relay
cd agent-chrome-relay
bin/chrome-relay setup     # secret, background service, identities, `chrome-relay` on PATH, Claude Code skill

Then, in each Chrome profile agents should use: open chrome://extensions, turn on Developer mode, Load unpacked, and pick the extension folder of your clone. Check with chrome-relay doctor.

After git pull: chrome-relay update (restarts the relay, reloads the extension in every profile). To remove: chrome-relay uninstall, then remove the extension in each profile.

Telling your agents

Claude Code: setup links the skill (skill/SKILL.md) into ~/.claude/skills/chrome-relay, so every repo gets it. Codex, Cursor and others: point them at the same file, e.g. a line in your global ~/.codex/AGENTS.md: "For any browser step that needs my logins, follow <path>/agent-chrome-relay/skill/SKILL.md." A repo's CLAUDE.md/AGENTS.md only needs a one-line pointer to the skill.

Who can drive it

Two checks on every agent connection:

This Mac's secret: generated at setup in ~/.chrome-relay/token (mode 600) and embedded in the URL that chrome-relay url prints.
An allowed agent app: the connecting process must come from Claude Code, Codex, Cursor or Paseo. The relay looks the process up (lsof, ps) and checks the markers those apps set in their child processes (CLAUDECODE, CODEX_*, CURSOR_*, PASEO_AGENT_ID), then its parent processes.

Connections that carry a browser Origin header (a web page) are refused even with the secret. Only this checkout's extension may connect as the extension: Chrome derives an unpacked extension's ID from its folder, setup records that ID in ~/.chrome-relay/config.json, the relay checks the connection's Origin: chrome-extension://<id> (which pages cannot fake), and the connecting process must be Chrome.

This keeps other local tools, web pages and accidents out. It is not a boundary against malware already running as you, which could read the secret and fake the markers.

Sign-ins

Agents never type credentials. When a site bounces through Google and the right account is already signed in, the extension clicks the account and Continue/Allow itself (page scripting, so it works even with 1Password's frame on the page). A password, passkey, 2-step screen or signed-out account stops the hop, and the agent gets SIGN-IN NEEDED: ... and asks you to sign in in your own window.

Which Google account a site uses comes from ~/.chrome-relay/identities.json (chrome-relay identities): your Chrome profiles (filled in by setup), optional hand-set sites.rules, and sites.learned, which the relay fills in after each successful hop. Default: the profile's own account.

Audit trail

Every agent action is recorded in ~/.chrome-relay/audit/YYYY-MM-DD.jsonl; read it with chrome-relay audit: who connected (app, Claude/Paseo session id, working folder, AGENT_BROWSER_SESSION), pages, clicks with positions, special keys, the agent's own scripts, screenshots, uploads, popups, sign-in clicks and blocked pages. Typed text is stored only as a character count, and URLs lose their query string.

Behaviour worth knowing

Popups and target=_blank links open as new hidden tabs owned by the same agent; popup sign-in flows that postMessage back to the opener and close themselves keep working. Message origins are the ones the relay saw each tab load (never what the page claims), and targetOrigin is enforced. A safety net adopts any tab an agent page opens anyway and hands focus back to the tab you were on.
1Password: Chrome drops an extension's debugger from a page that contains another extension's frame (1Password's menu on login forms). The agent's commands wait while the extension re-attaches.
Self-cleaning: tabs of an agent silent for 30 minutes are closed. When the relay restarts, the extension closes the agent tabs it opened (tracked by tab id, so your own tab groups are never touched).
Real input in background tabs: focus emulation is on in every agent tab, so clicks and typing land.

Development

cd relay && npm install && npm test     # who may connect: secret, allowed apps, Chrome-only extension, audit

Logs: chrome-relay logs (~/.chrome-relay/relay.log). Testing extension changes: edit extension/, then chrome-relay update. CHROME_RELAY_HOME and CHROME_RELAY_PORT override the data folder and port.

About the author

Made by Alexey Indeev, co-founder and CTO of Spare. I write about building more with AI, whether you code or not, at The Leveraged Mind.

Blog: https://read.aindeev.com
X: @AlexeyIndeev
LinkedIn: https://www.linkedin.com/in/alexey-indeev/
GitHub: @aindeev

Questions, ideas or bugs: open an issue or reach out on X.

License

MIT. See LICENSE.