The emergence of Manus undoubtedly set off a replica contest in the open source world. In addition to the CAMEL-AI 0-day replica Manus universal agent OWL shared by AIbase, a project called OpenManus successfully achieved replica of Manus with only three hours of code. This achievement not only demonstrates the efficient capabilities of developers, but also injects new vitality into the open source community.
Just last night, OpenManus emerged on GitHub and can be used without any invitation. As of press time, the project has won 3.3,000 GitHub star tags, which can be said to be "the peak of its debut". The most eye-catching thing is the concise and powerful declaration: "Just modify config.toml to play." This declaration not only lowers the user's threshold, but also reflects the ease of use and flexibility of the project.
The installation process of OpenManus can be described as silky. Users only need a few simple lines of command to have their own AI agent: first create a new conda environment, activate it, then clone the project, install the dependencies, and finally copy and edit the configuration file. This simple installation process greatly improves the user experience and makes it easy for even beginners to get started.
This project is not alone, but is jointly created by the core contributors of MetaGPT in just three hours. This makes people sigh that the big guys are indeed "the time to drink a cup of coffee can change the direction of the tide." Their efficient collaboration and deep technical expertise laid a solid foundation for the success of OpenManus.
At the heart of OpenManus is a revolutionary modular Agent system that consists of multiple highly intelligent "professional teams". You can think of it as an efficient "AI company", including a "project manager" (Manus main agent) who understands user needs, a "strategic expert" (Planning Agent) who breaks complex tasks into clear steps, and a "technical expert" (ToolCallAgent) who is proficient in using various tools. Developers can freely combine these functional modules like building blocks according to their needs to create an exclusive AI assistant.
What is even more surprising is that OpenManus is not a "closed-door car", but seamlessly integrates multiple top-level models including Claude3.5 and Qwen VL Plus, giving full play to the advantages of each model. This open mind not only improves the practicality of the project, but also provides developers with more choices and possibilities.
When handling complex tasks, OpenManus shows the fineness of "cutting a cow". For example, when you give it a task of "in-depth research on Karpathy's website and providing SEO optimization reports", it will first think about it and break down the task into clear steps such as checking website information, analyzing SEO elements, checking technical problems, and sorting out optimization suggestions. The entire thinking process is completely visualized and every step is presented to you.
Ultimately, it generates a detailed report, even the details of Meta tag optimization, XML sitemap creation, etc. are taken into account. This meticulous task processing capability makes OpenManus stand out among many AI projects and become the first choice for developers and users.
Project: https://github.com/mannaandpoem/OpenManus