Moonshot AI Launches Kimi Work, a Local Desktop Agent Reportedly Running on Kimi K2.6 With a 300-Sub-Agent Agent Swarm
重點摘要
Moonshot AI has introduced Kimi Work, an AI agent that runs on your own desktop. The Beijing-based AI entity announced it this week along with downloads for macOS and Windows. Kimi Work reads local files, drives your real browser, and runs scheduled tasks. It targets knowledge workers whose bottleneck is access to files and live sessions. Most agent tools of the past two years ran in the cloud. You type a goal, a remote server spins up a sandbox, and a hosted browser acts. Kimi Work runs locally instead, reaching files and sessions you already use. What is Kimi Work? Kimi Work is a downloadable application, not a web chat. You give it goals in plain language, and it acts on your machine. Independent community mentions report that it runs on Kimi K2.6, Moonshot’s flagship model. K2.6 is an
Moonshot AI has introduced Kimi Work, an AI agent that runs on your own desktop. The Beijing-based AI entity announced it this week along with downloads for macOS and Windows. Kimi Work reads local files, drives your real browser, and runs scheduled tasks. It targets knowledge workers whose bottleneck is access to files and live sessions. Most agent tools of the past two years ran in the cloud. You type a goal, a remote server spins up a sandbox, and a hosted browser acts. Kimi Work runs locally instead, reaching files and sessions you already use. What is Kimi Work? Kimi Work is a downloadable application, not a web chat. You give it goals in plain language, and it acts on your machine. Independent community mentions report that it runs on Kimi K2.6, Moonshot’s flagship model. K2.6 is an open-weight Mixture-of-Experts model released on April 20, 2026. It activates about 32 billion parameters per token. It carries a 256K-token context window for long, multi-step work. How Kimi Work Operates Four building blocks define the product. Knowing them helps you reason about what it can do. Agent Swarm: Kimi Work can run many sub-agents in parallel on your machine. According to Moonshot release, the swarm scales to 300 sub-agents. The system splits a task into parts, then coordinates the results. K2.6’s swarm is documented up to 4,000 coordinated steps. WebBridge: This browser extension lets the agent use a browser like a person. It searches, scrolls, extracts data, and fills forms across tabs. Because it uses your real session, it inherits your existing logins and cookies. Cron scheduling engine: A built-in scheduler runs jobs on a daily, hourly, or conditional basis. Per Moonshot, triggers include LLM agent calls and Python or shell scripts. A “Keep Computer Awake” toggle keeps overnight jobs from stalling. Local files and code: The agent reads folders you mount and runs Python in the background. According to Moonshot release, original files stay in place unless you approve a change. The desktop app also ships finance-specific data. It is pre-integrated with market data for A-shares, Hong Kong stocks, and US equities. According to Moonshot release, this removes the need for custom API setup. Finished research can convert into PowerPoint decks or Excel sheets. Use Cases With Examples Document triage: Point the agent at a folder of quarterly PDFs. Ask it to summarize them into one document, keeping originals intact. The swarm assigns one reader per file, then merges findings. Web data collection: Tell WebBridge to pull historical prices for three tickers. It opens your browser, sets the date range, and extracts the tables. Python then normalizes columns and writes an Excel workbook. Scheduled briefings: Define a 7:00 AM job in the cron engine. Each morning it gathers headlines and drafts a markdown briefing. With “Keep Computer Awake” on, the job survives overnight. Office generation: Ask for a short market-brief deck after a research pass. The agent drafts sections in parallel and renders native slides. Kimi Work vs Cloud Agents The core difference is where the agent runs and what it can reach. The table compares Kimi Work against a typical cloud agent. DimensionKimi Work (local)Typical cloud agentExecution locationYour desktopVendor serversFile accessMounts your local foldersUploaded or sandboxed filesBrowserYour real, logged-in browser via WebBridgeHosted virtual browserSchedulingBuilt-in cron engineOften external or limitedUnderlying modelKimi K2.6, reportedVendor’s hosted modelSetupInstall app, grant folder accessZero-install, open a tabSecurity responsibilityFalls on the userFalls on the vendor Neither approach wins outright. Local execution keeps data on your device and reaches real files. Cloud execution trades that control for zero-setup convenience and managed safety. Scheduling: The Cron Engine in Practice Kimi Work is driven by natural language, not a public API. Its scheduler is a cron engine, so it accepts standard cron schedules. The five fields are: minute, hour, day-of-month, month, and day-of-week. Copy CodeCopiedUse a different Browser# Standard cron schedules the engine understands 0 7 * * * # every day at 07:00 0 * * * * # every hour, on the hour 30 8 * * 1-5 # 08:30 on weekdays only (Mon-Fri) 0 0 1 * * # 00:00 on the first day of each month You pair a schedule with a plain-language task. A daily briefing job reads like this. Copy CodeCopiedUse a different BrowserSchedule: 0 7 * * * (every day at 07:00) Task: "Draft today's market briefing and save it to ~/KimiWorkspace/briefing.md. Ask before writing." The approval gate then applies to that write, and to any web action. Key Takeaways An “Ask before acting” gate, with YOLO mode off, prompts before any file write. Kimi Work is a local desktop agent for macOS (Apple silicon) and Windows. An Agent Swarm runs up to 300 sub-agents in parallel on your machine. WebBridge drives your logged-in browser; a built-in cron engine runs scheduled jobs. It reads local folders and runs Python, keeping originals unless you approve changes. Marktechpost’s Interactive Explainer #kimiwork-sim *{box-sizing:border-box!important;margin:0;padding:0} #kimiwork-sim{ --bg:#0b0c0f; --surface:#13151b; --surface2:#191c24; --line:#262a34; --ink:#e9edf5; --mut:#8b93a4; --green:#76B900; --violet:#8b7cff; --amber:#f4b740; --mono:ui-monospace,SFMono-Regular,"SF Mono",Menlo,Consolas,monospace; --sans:-apple-system,BlinkMacSystemFont,"Segoe UI",Roboto,Helvetica,Arial,sans-serif; all:initial; display:block!important; width:100%!important; background:var(--bg)!important; color:var(--ink)!important; font-family:var(--sans)!important; line-height:1.5!important; border:1px solid var(--line)!important; border-radius:16px!important; overflow:hidden!important; max-width:920px; margin:0 auto!important; } #kimiwork-sim .kw-wrap{padding:0!important} #kimiwork-sim .kw-top{ display:flex!important; align-items:center; gap:10px; padding:14px 18px!important; border-bottom:1px solid var(--line)!important; background:linear-gradient(180deg,#15181f,#0f1115)!important; } #kimiwork-sim .kw-dot{width:11px;height:11px;border-radius:50%;background:#33373f!important;display:inline-block} #kimiwork-sim .kw-dot.r{background:#ff5f56!important} #kimiwork-sim .kw-dot.y{background:#ffbd2e!important} #kimiwork-sim .kw-dot.g{background:#27c93f!important} #kimiwork-sim .kw-title{font-family:var(--mono)!important;font-size:12.5px;color:var(--mut)!important;margin-left:8px;letter-spacing:.3px} #kimiwork-sim .kw-badge{margin-left:auto;font-family:var(--mono)!important;font-size:10.5px;color:var(--green)!important;border:1px solid #2f3a1c!important;background:#141a0c!important;padding:3px 8px;border-radius:999px} #kimiwork-sim .kw-body{display:grid!important;grid-template-columns:1fr 1fr;gap:1px;background:var(--line)!important} #kimiwork-sim .kw-pane{background:var(--bg)!important;padding:18px!important;min-width:0} #kimiwork-sim .kw-h{font-size:11px;text-transform:uppercase;letter-spacing:1.4px;color:var(--mut)!important;margin-bottom:10px;font-weight:600} #kimiwork-sim .kw-sub{font-size:12.5px;color:var(--mut)!important;margin:2px 0 12px} #kimiwork-sim .kw-chips{display:flex!important;flex-wrap:wrap;gap:8px} #kimiwork-sim .kw-chip{ font-family:var(--sans)!important;font-size:12.5px;color:var(--ink)!important;cursor:pointer; background:var(--surface)!important;border:1px solid var(--line)!important;border-radius:10px!important; padding:9px 11px!important;text-align:left;transition:.15s;flex:1 1 calc(50% - 8px);min-width:140px } #kimiwork-sim .kw-chip small{display:block;color:var(--mut)!important;font-size:10.5px;margin-top:3px} #kimiwork-sim .kw-chip:hover{border-color:#3a414f!important} #kimiwork-sim .kw-chip.on{border-color:var(--green)!important;background:#10160a!important;box-shadow:inset 0 0 0 1px rgba(118,185,0,.35)} #kimiwork-sim .kw-controls{margin-top:16px} #kimiwork-sim .kw-row{display:flex!important;align-items:center;justify-content:space-betwee
Related
相關文章
Liquid AI Introduces LFM2.5-Embedding-350M and LFM2.5-ColBERT-350M: Dense Bi-Encoder and Late-Interaction Models for Fast Multilingual Search Across 11 Languages
This week, Liquid AI released two new retrieval models. They are LFM2.5-ColBERT-350M and LFM2.5-Embedding-350M. Both hold 350M parameters. Both are the first bidirectional members of the LFM family. They build on LFM2.5-350M-Base, released in March. The pair targets fast multilingual and cross-lingual search across 11 languages. Their footprint is small enough to run almost anywhere. Both are available now on Hugging Face under the LFM Open License v1.0. LFM2.5 Retrievers The two models share one backbone but represent text differently. LFM2.5-Embedding-350M is a dense bi-encoder. It turns each document into a single vector. Pick it when you want the fastest search and the smallest, cheapest index. LFM2.5-ColBERT-350M is a late-interaction model. It converts each token into a vector rather
Perplexity Launches Brain, a Self-Improving Memory System That Builds a Context Graph of an Agent’s Work and Learns Overnight
Most AI memory remembers the user. It stores your preferences, your tastes, and your role. Perplexity is taking a different path. Today, Perplexity launched Brain, a self-improving memory system for its agent product, Computer. Brain does not focus on remembering you. It remembers what the agent did. That reframes what memory in AI is for. What is Perplexity‘s Brain Brain is a self-improving memory system. It builds a context graph of the work Computer performs. At set intervals, such as overnight, Brain reviews that graph. It then teaches itself how to do the work better. The idea is straightforward. The more work you do, the more efficient Brain makes your Computer. Brain is rolling out today to Perplexity Max and Enterprise Max subscribers in Research Preview. Two Axes of AI Memory Perp

智譜新高,MiniMax承壓,“大模型雙雄”命運殊途
這篇消息聚焦「智譜新高,MiniMax承壓,“大模型雙雄”命運殊途」。原始導語提到:大模型在被市場重新定價 從 AI 情報角度來看,這類內容值得關注其背後的技術進展、產品落地、產業競爭與後續市場影響。

華為昇騰 0 Day 支持智譜 GLM-5.2 模型,提供全面推理優化
華為昇騰 AI 宣佈在智譜開源 GLM-5.2 大模型當天即完成深度推理優化。通過 MOE 大融合算子、通信計算融合、高併發調度等七項關鍵技術,顯著提升編程和長程任務的處理效率,現已支持 A3 系列產品部署。#AI 大模型# #國產算力#
企業AI轉型再添利器:青雲科技算力雲接入 MiniMax-M3 模型
企業AI落地面臨高效低成本難題。青雲科技旗下基石智算平臺接入國產開源大模型MiniMax-M3,提供新算力支持。MiniMax-M3以卓越上下文處理能力等三大核心技術見長,依託自研架構,助企業便捷部署AI業務。
阿里開源統一科學大模型 LOGOS,僅用五十六分之一參數超越微軟
阿里 ATH-Token Foundry 聯閤中國人民大學高瓴人工智能學院開源科學基礎模型 LOGOS。該模型採用統一科學語法與純序列建模範式,在六大科學任務上匹配或超越傳統專用方法。其中 LOGOS-1B 僅 1B 參數,即展現出極高效率,性能超越參數量達 8×7B 的微軟模型。