Clawdbot Ascends to Legendary Status: The 24/7 AI Butler That Sold Out Mac Minis

marsbit发布于2026-01-26更新于2026-01-26

文章摘要

Clawdbot, an open-source AI assistant project by Peter Steinberger, has taken Silicon Valley by storm, driving a surge in Mac mini sales as users seek hardware to run it. This "7x24h Jarvis" operates locally on devices like Mac mini, functioning as both an AI agent (using models like Claude and Gemini) and a gateway to communicate via apps like WhatsApp and iMessage. It offers unlimited memory, proactive task execution, and full system access—enabling it to run scripts, automate workflows, and even replace services like Zapier. Users report it managing businesses, handling emails, controlling smart home devices, and more, all while learning and evolving over time. With low setup costs (as little as $25/month using cloud servers) and growing accessibility, Clawdbot is redefining personal AI assistance by combining persistent memory, autonomy, and deep system integration.

Editor: Taozi, New Zhiyuan

[New Zhiyuan Insight] It's insane! Silicon Valley has become obsessed with Clawdbot overnight, hailed as the "24/7 Jarvis." It possesses infinite memory, is always on call, and takes initiative to get things done. The most outrageous part is that it single-handedly made Mac minis sell out.

The pace of AI iteration in Silicon Valley leaves no room for humans to breathe...

Wake up, and the entire internet is flooded with posts about a 24/7 AI assistant—Clawdbot.

This is an open-source project developed by developer Peter Steinberger and has recently become wildly popular in geek circles.

Clawdbot can run smoothly on a Mac mini, serving two roles:

A locally run "AI agent" capable of calling various models like Claude and Gemini;

A "gateway" that allows communication via chat apps like WhatsApp and iMessage.

It's no exaggeration to say that Clawdbot has completely redefined the concept of a "personal AI super assistant" for 2026.

Look, an AI startup CEO exclaimed, "We have AGI!" Since installing Clawdbot, it has quietly handled a ton of tasks—

Most incredibly, it solves the biggest pain point of current mainstream large models—memory. For example, it remembers small things mentioned casually two weeks ago.

Instantly, people started sharing their Mac configurations, and various Clawdbot tutorials emerged.

Probably even Tim Cook himself didn't expect that Mac minis would sell out overnight!

One developer frantically configured 12 Mac Minis at once. At a base price of $599 each, the total cost was $7,188 (approx. 50,000 RMB).

The true ultimate Skynet is Clawdbot.

Clawdbot is Completely Blowing Up, "The Real Jarvis" Has Arrived

Actually, Clawdbot isn't a brand-new AI; it was born late last year.

At that time, a software engineer from Vienna, Peter Steinberger, published a lengthy thousand-word article detailing his workflow for 2025.

He admitted, "The most profound change this year is that I almost never read code anymore."

Peter Steinberger came out of retirement to make a comeback

He built an "all-powerful private butler" named Clawdis, which has full access to all computers, text messages, and emails.

Moreover, it's a physical world "remote control," integrated with home automation systems to control cameras, lights, music, and even adjust bed temperature.

It even has its own voice system, running Clawdbot.

In fact, a key glimpse into its capabilities can be gleaned from the article by Steinberger, the "Father of Clawdbot"—

Clawd is an AI cyber butler with "highest privileges," managing not only human daily life but also overseeing other working AI agents.

At the time, this article also drew praise from Karpathy.

Just like the release of Claude Opus 4.5, it didn't cause much of a stir for a long time.

A month later, which is now, Claude Code showed everyone in Silicon Valley its true power. The same goes for Clawdbot.

It's an open-source project. On GitHub, Clawdbot has garnered nearly 9.2k stars and 1.2k forks.

GitHub address: https://github.com/clawdbot/clawdbot

Clawdbot promotes itself as a "24/7 personal assistant," truly bringing the long-imagined "Jarvis" into reality.

Silicon Valley is Collectively Freaking Out, AI is Taking Over Everything

Clawdbot's real killer feature is still its core AI agent capability.

It can run entirely on a personal local computer. All settings, memories, and instructions are just folders and Markdown documents on the hard drive.

Except for the moment it calls the large model which requires internet, everything else is local. This means it has access to the computer's Shell and file system permissions.

This is the most explosive part!

Because it has permissions, Clawdbot can execute terminal commands, instantly write and run scripts, install new skills, and even set up MCP servers to extend external integrations.

Ultimately, what everyone gets is a self-evolving, fully controllable personal Agent.

Rather than more descriptions, it's better to go straight to the developers' "magic" demos.

Official Clawdbot curated demo showcase: https://clawd.bot/showcase

Dan Peguine used the Clawdbot platform to manage his parents' tea business. Unexpectedly, it handled:

Automatic scheduling → Following up with corporate clients → Managing inventory → Customer service, and it gets smarter with use.

He exclaimed in amazement, "In a few months, Clawdbot will probably be able to manage businesses of any scale."

Developer Nimrod Gutman said Clawdbot helped him build another amazing feature!

It created an automatic setup for a home assistant that intelligently controls how long the boiler runs based on the weather over the past 12 hours, so no cold showers even on cloudy days.

AI browser Arc developer Andrew Jiang tested it: 24 hours after giving Clawdbot the idea, it had completed scraping a content project involving 100 top X platform accounts, totaling 4 million tweets.

Now, he can partner with a copywriting AI agent to polish the first story. This era is amazing for creation.

Some are completely captivated by Clawdbot's capabilities.

A big shot said, Clawdbot is all you need.

Writes Its Own Code, Kills Zapier

Developer Federico Viticci recounted: Clawdbot showed me what the future of AI personal assistants looks like.

During testing, he asked Clawdbot to add functionality for image generation using Google's Nano Banana Pro model.

Not only did it do it, but it also obediently changed its own avatar to a "Zelda-style crab" upon command.

In daily use, the "memory files" are actually its automatically generated Markdown diaries, recording daily interactions.

The moment that most excited Viticci, and was also slightly terrifying, arrived.

Viticci asked if it could help him save money by canceling the automation services he previously bought on Zapier and switching to running locally on his Mac mini.

For example, automatically creating a new project in Todoist every Friday after sending the Newsletter.

Clawdbot thought for a moment and proposed a solution: set up a cron job on the Mac mini to check the RSS feed every few hours, and once there's an update, call the Todoist API to create a task.

After a 5-minute conversation, it actually wrote all the code on the Mac and got the process running. No cloud dependencies, no subscription fees, entirely done by the LLM calling local Shell tools.

Mac Minis Sell Out, Cook Smiles

Now, many people are even filling their homes with Mac minis just to run it.

Netizens joked that the Father of Clawdbot single-handedly boosted Apple's sales in the first quarter. Probably even Tim Cook would laugh in his sleep.

<极客迷们为之疯狂。div>

Does that mean you're not worthy without a Mac mini?

The Father of Clawdbot stated that there's no need to buy an additional device; you can just deploy a VPS to use it.

Even a long-unused, dusty MacBook or gaming PC can run it, and a Raspberry Pi勉强也行 (barely works too).

A Lobster, Ruling the World

On his personal homepage, the "Father of ClawdBot" aims to help a lobster rule the world.

Now, he has truly succeeded.

Many people have almost gone crazy trying to use it. One developer shared some personal experience and tutorials for non-developer audiences to understand.

You can understand it like this: ChatGPT and Claude live on websites; humans have to actively go find them, type, wait for a response, and then copy-paste elsewhere.

Clawdbot is an AI that "lives" in your phone. The reason it's so popular mainly comes down to three reasons:

1. It actually has "memory"

Ask Siri what you said to it yesterday, and it will definitely be clueless.

Clawdbot remembers your last conversation, remembers your preferences, and even remembers a small thing you mentioned casually two weeks ago.

It continuously accumulates background information over time, becoming more and more understanding of you.

What Apple's Siri couldn't solve in 13 years has now been cracked by an AI expert who came out of retirement.

2. It "proactively" seeks you out

This is the coolest point. Ordinary AIs always wait for people to open them. Clawdbot takes the initiative:

Hey, you have 3 urgent emails, and there's a meeting in 20 minutes;

That stock you follow just dropped 5%;

The weather isn't great tomorrow, you might need to adjust your schedule.

It feels like hiring a real private secretary who actually keeps an eye on things for you.

3. It can directly control the computer

It doesn't just talk and answer questions; it can really work:

Fill out forms, send emails, move files, run programs, control the browser.....

One guy重构 (refactored) his entire website while lying in bed watching Netflix. He never touched his laptop the whole time, just texted Clawdbot what to do.

The developer said many people have fallen into a misconception—

I've seen people stack 3 Mac minis on their desk, pulling Raspberry Pis everywhere,搞得好像在建数据中心一样 (as if they're building a data center), but it's really not necessary.

Clawdbot can run on a $5 per month cloud server, cheaper than a cup of coffee, with a minimum cost of $25.

The technical requirements are actually simple:

A cheap cloud server (or your own computer)

Install Node.js (free software)

A Claude or ChatGPT subscription. That's it, no need to pioneer some "Mac mini farm."

Basic cost estimate—

Software: Free (open source)

Server: $5-50 per month (depending on usage). Most people can get by with a $5 Hetzner VPS, or run it directly on their own computer ($0).

AI fees: $20-100 per month. Claude Pro is $20/month, or pay directly based on API usage.

Total: About $25-150 per month, and you get a truly capable AI assistant.

Think about it, some "AI consultants" charge $10,000 just to set up a basic robot; this price is简直香爆了 (incredibly attractive).

So, how is it different from ChatGPT and Siri?

ChatGPT is a chat box; Clawdbot is an assistant living in your personal life. Siri's memory is about as good as a goldfish's; Clawdbot actually has a brain.

How to Get Started?

In simple terms, Clawdbot runs on a computer, can connect to chat software, you send messages, it replies.

Of course, it can also execute tasks on the computer.

From a professional perspective, a "gateway" runs in the background, which can be seen as a switchboard operator.

Messages come in from channels like Telegram, and the gateway routes them to the AI. The AI thinks, replies, and triggers actions—like opening a browser or running a script.

Except for calling the Claude/ChatGPT API, personal data is not sent to any company's servers.

Some classic use cases:

Morning Briefing: Wake up, and there's already a summary on your phone: important emails, the day's schedule, to-do items. Helps you sort out your thoughts before even getting out of bed.

Health Tracking: "Connected to a WHOOP fitness tracker, reports data daily." Someone set it up in 5 minutes, automatically gaining health insights every day.

Email Management: "Help me unsubscribe from all these乱七八糟的 (messy) news emails." It will log into the邮箱 (email) itself, find the spam, and handle it.

Research Assistant: "Help me find the 5 best-reviewed restaurants near hotels in Tokyo." It will search, compare prices, and give suggestions, all within the chat box.

Task Automation: "Every Friday at 5 PM, send me a weekly review." Set it once, and it can run forever.

High-end Tricks: One user had Clawdbot write meditation scripts, generate audio with AI voice, add background music, and send it to him准时 (punctually) every morning. 100% automated.

Do You Need Technical Skills?

Honestly, you need a little.

If you can follow instructions and know how to copy-paste command lines, you can manage it. It's not a "click and done" thing, but it's not rocket science either.

Official website here: https://clawd.bot

The installation command is just one line:

curl -fsSL https://clawd.bot/install.sh | bash

Then follow the setup wizard; it will teach you how to connect chat software.

If this seems too hardcore, you can wait a few months. The community optimizes the process weekly to make it simpler.

In this era of information explosion, what people lack is a second brain that can filter, remember, and execute for them.

Clawdbot is a typical representative, fulfilling the dreams of many.

Perhaps, in the future, a company only needs one CEO and many Clawdbots.

References:

https://x.com/NoahEpstein_/status/2015136736989397011?s=20

https://x.com/nickvasiles/status/2014790519529095447?s=20

https://x.com/naruto11eth/status/2015030005370417636?s=20

https://www.macstories.net/stories/clawdbot-showed-me-what-the-future-of-personal-ai-assistants-looks-like/

相关问答

QWhat is Clawdbot and why has it become so popular in Silicon Valley?

AClawdbot is an open-source, 24/7 AI assistant developed by Peter Steinberger that runs locally on devices like Mac mini. It acts as both a local AI agent capable of calling models like Claude and Gemini, and a gateway that communicates via apps like WhatsApp and iMessage. Its popularity stems from its ability to have infinite memory, proactively perform tasks, and operate with full access to the user's system, effectively reshaping the concept of a personal AI super assistant.

QHow does Clawdbot address the memory limitations of current large language models?

AClawdbot solves the memory limitation by maintaining persistent memory through locally stored Markdown diary files that record all interactions. This allows it to remember details from previous conversations, user preferences, and even minor mentions from weeks ago, enabling it to accumulate context over time and become more personalized.

QWhat are some practical examples of tasks Clawdbot can perform autonomously?

AClawdbot can autonomously handle tasks such as managing business operations (scheduling, inventory, customer service), controlling home automation systems (adjusting boilers based on weather), web scraping (collecting data from social media), writing and running scripts to replace services like Zapier, and providing personalized updates like morning briefings and health insights.

QWhy did Clawdbot lead to a surge in Mac mini sales, and are there alternative ways to run it?

AClawdbot led to a surge in Mac mini sales because it is optimized to run efficiently on these devices, making them a popular choice for users. However, alternatives include using a VPS (Virtual Private Server) for as low as $5 per month, repurposing old MacBooks or gaming PCs, or even using a Raspberry Pi, though performance may vary.

QWhat are the key differences between Clawdbot and conventional AI assistants like ChatGPT or Siri?

AUnlike ChatGPT, which is primarily a chat interface, Clawdbot is an integrated life assistant with system-level access to perform tasks directly. Compared to Siri, which has limited memory, Clawdbot features persistent memory, proactive notifications, and the ability to execute commands on the user's device, making it more capable and context-aware.

你可能也喜欢

SemiAnalysis 拆解华为麒麟 9030:制程走不动了,把芯片折叠起来

半导体分析机构SemiAnalysis近期发布了对华为麒麟9030芯片的详细拆解报告。该芯片采用中芯国际N+3制程,其最小金属间距(32.5nm)甚至小于英特尔18A制程,逻辑密度也追平了台积电N6水平。然而,这一成果是在没有EUV光刻机的情况下,通过复杂的四重图案化等工艺实现的,导致制造成本更高、工艺更复杂且良率控制难度大。 在芯片设计上,华为海思在近乎相同的芯片面积内,通过增加CPU核心、GPU单元和NPU核心,并扩大缓存,显著提升了麒麟9030的性能。其GPU性能已追平2022年旗舰水平,但受限于制造工艺,CPU性能与当前使用先进制程的苹果、高通旗舰芯片仍有明显差距。 面对制程进步的瓶颈,华为提出了转向“时间域”优化的τ缩放定律和“LogicFolding”(逻辑折叠)技术路线图。该技术旨在通过3D堆叠将同一逻辑模块拆分为上下两层,以缩短信号路径、提升频率并降低功耗。华为的目标是到2031年将大核频率提升至5GHz,并将等效密度推向台积电14A级别。不过,分析指出,其密度计算方式与传统方法不同,且实现难度极高。 报告总结认为,出口管制虽未阻止中国芯片进步,但改变了其发展路径,使其代价更高。同时,中芯国际的先进制程技术正扩散至华虹等公司,国产EDA工具和存储芯片(如长鑫)也在供应链中取得进展。未来的关键在于,华为的3D堆叠路线能否在成本可控下,使中国芯片在关键应用场景达到“够用”水平,从而重塑供应链价值。

marsbit24分钟前

SemiAnalysis 拆解华为麒麟 9030:制程走不动了,把芯片折叠起来

marsbit24分钟前

比特币短期利好结构验证,HYPE逢低布局窗口开启 | 特邀分析

本周市场环境复杂,全球资产剧烈波动。文章对比特币(BTC)和HYPE代币的本周走势进行分析与预判。 **比特币(BTC)分析:** 当前BTC已站上65,000美元,本周需关注对其回踩确认的结果。 * **若站稳**:可能挑战69,500-70,500美元压力区,该区域是计划布局中线空单的重要位置。 * **若失守**:可能再度下探60,000-62,000美元支撑区间。 * **操作策略**: * **中线**:依据65,000美元博弈结果,考虑在69,500-70,500美元区域出现承压时布局空单,或在跌破关键支撑后顺势沽空。 * **短线**:利用部分仓位,在关键支撑与压力位间寻找价差机会。 **HYPE代币分析:** HYPE完成四段式调整后,在52美元区域企稳反弹,上方关键压力在62.5-64.57美元区域。 * **本周预判**:重点观察价格在62.5-64.57美元区域的承压效果。 * **操作策略**:采取“逢低布局”思路。若价格回测52-54.5美元或47-49美元关键支撑区域并出现企稳信号,可考虑轻仓试多,需严格控制仓位并设置止损。 **交易复盘:** 文章回顾了上周一次HYPE短线多单操作,在54.39美元附近买入,于60.85美元附近卖出,实现约11.88%的收益。开平仓决策结合了自建的价差交易模型和动能量化模型信号。 **风险提示:** 本文所有观点与策略仅为个人技术分析,不构成投资建议。市场风险高,投资需谨慎。操作时应严格执行止损纪律,动态调整策略。

marsbit51分钟前

比特币短期利好结构验证,HYPE逢低布局窗口开启 | 特邀分析

marsbit51分钟前

Trust Wallet 通过与 bStocks 集成推出代币化美股

全球领先的自托管加密货币钱包Trust Wallet宣布整合bStocks,使用户能通过自主托管方式直接在BNB链上访问代币化美股。符合资格的用户现可全天候从钱包中交易这些资产,无需传统券商账户。 目前首发提供五支代币化美股:TSLAB(特斯拉)、CRCLB(Circle)、MUB(美光科技)、SNDKB(闪迪)和NVDAB(英伟达),未来将增加更多标的。用户可通过USDT在钱包内即时兑换bStocks。这些资产基于BNB链构建,自动反映价格变动、股息和股票拆分,用户无需手动操作即可获得经济敞口。 bStocks可集成至BNB链整个DeFi生态,例如在Venus和Lista DAO进行借贷,在PancakeSwap和Aster交易,同时继续获得底层证券的股息。该服务保持自托管特性,无需KYC验证。 Trust Wallet CEO表示,此举旨在降低全球投资者接触股票的门槛,提供全天候、自托管且可组合的DeFi访问途径。这是Trust Wallet在现实资产上链领域的又一探索,未来将继续拓展代币化传统金融工具。 **重要提示**:bStocks属于金融工具凭证,非实际股权,持有人不直接拥有相关公司股份。该服务仅限合格用户在许可区域内通过二级市场参与,不向美国、英国、欧盟等地区提供。用户需自行确认当地合规性,并注意产品存在流动性、监管、技术等多重风险,可能导致本金全部损失。详细信息请参阅Trust Wallet服务条款。

TheNewsCrypto52分钟前

Trust Wallet 通过与 bStocks 集成推出代币化美股

TheNewsCrypto52分钟前

交易

现货
合约

热门文章

加密市场宏观研报:原油飓风、AI巨浪与比特币的十字路口

全球金融市场正经历一场由地缘冲突引发的系统性重估:霍尔木兹海峡封锁导致原油一度暴涨30%,G7紧急释放储备后涨幅收窄,滞胀风险取代通胀成为核心担忧,美元成为“唯一避风港”并逼近100大关,亚太及美股遭遇“黑色星期一”全线重挫;AI领域则冰火两重天,国家发改委提出“十五五”末10万亿规模目标,OpenClaw项目火爆推动概念股狂飙;比特币在宏观风暴中跌破70000美元关键防线。

568人学过发布于 2026.03.12更新于 2026.03.12

加密市场宏观研报:原油飓风、AI巨浪与比特币的十字路口

相关讨论

欢迎来到HTX社区。在这里,您可以了解最新的平台发展动态并获得专业的市场意见。以下是用户对AI(AI)币价的意见。

活动图片