Today, the surge of Swarms has once again caught people's attention, and the entire community is buzzing with two hot topics: the rumored 'anxiety' of Shaw, the founder of AI16Z, and the suspected infringement of Swarm multi-agent framework by Sama from OpenAI. Some speculate that the behind-the-scenes driver behind this exciting pump may be the emergence of the AI Agent based on Mcs. This Agent not only answers medical common sense questions but is also known as the most user-friendly and practical deliverable product in the Swarms architecture. Its founder, Kye Gomez, a 'genius teenager' who dropped out of high school at the age of 20, spent three years completing the multi-agent coordination framework Swarms, running 45 million agents, and serving fields such as finance, insurance, and medical care, making it a hardcore powerhouse.

Roller Coaster Trend

After the Swarms token was launched on December 18th, it quickly surged to a peak market value of $74.2 million on the 21st, but unfortunately the good times didn't last long, and the market value plummeted to only about $6 million, like a roller coaster ride.

Next, it fluctuated around 13 million US dollars until the 27th, when it started to counterattack, pushing up from a low of 12 million US dollars to 30 million US dollars, and then surged nearly three times to nearly 70 million US dollars, almost breaking the previous high. Today's trading volume is also considerable, directly soaring to 60.8 million US dollars. This stimulating market trend has made netizens feel like they are experiencing a roller coaster ride in the currency circle.

The Future Password Behind Swarms

Behind the rollercoaster-like price movements, there are multiple AI agents working together like a closely coordinated team, dividing the work and collaborating to tackle complex challenges. The collective intelligence and coordination capabilities far exceed the limitations of individual agents, which is the goal pursued by Kye Gomez's Swarms project. However, creativity and ideas alone are not enough. What truly makes all this possible is the core technology launched by Swarms - Swarm Node (SNAI). It can be said that SNAI is the 'neural center' of the AI agent world, providing powerful support and assurance for seamless cooperation between agents.

"Genius Boy" Founder

Behind the core founder of Swarms, Kye Gomez, is hailed as a 'genius youth' in the field of artificial intelligence, demonstrating astonishing hardcore strength at just 20 years old. Despite dropping out of high school, he developed the multi-agent coordination framework Swarms in just three years, successfully running 45 million AI agents and providing high-quality services to multiple industries such as finance, insurance, and healthcare, demonstrating the strength of the youth.

In his research on autonomous and collaborative AI agents, he has not only developed 'super-efficient SSM + MoE model' and 'hybrid flow model', but also deeply explored the potential of AI alignment in the fields of biology and nanotechnology. In fact, Swarms is just one of his many excellent projects. The young man's strength is hidden and after in-depth understanding, it is discovered that he has many other outstanding projects.

For example, Agora serves as an open-source AI research lab, focusing on the integration of AI with biology and nanotechnology. Pegasus is its exploration in the field of natural language processing and embedding models, and it has also participated in the open implementation of AlphaFold3. Kye's resume and achievements all indicate the rise of a true technological innovator.

Swarms AI Agent Orchestration Framework and Core Features

Next, we will start to analyze the Swarms project of the genius teenager. The project aims to develop and promote an enterprise-ready multi-agent orchestration framework. In simple terms, the core function of Swarms is to enable multiple AI agents to work together like a team, using collective intelligence to solve complex problems. It not only supports seamless integration with external AI services and APIs to extend functionality, but also provides agents with almost unlimited long-term memory to enhance contextual understanding, while allowing for custom workflow. For enterprise-level requirements, Swarms possesses high reliability and scalability, and ensures optimal performance through automatic optimization of language model parameters. In this way, Swarms can leverage the collective intelligence of agents to more easily tackle complex challenges than individual agents.

The Swarms project stands out with its powerful technical barriers and market performance. Its AI agent orchestration framework has been operating steadily for nearly three years and has provided efficient solutions to many enterprises on its official website. From data processing to customer service and report generation, Swarms has significantly improved business efficiency and significantly reduced operating costs through automation, demonstrating its strength. As an open-source project, Swarms has also attracted great attention in the developer community, with over 2.1K stars on GitHub and gaining the wisdom and support of many developers, which confirms the maturity and innovation of the technology.

SNAI

It seems that netizens on Twitter all agree that the next stage of AI agents is Agent Swarms, which achieve more efficient work through communication and collaboration among multiple agents. This approach allows agents from different frameworks to communicate with each other and leverage their specialized advantages to perform better in specific tasks and scenarios.

Swarm Node (SNAI) is an auxiliary tool for implementing Agent Swarms, a serverless infrastructure designed specifically to support the concept of Swarm. SNAI solves all the technical challenges of running AI agents, allowing users to easily deploy, coordinate, and manage agents through Python scripts without worrying about hardware and infrastructure costs. It also supports chain interaction, scheduling, and multi-language operations, providing new possibilities for small creators who cannot run agents around the clock or lack hardware support.

Users do not need to pay for server fees, only for the actual execution time used, which makes SNAI more efficient than other subscription-based solutions. The uniqueness of SNAI is that its agents are not isolated, but can collaborate "chained" to form a Swarm.

The role of Swarm is to assign tasks to different agents, each focusing on a specific task and passing the results to the next agent. Through REST API and Python SDK, other applications can easily integrate SNAI, and users can flexibly coordinate the behavior of their Swarm (for example, when to run and which data to use).

But that's not all. With the SNAI framework still in the early stages of development, there will be new features in the future, including data storage (a mini cloud database that allows agents to share selected data), task scheduling (running agents at specific times), and agent library (ready-made agents created by the community for running, customization, and optimization). In addition, SNAI will also achieve multi-language compatibility. Currently, a Python client that simplifies API operations has been provided, and there are plans to support the deployment of agents written in languages such as Go, Rust, TypeScript, C#, and PHP. The community has started developing a TypeScript client, and more languages will be supported in the future.

Only this week, there have been over 500 builds - these 'dependencies' are used to optimize the efficiency of AI agents' execution. With over 10,000 executions - instances where the agent starts and then pauses, SNAI only charges for active running time, greatly improving the flexibility of agent operations.

The core features of SNAI include supporting agentless serverless operation, allowing developers to integrate agents into code libraries, achieving agent chain collaboration and interactive coordination, while adopting a pay-as-you-go model, greatly reducing infrastructure costs, and lowering the threshold for entering AI agent infrastructure.

Versus AI16Z

Swarms and AI16Z both have significant influence in the field of AI agents, and they have been constantly debated on Twitter. Although there are some similarities, they differ in technical architecture and applications. Swarms adopts a collaborative 'team' framework, where multiple AI agents work together to complete complex tasks and improve efficiency. In contrast, AI16Z's Eliza framework is more like a flexible 'coordinator', emphasizing support for multiple platforms and integration of multiple models, enabling rapid adaptation in various scenarios. The following compares the two agents from two aspects.

Technical Framework and Architecture

Swarms is like a disciplined team. The Swarms framework supports multiple AI agents working together. With autonomy, modularity, and scalability, AI agents can collaborate efficiently, excel at breaking down complex tasks, and accomplish "clear division of labor and seamless coordination". On the other hand, AI16Z's Eliza framework is more like an all-round coordinator, focusing on running on multiple platforms and integrating multiple models, while emphasizing interaction between agents and having its own characteristics in flexibly adapting to various scenarios.

AI Models and Applications

In terms of AI models and applications, Swarms focuses more on how to cleverly integrate existing AI models, improve enterprise-level automation and team efficiency through task orchestration and team collaboration. It is more like a fine commander, good at allocating multiple forces properly, and focuses on 'how to do better'. The AI16Z Eliza framework provides developers with greater freedom, supporting various AI models (such as Llama, Claude), giving applications more flexibility, and being able to deal with various scenarios from social media management to financial transactions, bringing a versatile solution. One focuses on collaboration, the other emphasizes diversity, both are equally innovative in application, and each has its own advantages.

Overall, Swarms and AI16Z are exploring the future of AI agents in radically different ways. Swarms is more like a disciplined team, impressing enterprise users with efficient collaboration and hardcore technology, while AI16Z's Eliza is more like a versatile free player, demonstrating infinite potential with flexible adaptation and diverse scenarios. In fact, both have their own strengths. In this competitive era, the story of AI agents is just beginning. Who will stand out in this competition? We wait and see!