Manus

There are two things to consider: which tasks you will hand it and whether you are ready to pay credits for each one.

Who it is for. For those handing off long tasks end-to-end: sort through a stack of resumes, turn data into analytics, build a website or slides by morning. Manus takes these tasks to a finished file itself, without your guidance along the way.

Who it is not for. For those expecting quick answers to questions: regular chatbots are for that, while Manus works for minutes and charges hundreds of credits per run. Also not for those unprepared to use it from Russia: you will need a foreign IP address and card.

Paused until August 25. The service is unavailable on August 23–24: after splitting from Meta*, the vendor is deleting data created since December 29, 2025, and promises to restore access on August 25, 2026 at 8:00 Singapore time. This does not prevent a new user from getting started on the 25th.

A fit for you — section 3 takes you from registration to your first task. Choosing between it and ChatGPT Agent: see the split in section 7.

What vibecoding isStarting from scratch: how to set tasks for agents with no coding experience

One cycle for any task: a plan, work in its own virtual machine, and a finished artifact at the end.

Task in words. “Build a quadrant chart of NBA player performance” from the official demo is the entire input. The agent then creates a plan, finds data, writes and runs code in an isolated sandbox, and checks the result itself.

Work is visible. Next to the chat is the “Manus’s Computer” panel: it shows which command the agent is running, which website it opened, and which file it is editing. If it goes off track, correct it in words as it works.

Wide Research. For large tasks, Manus deploys up to a hundred copies of itself in parallel. Vendor examples: rank 100 MBA programs or analyze 1,000 stocks. Each copy works as a full agent, not a narrow assistant.

Browser Operator. The agent operates a browser like a person: logs in, clicks, fills out forms, and pulls data from live websites. The feature has been available to all users since November 22, 2025.

What was actually done. Official demos include screening a stack of RL engineer resumes with a final ranking (launch March 6, 2025) and an NBA quadrant chart with player avatars. Third-party tests include a wedding invitation website in 25 minutes for 360 credits, and a weather forecast web app for about 900 credits (cyber.sports.ru, June 2025). We have not run Manus ourselves: from Russia it is only available with preparation, and the service was paused during the review window, so the figures come from official demos and third-party tests.

There are three doors: browser, phone apps, and desktop. First, two preparation steps.

You can use it from Russia. The first step is standard. Change your Russian IP address to a foreign one — American, Singaporean, or any other. The service is not officially available in Russia, so neither registration nor payment will work from a Russian address.

Step 2. Register at manus.im: email, Google, Apple, or Microsoft, with no phone number required. An invite code is not needed either — since 2026, it has been a 500-credit referral bonus rather than a pass.

Step 3. Give it your first task and name the outcome: “build a one-page invitation website,” “turn these tables into a report with charts.” The free 300 credits per day are enough for one or two small tasks — you can get a feel for the agent without paying.

Apps. The web version works in any browser. The iOS app requires a foreign Apple ID, Android is in Google Play, and the website provides desktop apps for macOS and Windows. Do not install APKs from third-party websites: the official build is in Google Play.

In Russian. You can write tasks in Russian: the agent detects the language itself and replies in Russian. The interface is currently English or Chinese.

Steps checked August 23, 2026 using vc.ru and Bitrix24 guides · service paused until August 25, 2026 08:00 SGT

Benchmark pairs of “agent + model” are not yet measured for general-purpose agents — look at three other signals.

Vendor claim. At launch, Manus claimed a GAIA benchmark record: 86.5% at level one versus 74.3% for OpenAI Deep Research (claim dated March 6, 2025). There is no independent reproduction of this figure, and GAIA itself is criticized as easy to optimize for — treat it as advertising, not a measurement.

Money as a measurement. Annualized revenue grew from $125 million in December 2025 to $450 million by June 2026 (Sacra estimates). Paying demand tripled in six months — even as Meta* and regulators were dividing up the company throughout that period.

Popular demand in Russia. “Manus” and “Manus AI” together draw about 20 thousand searches per month on Yandex (Wordstat, measured August 23, 2026) — a lot for a service that is not officially available in Russia.

You do not pay for access, but for work: every task consumes credits, and that is the main thing to understand before subscribing.

Free entry. 300 credits per day, expiring after 24 hours and not accumulating. Users spent 360 credits on an invitation website and about 900 on a web app with live data, so a free day is enough for one small task or a couple of very small ones.

Paid tiers. From $20 per month for 4,000 credits to $200 for 40,000; all paid plans retain the daily 300. Official pricing was unavailable during the review window along with the website, and the figures are from June 2026 review summaries, so they may change after the August 25 relaunch.

Paying from Russia. Russian cards do not work; charges are in dollars. Usual options: a foreign card or an intermediary with a 13–20% fee. For instructions, see payment guide.

Three questions: where your data lives, what can happen to it, and how much to trust the results.

Data lives with the vendor. All tasks run in the Manus cloud, and August 2026 showed what that means in practice: at regulators' request, the vendor deleted user data created after 12/29/2025 in several jurisdictions. The lesson is simple: download finished artifacts immediately; Manus conveniently provides them as files.

Which jurisdiction. The company was founded in China; its legal entity and headquarters are in Singapore, while the vendor says its data stores are in the US and Singapore. A Chinese regulator blocked the Meta* deal. A Tencent-led consortium is now negotiating to buy Meta*'s stake - the deal has not closed, and the ownership structure is still in flux.

Results need fact-checking. Reviewers agree: the agent "hides hallucinations well," and its report looks polished even when the numbers are wrong. Long tasks can loop; a known failure was booking a trip to Japan. The agent runs code in an isolated sandbox and does not touch your machine.

The choice is not "who is smarter," but "what work and what budget."

Different economics. ChatGPT Agent is included in the $20 Plus subscription with no credit counter: practitioners call it the safest default choice for that reason. Manus charges credits for every run, and a complex task costs 300–900 - for regular work, it is more expensive.

Different depth. Manus handles long autonomous tasks and delivers finished artifacts: a website, slides, a report with charts; Wide Research can spin up to a hundred agent copies for one task. ChatGPT Agent is faster and more convenient for small tasks within the familiar chat.

Who else is nearby. Genspark wins on presentation and multimedia speed, Comet embeds an agent directly in the browser. All neighbors accessible from Russia also work only through workarounds.

The product is a year and a half old, and nearly all of its second year was spent deciding who it would belong to: the Meta* deal, a regulatory block, relaunch.