Moonshot launches Kimi Work internal testing, a general local agent for knowledge workers
The large model application space in China is once again seeing a fundamental shift in productivity tools. On June 3, AI startup Moonshot announced that its general-purpose local agent product for knowledge workers, Kimi Work , has entered internal testing. This feature will launch alongside the latest Mac and Windows desktop test versions of Kimi.
Positioned as an efficiency tool that "moves from a conversation assistant to a work executor," Kimi Work is built on Moonshot's Kimi Code. Driven by advances in underlying capabilities, the application features a powerful local agent infrastructure. It not only enables AI to run scheduled tasks in the user's local computer environment but also supports the installation and independent use of various operational skills (Skill).

In terms of professional skill reserves, the new product fully inherits the strengths of the online Kimi Agent, offering high-frequency professional skills like website building and PPT creation right out of the box. Additionally, the system integrates deeply with professional-grade databases covering verticals such as finance, research, and law, and includes the Kimi WebBridge solution that supports browser invocation, greatly expanding the boundaries of local AI collaboration.
The most notable feature is its "teamwork capability" for handling complex, long-duration tasks. Kimi Work now supports Agent clusters for the first time. The system can autonomously create and schedule virtual expert teams of up to 300 sub-agents based on the complexity of the user's input task. Through parallel collaboration and division of labor among multiple agents, it helps users manage complex, large-scale projects that are more time-consuming and cross multiple applications with diverse technical requirements.

In terms of actual interaction experience, this update has completely broken through traditional development and operational barriers. Users don't need to understand any code, open a terminal, write command lines, or configure the underlying environment. They simply describe the final goal in natural language, and Kimi Work automatically breaks down the task, runs processes in parallel, calls tools across systems, and even creates and organizes folders on its own.
Ultimately, the system delivers highly completed documents, spreadsheets, PPTs, and other core work products directly to users, fully covering knowledge-intensive work scenarios such as office tasks, deep research, content creation, and daily data organization. With the implementation of local agents, AI is truly evolving from a simple "chatting" generative dialog box into a versatile digital employee capable of doing real work in the computer operating system on behalf of humans.
Related article
Indian Tech Tycoon Invests $30M in AI Rival to Microsoft Office
Serial entrepreneur Bhavin Turakhia is investing $30 million of his own capital, betting that the enterprise AI sector still has room for new players. His latest startup, Neo, operates on a core belief: legacy workplace software cannot simply be patc
Former OpenAI Chief Scientist Ilya’s SSI Unveils First Model
AI has achieved another major milestone. Following his departure from OpenAI, former chief scientist Ilya Sutskever established Safe Superintelligence Inc. (SSI), which has recently unveiled details regarding its inaugural model. Reports from oversea
Lovable Leads Atech's Seed Round as AI Ambient Coding Officially Enters the Hardware Field
On May 14, 2026, AI application development platform Lovable announced its participation in the $800,000 seed funding round for Danish hardware startup Atech. Led by Lovable, the round attracted top-tier venture capital firms including the a16z Scout
Related Special Topic Recommendations
Comments (0)
0/500
The large model application space in China is once again seeing a fundamental shift in productivity tools. On June 3, AI startup Moonshot announced that its general-purpose local agent product for knowledge workers,
Positioned as an efficiency tool that "moves from a conversation assistant to a work executor,"

In terms of professional skill reserves, the new product fully inherits the strengths of the online Kimi Agent, offering high-frequency professional skills like website building and PPT creation right out of the box. Additionally, the system integrates deeply with professional-grade databases covering verticals such as finance, research, and law, and includes the Kimi WebBridge solution that supports browser invocation, greatly expanding the boundaries of local AI collaboration.
The most notable feature is its "teamwork capability" for handling complex, long-duration tasks.

In terms of actual interaction experience, this update has completely broken through traditional development and operational barriers. Users don't need to understand any code, open a terminal, write command lines, or configure the underlying environment. They simply describe the final goal in natural language, and
Ultimately, the system delivers highly completed documents, spreadsheets, PPTs, and other core work products directly to users, fully covering knowledge-intensive work scenarios such as office tasks, deep research, content creation, and daily data organization. With the implementation of local agents, AI is truly evolving from a simple "chatting" generative dialog box into a versatile digital employee capable of doing real work in the computer operating system on behalf of humans.
Indian Tech Tycoon Invests $30M in AI Rival to Microsoft Office
Serial entrepreneur Bhavin Turakhia is investing $30 million of his own capital, betting that the enterprise AI sector still has room for new players. His latest startup, Neo, operates on a core belief: legacy workplace software cannot simply be patc
Former OpenAI Chief Scientist Ilya’s SSI Unveils First Model
AI has achieved another major milestone. Following his departure from OpenAI, former chief scientist Ilya Sutskever established Safe Superintelligence Inc. (SSI), which has recently unveiled details regarding its inaugural model. Reports from oversea
Lovable Leads Atech's Seed Round as AI Ambient Coding Officially Enters the Hardware Field
On May 14, 2026, AI application development platform Lovable announced its participation in the $800,000 seed funding round for Danish hardware startup Atech. Led by Lovable, the round attracted top-tier venture capital firms including the a16z Scout





Home






