AI & Agents
agent-chrome-relay
Source: aindeev/agent-chrome-relay
Last updated 2026-10-10 · benchmark checked 2026-11-16 · unchanged since 2026-10-10 — deterministic & reproducible
A Chrome extension relay for agent-based browser automation.
agent-chrome-relay at a glance
agent-chrome-relay, also called Chrome Relay, is a Mac tool that lets AI coding agents such as Claude Code, Codex, Cursor, Paseo, and pi control your everyday Chrome browser, signed in as you, in background tabs that don't take focus or move anything on screen.
Good for
- Letting an AI coding agent complete a whole browser task from one command without the browser window popping up or stealing focus
- Keeping login credentials, 2-step codes, and passkeys hidden from the agent by having 1Password fill them in automatically
- Approving an agent's action from an iPhone with Face ID when you're away from the Mac
Pricing
No price is listed; the project is released under the MIT license.
Questions people ask
What does agent-chrome-relay (Chrome Relay) do?
It lets coding agents like Claude Code, Codex, Cursor, Paseo, and pi control your everyday Chrome browser, signed in as you, in background tabs that don't take focus or move anything on your screen.
How does it handle my logins and passwords?
Google account sign-ins are clicked through automatically, and other logins come from 1Password vaults you share with it; passwords, 2-step codes, and passkeys are typed by Chrome Relay so the agent itself never sees them.
Can I see what an agent did after the fact?
Yes, Chrome Relay keeps an audit trail of everything every agent did.
What do I need to set it up?
It requires macOS, Google Chrome, and Go 1.25+; setup involves cloning the repository, running ./build, then ./chrome-relay setup, which takes about 2 minutes.
Which password managers does it support?
Currently only 1Password is supported.
Written by Legit.Show from github.com on 2026-10-24. It does not change the score.
Are you the maker of agent-chrome-relay? Claim this listing. It is free, takes a meta tag, a DNS record or GitHub admin rights, and never changes the score.
Launched something? Add your product, free.
To cite this score: legit.show/s/gh-agent-chrome-relay/2026-11-16. That address never changes; this page moves with every re-measure.
Legit.Show scored agent-chrome-relay 100/100 on 2026-11-16, measured across 3 of 7 frames from its public surface. legit.show/s/gh-agent-chrome-relay/2026-11-16
Is agent-chrome-relay production-ready?
Legit.Show scores agent-chrome-relay 100 out of 100 — the simple average of its 3 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on agent-chrome-relay (github assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Security; its weakest is Discoverability. 3 of the seven frames returned a score; Performance, Accessibility, Privacy and Reliability were not measurable on this service and are recorded as null — not as zero. Maintenance is an additional frame from the open-source teardown, scored separately from the seven. Every frame it averages is published with its evidence on the Legit.Show listing.
The 7 Frames
- Performance — not measurable on this service (null — not scored as 0)
- Accessibility — not measurable on this service (null — not scored as 0)
- Security — 100/100How this compares across the catalogue: The Web Security Baseline
- Privacy — not measurable on this service (null — not scored as 0)
- Reliability — not measurable on this service (null — not scored as 0)
- Standards — 100/100
- Discoverability — 100/100
Open-source teardown
Scored separately — not one of the seven.
- Maintenance — 100/100
What we measured
- No Content-Security-Policy and no HSTS.
- No privacy policy found.
- Sets cookies / loads scripts with no consent prompt.
Who it's for
AI developers · Agent creators · Automation engineers
Sources and updates
- Description
- Taken from github.com's own website on 2026-10-10.
- Code
- github.com/aindeev/agent-chrome-relay.
- Benchmark
- Measured by Legit.Show from the live site, the way any visitor sees it — with no access to its code or accounts. Same method for every product, and no AI decides the score. Last checked 2026-11-16.
Put together from public information, without agent-chrome-relay's involvement. If anything here is wrong, tell us and a person will check it.
Visit agent-chrome-relay → · Alternatives to agent-chrome-relay → · How this was measured →