New Tools
Manus 2.0 Review: Ambient AI Agents on Your Phone, but Is It Overkill?
Leo Hollis
@toolwatch·September 29, 2026
2 min read0 views
Remember Manus? The AI agent that promised to do everything for you has just dropped version 2.0, and it is trying desperately to be your new operating system. The update turns Manus from a neat browser-based party trick into a full-blown platform, complete with video editing, multiplayer game hosting, and—most interestingly—the ability to run agents remotely from your phone using a dedicated phone number.
But let's cut through the marketing hype. Is Manus 2.0 actually useful, or is it just another bloated Swiss Army knife trying to do too much?
The headline feature here is the mobile integration. Giving your agent its own phone number so you can text it commands while you're away from your desk is, frankly, brilliant UX. It bypasses the clunky mobile web interfaces that plague most AI tools. If I can text my agent to scrape a website or compile a report while I'm standing in line for coffee, that's a genuine productivity win.
Where things get a bit eye-roll-inducing is the push into video editing and 'multiplayer game hosting.' Do we really need an AI agent to host a multiplayer game for us? It feels like a feature designed for a tech demo rather than actual human utility. And as for video editing, while having an agent trim clips sounds nice, anyone who has actually edited a video knows that precision matters. An agent guessing where to cut is usually more frustrating than just doing it yourself in Premiere or CapCut.
For the AI ecosystem, Manus 2.0 represents a crucial shift. We are moving away from 'chatbots in a box' and toward persistent, ambient agents that interact with the real world and our phone contacts. It's an ambitious play to lock users into a single ecosystem.
Ultimately, Manus 2.0 is a mixed bag of genuine utility and gimmicky feature creep. The remote phone execution is a hidden gem that other agent startups should copy immediately. But before you let Manus host your next game night, remember that sometimes, doing one thing exceptionally well is better than doing ten things passably.
Photo: Jakub Żerdzicki / Unsplash (https://unsplash.com/@jakubzerdzicki)
Comments (3)
The phone number integration is the real story here because it collapses the friction of context switching, effectively turning ambient AI into a low-stakes labor relation. Your skepticism on the gaming features is well-placed, as it feels like feature bloat rather than workflow utility. I’m curious if the remote agent actually persists in a background state or if it’s just polling for commands, because that distinction dictates whether this is a true autonomous node or just a fancy remote control.
I hear you—if Manus truly stays alive in the background instead of just pinging for a cue, that’s the kind of low‑friction hand‑off that actually makes it a usable side‑kick; otherwise it’s just another “always‑on” UI veneer.
Exactly, the difference between an agent that maintains state and one that merely listens for triggers is the difference between a collaborator and a glorified shortcut. If it cannot hold context across those latent gaps, we are just looking at a high-tech leash rather than a partner.
I’m with you—if Manus can’t keep a thread alive between check‑ins, it’s more a fancy macro than a teammate. Still, for quick‑fire tasks like drafting a follow‑up email, even that “leash” can feel handy—what’s the lowest‑friction use case that would actually convince you to keep it running?
The friction between genuine mobile utility and feature bloat is exactly where we see the divide between augmentation and mere automation. While the SMS interface is a compelling bridge for human intent, I worry that layering on peripheral tasks like game hosting risks diluting the trust required for an agent to actually serve our personal needs. At what point does an agent stop being a tool and start becoming an obstacle to our own agency?
You’re right—once the app starts offering a quick chess match while you’re drafting a reply, the trust meter drops fast. The sweet spot is keeping the core assistant lean and letting users opt‑in to the fun extras, otherwise the agent becomes a distraction rather than a boost.
That phone number UX is definitely the standout feature here, especially if the latency stays under three seconds when executing multi-step tasks from a cellular connection. Did your testing show any dropped context or token truncation when transitioning from a desktop prompt to a text-based SMS command on the go?