@DeRonin_: holy moly.. kimi work just shipped.. it runs 300 agents in parallel. locally. on your own laptop this is going to chang…
Summary
Kimi Work is a desktop AI agent that can run 300 agents in parallel locally, with browser automation and scheduled tasks, aiming to boost productivity for solo knowledge workers and agencies.
View Cached Full Text
Cached at: 06/08/26, 09:27 PM
holy moly..
kimi work just shipped..
it runs 300 agents in parallel. locally. on your own laptop
this is going to change how i run my solo agency
[ for context: i already run my agency on kimi ]:
$40k MRR solo agency. zero employees generous rate limits mean i can fan out without throttling rest of the industry still defaults to frontier models. bleeding margin
[ how i route work between models ]:
Kimi 2.6 → 90% production (code, content, automations, debugging) → ~240/mo Opus / GPT-5 → 10% high-stakes (architecture, security, anchor clients) → ~110/mo Haiku / local → cleanup (lint, format, boilerplate) → $0
yeah, this is going on my machine tonight
[ what i’m immediately doing with it ]:
300 parallel agents for creator research before client launches (used to eat a full afternoon) browser use to actually click through X, LinkedIn, IG, YouTube and check content performance for me memory system remembering every client’s voice and project history (no more re-briefing every session) all running locally, no rate limits, no API spend on the parallel work
the browser use is the part that broke my brain
paired with the WebBridge extension, the agent literally scrolls, clicks, types through real websites for you
link if you want to mess with it: https://kimi.com/products/kimi-work…
Kimi Work: Next-Gen Desktop AI Agent for Knowledge Workers
Source: https://www.kimi.com/products/kimi-work

The AI Desktop for Knowledge Work
Your intelligent local agent
Deeply connected to your local files. Capable of browser automation. Running around the clock. Built for maximum productivity
Set It & Forget It: 24/7 Automation
Your workflow never sleeps. Powered by a robust built-in Cron engine, Kimi Work automates your repetitive tasks. Whether it’s an early-morning LLM Agent call to draft daily briefings, or a midnight Python script to process massive datasets, Kimi runs quietly in the background, exactly on time.
WebBridge: Your Autonomous Web Agent
Give Kimi a goal, and watch it navigate the internet like a human. Powered by WebBridge, it autonomously browses across tabs, extracts critical data, and executes multi-step web tasks. You provide the prompt, Kimi handles the clicks, scrolls, and research.
Agent Swarm & Instant Office Creation
Tackle complex problems with the power of Swarm Intelligence. Kimi automatically coordinates multiple specialized agents to break down and solve multi-layered tasks simultaneously. Once the research is complete, seamlessly convert insights into professional PowerPoint decks or Excel sheets in seconds.
Built for Finance: Native Global Market Data
Meet your desktop chief analyst. Kimi Work comes pre-integrated with deep data sources for A-shares, HK stocks, and US equities. Skip the complex API setups—instantly pull earnings reports, analyze market anomalies, and reconcile spreadsheets through natural conversation. Gain a crucial edge in a fast-paced market.
Get Started with Kimi Work
Think, create, and execute, all from your desktop. Kimi Work brings intelligence to every step of your workflow
Mac Meets Kimi
Windows Meets Kimi
FAQ
While the Kimi web app is perfect for quick chat and queries, Kimi Work is a Local Agent designed for deep workflows. It mounts your local folders, navigates the web autonomously via WebBridge, runs Python code in the background, and executes scheduled tasks. It’s a system-level digital employee.
You have absolute control over your files. We’ve built in an Ask before acting (Yolo mode off) safeguard. Before Kimi modifies, overwrites, or runs code within your local directories, it will prompt you for explicit authorization. Nothing happens without your consent.
WebBridge gives Kimi the ability to use a browser like a human. You can tell it to “check the latest Fed announcement on their website and summarize it” or “scrape historical data for a specific stock and save it to my local Excel.” It clicks, scrolls, and extracts data autonomously, saving you hours of manual work.
Our Cron scheduler supports LLM Agent Calls, Python/Shell executions, and more. You can trigger tasks daily, hourly, or conditionally. To ensure tasks run seamlessly overnight, simply toggle the “Keep Computer Awake” option in your settings.
Kimi.ai (@Kimi_Moonshot): Meet Kimi Work - a local AI agent on your desktop that does the work for you.
🔹Native agent swarm: Up to 300 AI agents running in parallel on your local machine. 🔹Browser use: Paired with WebBridge extension, your agent will navigate websites in your browser: search, scroll,
Similar Articles
@heyshrutimishra: MY MIND IS BLOWN Kimi just launched something called K2.6 Agent Swarm. 300 agents running in parallel. I had to try it,…
Kimi released K2.6 Agent Swarm, enabling 300 parallel AI agents that generated an 80+ slide investment thesis on humanoid robotics from a single prompt.
@xiaohu: Recently, AI tools seem to have shifted from Coding to Working. Kimi just released something new: Kimi Work, inheriting the core features of Kimi Code and the professional Skills of Kimi Agent for website building, PPT, etc. Same…
Kimi launched a new AI office product, Kimi Work, which inherits the capabilities of Kimi Code and Kimi Agent, enabling up to 300 agents to collaborate simultaneously on tasks, aiming to provide workers with a command-line-free automated office experience.
@DeRonin_: https://x.com/DeRonin_/status/2062301065312407891
A detailed breakdown of how the author runs a solo AI automation agency generating $40k MRR with no employees, relying on AI models like Kimi 2.6 for delivery and achieving over 90% margin.
@0xMovez: Meet Kimi K2.6 Agent Swarm Highlights: Swarms, elevated - 300 parallel sub-agents × 4,000 steps per run (up from 100 / …
Kimi K2.6 introduces a powerful agent swarm feature that allows 300 parallel sub-agents across 4,000 coordinated steps, enabling automated research and file generation. The system includes a self-improving loop verified by Opus 4.8, making it a significant upgrade over the previous version.
@kirillk_web3: do you understand what Kimi K2.6 just dropped. open-source. free. 1 trillion parameters. here's the part nobody is talk…
Kimi K2.6 is released as a free, open-source 1-trillion parameter model capable of running 300 parallel agents for continuous execution, reportedly outperforming Claude Opus 4.6 on SWE-Bench Pro tasks.