Introducing Manus: The General AI Agent
Hi, I’m Peak from Manus AI.
For the past year, we’ve been quietly building what we believe is the next evolution in AI. And today, we’re launching an early preview of Manus, the first general AI agent. This isn’t just another chatbot or workflow; it’s a truly autonomous agent that bridges the gap between conception and execution. While other AI stops at generating ideas, Manus delivers results. We see it as the next paradigm of human machine collaboration and potentially a glimpse into AGI. Now, let me show you Manus in action across three completely different tasks.
Let’s start with an easy one. In this example, we ask Manus to help screen resumés. I’ve just sent Manus zip file containing 10 resumé documents. Since each Manus session has its own computer, it [can] work like a human: first, unzipping the file, then browsing through each resumé page by page and recording important information to documents.
Manus works asynchronously in the cloud, which means you can close your laptop anytime and Manus will notify you when everything is complete. Of course, you can also give Manus new instructions at any time. Here, I’ve sent Manus five more resumés. After carefully reading all 15 resumés, Manus provides its ranking suggestions along with candidate profiles and evaluation criteria as supporting materials.
This is pretty good, but I’d prefer a spreadsheet. Let’s have Manus create one. Manus has its own knowledge and memory so I can teach Manus that the next time it handles a similar task, it will deliver a spreadsheet right away.
In this example, we have Manus conduct some research. It needs to filter New York properties based on multiple criteria. For complex tasks, Manus first breaks them down and creates a to-do list. Manus begins by searching and carefully reading articles about the safest neighborhoods. Then Manus researches middle schools in New York. Next, Manus writes a Python program to calculate my budget. Based on my budget, Manus filters listings on real estate websites. Finally, combining all the information gathered, Manus write a detailed report and compiles all the resources.
In this example, we have Manus perform a correlation analysis between stocks. For professional data, Manus can access authoritative data sources through APIs. After validating the acquired data, Manus begins writing code for data analysis and visualization. For Manus, coding isn’t necessarily the goal but rather a universal tool for solving problems. It looks like Manus has completed the data analysis and visualization, but interactive data visualization is even cooler, so I asked Manus to create a website based on this data. With my permission, Manus deploys the finished website online and provides me with a sharable link. Let’s see what Manus has created.
What you’ve just seen is just a small sample of what Manus can do. In fact, on benchmarks designed to evaluate general AI assistants, an early checkpoint of Manus has already achieved state-of-the-art performance, and it’s only getting better. Beyond benchmarks, Manus has been solving real-world problems on platforms like Upwork and Fiverr and has proven its capabilities on Kaggle competitions.
This wouldn’t be possible without the amazing open-source community, which is why we’re committed to giving back. Manus operates as a multi-agent system powered by several distinct models, so later this year, we’re going to open source some of these models specifically post-trained for Manus, inviting everyone to explore this agentic future together.返回搜狐，查看更多
