Yichao 'Peak' Ji

Hi! I'm Peak from Manus AI. Actually, it's not that complicated - the sandbox is directly accessible to each user (see screenshot for method). Specifically: * Each session has its own sandbox, completely isolated from other sessions. Users can enter the sandbox directly through

402K

Yichao 'Peak' Ji

@peakji

Mar 10, 2025

Actually, Manus doesn't use MCP. We were more inspired by my friend

@xingyaow_

's work: openreview.net/forum?id=jJ9Bo. While we haven't fully adopted CodeAct, this work provided 3 crucial insights: * Coding is not the ultimate goal, but rather a universal approach for solving general

Quote

Thomas Wolf

@Thom_Wolf

Mar 10, 2025

Manus Context Protocol wen?

Feeling so much love from the community today! Manus launched with rumors flying, and we panicked. But as more people tried it (crashes and all), the truth spoke for itself. People I quietly admired reached out to help—it felt unreal. Grateful beyond words for this support.

Important Notice Regarding Manus's X Account Suspension Our official X account (@ManusAI_HQ) was unexpectedly suspended yesterday. We're actively working with X's support team to resolve this matter. Preliminary observations suggest the suspension might relate to third-party

The media could not be played.

Good news: We've nearly doubled @ManusAI_HQ 's context limit & beefed up our sandbox hardware. Failure rate down dramatically!

Bad news: With lower failure rate, now sessions run longer, system's sweating bullets, and failures are climbing back up... Had to throttle things

The Jevons Paradox in AI is absolutely real. Over the past two years, we've been building chatbots and have witnessed the inference costs of models with the same level of intelligence decrease by 50 to 100x. Last year, when we believed that the efficiency was sufficient to

Replying to

and

We use Claude and different Qwen-finetunes. Back when we started building Manus, we only got Claude 3.5 Sonnet v1 (not long-CoT, aka reasoning tokens), so we need a lot of auxiliary models. Now Claude 3.7 looks really promising, we are testing internally, will post updates!

Replying to

Co-founder of Manus AI here! Thanks for your interest in Manus

@heyBarsee

, but this video is definitely NOT Manus

. Our official account is @ManusAI_HQ , and Manus is a web-based AI agent, like OpenAI Operator/DeepResearch, not a VNC for smartphones.

Replying to

and

We have a lot of fine-tuned models in our company. Some Manus' planning technique originated from this model I've open-sourced last October:

peakji/steiner-32b-preview · Hugging Face

Thanks, Rowan! And we just had our Rowan moment.

Quote

Rowan Cheung

@rowancheung

Mar 8, 2025

I think China's second DeepSeek moment is here. This AI agent called 'Manus' is going crazy viral in China right now. Probably only a matter of time until it hits the US. It's like Deep Research + Operator + Claude Computer combined, and it's REALLY good.

We are back! This is the ONLY official account of Manus

Just to be clear: - Manus has never been involved with cryptocurrency projects, token issuance, or blockchain initiatives - Any similarly named cryptocurrency ventures claiming association with us are fraudulent

Quote

Manus

@ManusAI

Mar 6, 2025

Would you like ask Manus to complete a task for you? Reply to this tweet with a task you'd like Manus to handle. Our team will run your request with Manus and share the results with you. Whether it's research, content creation, data analysis, or something creative - let's see

Quote

jack

@jack

Mar 9, 2025

excellent x.com/ManusAI/status…

Today a16z released the latest AI Top 50 list. As a small startup, it's truly an honor that we made it with not just one, but two products. The company is charging toward the $100M milestone, and I'm about to enter my 15th year in entrepreneurship. In the beginning, I thought

I feel we need a place for everyone to share their Manus creations.

Quote

@_akhaliq

Mar 10, 2025

Got access to Manus AI prompt: make a three.js endless runner game

Wide Research is our latest exploration in agent-agent collaboration. Built on our large-scale virtualization infrastructure, Manus can now autonomously dispatch a team of homogeneous Manus agents to work in parallel and aggregate the results. While building AI agents, we've

Quote

Manus

@ManusAI

Aug 1, 2025

Introducing Wide Research

The all new web dev experience are now fully rolled out and available to all users. Behind it is still a unified general agent architecture, where every capability works together seamlessly: researching deeply to create sites, analyzing collected data, turning those insights

Quote

Manus

@ManusAI

Oct 17, 2025

Introducing Manus 1.5 Faster, better quality results. Unlimited context. Build full-stack web apps, with real AI features, backends, user logins, custom domains and analytics. Run your biz, start your side hustle, or just have fun. If you can dream it, Manus can build it.

Replying to

and

Because... Manus started before the introduction of Model Context Protocol

Replying to

and

Relying on text alone loses a lot of information, here are two examples: 1. Interacting with web apps requires understanding of layouts; 2. For tables, 'merged cells' cannot be properly described using text.

Well Vasek, you brought it up first, so I can't be blamed now!

I was holding back from tagging you until Manus became more stable... But no worries everyone, any issues are totally on our end -

@e2b

is an amazing technology!

Quote

Vasek Mlejnsky

@mlejva

Mar 11, 2025

If Manus was mentioned on cnbc showing the Manus's computer which is @e2b sandbox does it mean e2b was transitively on CNBC?

Thank you

for the support! Always proud to be part of the

@huggingface

community.

Quote

clem

@ClementDelangue

Mar 9, 2025

I was chatting with @peakji, one of the cofounders of @ManusAI_HQ, who told me he was on @huggingface (very cool!). He shared an interesting insight which is that agentic capabilities might be more of an alignment problem rather than a foundational capability issue. Similar to

Thinking of you guys, while the rest of us are squashing bugs back in Singapore.

Quote

hidecloud

@hidecloud

May 22, 2025

We were excited to meet with @satyanadella and the team in Seattle last week - and are excited for our partnership ahead! x.com/ManusAI/status…

Grateful to be named in this year's MIT TR35 at 33. Fourteen years ago, I was fortunate to be on Forbes 30 Under 30 at 19. The past 14 years have been about learning, failing, and striving. Innovation is a journey, not a moment.

Quote

MIT Technology Review

@techreview

Sep 11, 2025

Yichao “Peak” Ji developed Manus, one of the buzziest AI apps of the year, in the latest project that blends his technical prowess with killer consumer instincts. We named him as one of this year’s 35 Innovators Under 35. trib.al/HJ14S5c

Just had a great conversation with

@paulharapin

at Stripe Tour Singapore. It's amazing to see Manus grow from launch in March to a $90M revenue run rate, with $100M just around the corner. Grateful for Stripe's strong support along the way!

Replying to

I've also recorded my "human Chain-of-though" in a blog post:

medium.com

A Small Step Towards Reproducing OpenAI o1

Progress Report on the Steiner Open Source Models

Forgot to include a key lesson in the blog: Context engineering can also overfit - not just to specific model families, but also to today's model limitations via premature optimization. At Manus, we never commit to an architecture based on static benchmarks. Instead, we treat

Quote

Yichao 'Peak' Ji

@peakji

Jul 19, 2025

After four overhauls and millions of real-world sessions, here are the lessons we learned about context engineering for AI agents: manus.im/blog/Context-E

Replying to

and

Hey

, I'm Peak from Manus. I've just wrote a tweet to clarify:

Quote

Yichao 'Peak' Ji

@peakji

Mar 10, 2025

Replying to @jianxliao and @browser_use

Also, there are a bunch of fake Manus apps on the App Store... This is the only real one: manus.onelink.me/2Tdk/g6ttrj4c Please be careful of fake apps, fake websites, fake accounts, fake emails, fake news, fake invite codes, and fake meme coins!

Quote

Manus

@ManusAI

Mar 31, 2025

We have noticed an increase in phishing attempts impersonating official communications from Manus. Only trust emails from manus.im & manus.ai.

Double-check the sender.

Don't click suspicious links.

Protect your email privacy on social

Replying to

and

We’re working hard to scale up! The response to this closed beta has been way more than we expected.

Honestly, I'm surprised too — that's a legacy Manus from a few versions back lol...

Quote

Zephyr

@zephyr_z9

Nov 3, 2025

LOL How the hell is Manus No. 1?? x.com/vbingliu/statu…

Happy to see Manus hitting SOTA in

@scale_AI

@cais

' new benchmark, but that 2.5% on the Y-axis says we've still got a loooong way to go

Quote

Dan Hendrycks

@hendrycks

Oct 30, 2025

Can AI automate jobs? We created the Remote Labor Index to test AI’s ability to automate hundreds of long, real-world, economically valuable projects from remote work platforms. While AIs are smart, they are not yet that useful: the current automation rate is less than 3%.

What's going on here

, aren't we supposed to be best buddies?

Quote

Olivia Moore

@omooretweets

Aug 29, 2025

IMO, this may be the most interesting data from our @a16z top 100 AI apps report. We looked at "Affinity Scores" for the top 6 most popular LLMs. Ex. what other apps are you most likely to have if you're a Claude or Perplexity user? This gave us mini-profiles of AI x.com/omooretweets/s…

5.8K