Crawler operator
Manus
In short
Manus told users on 29 December 2025 that it was joining Meta, while staying based in Singapore. It asks the user to take over when a CAPTCHA or an SMS code stops the agent, keeps each user's sessions in a separate isolated browser, and works in logged-in tabs only after the user authorises a session.
- Type
- Crawler operator
- Operator
- Meta
- Based in
- Singapore
- Homepage
- manus.im
- In one line
- General-purpose AI agent, owned by Meta since December 2025, that browses either in an isolated cloud browser or through an extension inside the user's own browser, and publishes no identifier, robots.txt policy or signing keys for site owners.
- Last read
- 2026-11-05
What Manus does for this layer
From the vendor's own pages
Manus announced on 2025-12-29 that it is joining Meta and said the company would continue to operate from Singapore and keep selling its subscription through its own app and website. (manus.im, dated 2025-12-29) Manus browses in two modes: Cloud Browser, an isolated sandboxed browser in the cloud, and Browser Operator, an extension that works inside the user's local browser with existing logins and sessions. (manus.im) Manus's Browser Operator docs say using the local browser "avoids CAPTCHAs and security checks" on sites where the user is already logged in. (manus.im) When Cloud Browser meets SMS codes, CAPTCHAs or multi-factor prompts, Manus asks the user to "Take Over" the browser, complete the check and hand control back. (manus.im)
Manus lets users log into personal or work accounts inside Cloud Browser so the agent can act with those sessions, and gives each user a separate isolated browser instance. (manus.im) Manus's Browser Operator requires the user to authorise every session, and the user can stop the agent by closing its browser tab. (manus.im)
Claims the vendor makes about itself
Manus says its agent had processed more than 147 trillion tokens and powered over 80 million virtual computers by the time of the Meta announcement. (manus.im, dated 2025-12-29) Manus's homepage, read on 2026-11-05, introduces Manus 2.0 and lists slides, websites, games, video and design among the tasks the agent takes on. (manus.im)
What our crawl saw
A GET for manus.im/.well-known/http-message-signatures-directory returned HTTP 404 on 2026-11-05. (manus.im)
Products and plans
| Product | What it does | Price model | From | As of |
|---|---|---|---|---|
| Manus Cloud Browser | Isolated cloud browser the agent operates, with user takeover for verification steps. | |||
| Manus Browser Operator | Browser extension that lets the agent work in the user's own browser and logged-in tabs. | |||
Standards
| Standard | Status | Evidence |
|---|---|---|
| RFC 9309 (robots.txt) | No statement | No robots.txt statement on the docs pages read (2026-11-05). |
| Web Bot Auth | No statement | No key directory at manus.im (HTTP 404, 2026-11-05). |
| Published IP list | No statement | No IP list published for Cloud Browser traffic (2026-11-05). |
Our checks
| Check | Result | Method | Date |
|---|---|---|---|
| Homepage fetch | HTTP 200 | GET with the crawl user agent after a robots.txt check | 2026-11-05 |
| Web Bot Auth key directory | HTTP 404, text/html | GET https://manus.im/.well-known/http-message-signatures-directory with the crawl user agent after a robots.txt check | 2026-11-05 |
What Manus does not do
- Manus publishes no user agent string, robots.txt token, IP list or signature key directory for either browser mode (checked 2026-11-05).
- Manus Browser Operator works inside the user's own browser with the user's logins, so its requests carry that browser's identity rather than a Manus identifier.
Related pages on this site
Sources
Last reviewed 2026-11-05