Moonshot AI’s Kimi Work Brings 300 AI Brokers to Your Desktop

Moonshot AI has launched Kimi Work, a downloadable desktop agent for macOS and Home windows that lives in your machine, reads your information, drives your browser, and runs jobs on a schedule. The Beijing-based firm—considered one of China’s so-called AI Tiger startups—introduced the product this week alongside free downloads, with the app at the moment in inner testing.

The corporate’s WebBridge extension, launched a month in the past, already let brokers drive your actual Chrome or Edge session regionally. Kimi Work takes that concept and turns it right into a full desktop product.

The pitch is straightforward. Most AI instruments from AI suppliers right now reside within the cloud. You ship a immediate, a server someplace spins up, a sandboxed browser clicks round, and also you get a outcome. Kimi Work does the other.

Kimi Work, being a neighborhood app put in in your pc, has entry to your native information and is ready to work together together with your pc as a substitute. It will possibly manipulate your PDFs, manage your desktop, pull inventory knowledge out of your browser, compile a report in HTML and e-mail it to you, and so forth.

In apply it’s the equal of what OpenClaw or Hermes attempt to do, however totally developed and built-in within the Kimi ecosystem with particular options that different options don’t provide.

A type of issues is Agent Swarm, which lets Kimi Work spin up a number of sub-agents in parallel—as much as 300 of them, every dealing with a distinct slice of a activity.

It’s additionally built-in with WebBridge, which palms the agent management of your actual browser utilizing Chrome DevTools Protocol, the identical interface builders use for debugging; your logged-in classes and cookies keep in your machine.

A built-in Cron engine schedules duties on day by day, hourly, or conditional triggers, with a “Maintain Pc Awake” toggle for in a single day jobs. And a neighborhood file layer lets the agent learn folders you mount and run Python within the background.

The app additionally ships with native market knowledge for A-shares, Hong Kong shares, and U.S. equities pre-integrated—no API setup required. Completed analysis converts on to PowerPoint or Excel.

Below the hood, Kimi Work runs on Kimi K2.6, in line with those that have been capable of take a peek. (We’ve but to check this ourselves). K2.6 is a roughly one-trillion-parameter mixture-of-experts mannequin Moonshot launched on April 20. Combination of specialists is an structure that retains solely a fraction of its parameters lively at any second; K2.6 prompts round 32 billion per token whereas carrying a 256K-token context window. (For reference, tokens are the smallest quantity of knowledge an AI can course of whereas parameters are all of the numerical values that retailer all of the data and traits a mannequin has.)

That context window issues: It means the agent can maintain an infinite quantity of knowledge in thoughts throughout an extended, multi-step workflow with out forgetting what it began on.

You probably have doubts about Kimi’s high quality as an AI mannequin, think about that this was the bottom utilized by the favored AI code editor Cursor to advantageous tune its personal specialised coding massive language mannequin, “Composer 2.”

The misunderstanding value clearing up first

“Native” in Kimi Work refers to the place the actions occur—your machine—not essentially the place the AI mannequin runs. The K2.6 mannequin inference can nonetheless route by Moonshot’s API within the cloud, even whereas the file reads, browser clicks, and Python executions occur regionally.

If you would like full on-device inference, the weights can be found on Hugging Face underneath a Modified MIT License—however a trillion-parameter mannequin calls for critical {hardware} most residence customers haven’t got.

The privateness image can also be extra nuanced than “native equals protected.” As a result of WebBridge drives your precise logged-in browser, it will probably contact your checking account, your e-mail, and your organization’s inner instruments. Researchers at UC Riverside warned in Might that AI brokers typically perform duties with out recognizing when their actions are dangerous—a conduct they known as “blind goal-directedness.”

Moonshot contains an “ask earlier than performing” mode that requires your approval earlier than any file is modified or code is run. That is the suitable default to depart on, nevertheless it’s nonetheless removed from being 100% protected.

The brewing conflict within the agentic AI period

The desktop agent race has gotten crowded quick. Anthropic’s Claude has supplied full-desktop pc use since late 2024. OpenAI shipped Codex Background Pc Use for macOS in April 2026, working brokers in parallel desktop classes. Google’s Gemini pc use—descended from Challenge Mariner—focuses on browser workflows. Microsoft’s Copilot Studio added computer-use in Might 2026, geared toward enterprise automation and utilizing each OpenAI and Anthropic fashions underneath the hood.

But it surely looks like as a substitute of being constrained to a single supplier, customers need some flexibility. That is the place instruments like OpenClaw, Hermes, or NanoClaw enter within the sport. They’re mainly native platforms that configure your AI brokers utilizing any LLM over API.

The distinction with Kimi Work is the local-first design paired with a 300-agent swarm. Most rivals both run all the things in a cloud sandbox—which might’t contact actual logged-in classes—or provide desktop management with out coordinated parallel brokers. Kimi Work does each. The tradeoff is that this: When your laptop computer is closed, duties cease. Moonshot’s personal cloud product, Kimi Claw, runs 24/7 with out your machine.

The app is a free obtain. Significant agent options require a paid plan. Moonshot’s Moderato tier begins at $19/month and contains K2.6, Deep Analysis, and Kimi Code entry.

The Agent Swarm with restricted sub-agents unlocks at Allegretto ($39/month), whereas the complete 300-agent swarm and highest-volume skilled workflows require the Allegro ($99/month) or Vivace ($199/month) tiers for individuals who actually want 300 brokers.

Downloads for macOS (Apple Silicon) and Home windows are reside at kimi.com, with the interior testing section that means some options should shift earlier than a wider rollout.