文档Docs
Agent J 和同类产品：一类东西，几处不同Agent J and similar products: same kind, different choices
Claude Code、Codex、OpenClaw、Hermes Agent、Meta Muse、Grok Bot、OpenAI dots 和 Agent J 是同一类产品；这篇先讲相同的地方，再逐个列出不同，每条都附官方出处。Claude Code, Codex, OpenClaw, Hermes Agent, Meta Muse, Grok Bot, OpenAI dots and Agent J are the same kind of product. Here is what they share and, one by one, where they differ, with official sources.
常有人问：Claude Code 自己就能用手机遥控，OpenAI 刚发了 dots，Meta 有 Muse，网上大家都在养龙虾（OpenClaw），那 Agent J 跟它们有什么不一样？
先说结论：它们和 Agent J 是同一类产品，都想让 AI 不只回答问题，而是替你把事情办完。不同的地方在于：AI 在谁的电脑上干活，用谁的模型，你在手机上怎么指挥它，以及一个人要管很多件事的时候怎么管。
注意：下面关于别家产品的内容，全部来自各家的官方页面，查阅日期是 2026-10-05，每一条都附了出处；官方没写的，我们就写官方未公布，媒体的转述只在注明的地方用。这些产品每周都在变，以各家官网为准。关于 Agent J 的内容，只写今天已经上线的功能。
先说相同：都是一本让 AI 干活的秘籍
产品定位 那篇打过一个比方：大模型像一把刀，让模型干活的那套方法像一本武功秘籍。下面这些产品都是秘籍，只是练法不同：
- 把模型、工具和步骤串起来，让 AI 自己干活，不用你一句句问；
- 大多能在手机上派活、看进度；
- 遇到要你拍板的事，会停下来问你；
- 大多能定时自动跑，比如每天早上出份报告。
所以选哪一个，不是有没有 AI 的问题，而是下面这几处不同，哪一处对你最要紧。
一张表看全
| 产品 | AI 在哪干活 | 用谁的模型 | 手机上怎么用 | 价格起点（官方） |
|---|---|---|---|---|
| Agent J | 你自己的电脑或你自己的云服务器 | 你已经在用的 Claude Code、Codex、OpenCode、Kimi Code 或通义千问 Qwen Code，模型账号是你自己的 | 网页版 App，加到主屏幕 | 每个席位每月 $20，或每年 $200；模型费另付 |
| Claude Code（含 Remote Control） | 你的电脑，或 Anthropic 的云端虚拟机 | Anthropic 的 Claude | Claude 手机 App、claude.ai/code | 含在 Pro 里，$20/月起 |
| OpenAI Codex | 你的电脑，或 OpenAI 的云端沙箱 | OpenAI 的模型 | ChatGPT 手机 App | 命令行和云端从 Plus 起，$20/月 |
| OpenClaw（小龙虾） | 你自己的电脑、服务器或 VPS | 任意模型，用你自己的 key | WhatsApp、Telegram 等聊天软件 | 免费开源，模型费另付 |
| Hermes Agent | 你自己的机器，也可选 Nous Portal 云托管 | 任意模型 | Telegram、Discord、WhatsApp 等聊天软件 | 免费开源；云托管 $20/月起 |
| Meta Muse | Meta 云上的专属虚拟机 | Meta 的 Muse Spark | Muse App、网页、WhatsApp | 有免费档和订阅档 |
| Grok Bot（xAI） | xAI 云上的电脑 | xAI 的 Grok | Grok App | 含在 SuperGrok 等方案里，用量另算 |
| OpenAI dots | OpenAI 云上的电脑和浏览器 | OpenAI 的 GPT-6 Astra | ChatGPT App | 含在 Pro 里，$100/月起 |
出处见下面每一节。
Agent J 是什么样的（作为对照）
- 在哪干活：你自己的电脑（Mac 或 Linux，Windows 要先装 WSL2），或者你自己的云服务器。我们不替你托管 AI。
- 用谁的模型：Agent J 本身不是模型。它用你电脑上已经登录好的 Claude Code、Codex、OpenCode、Kimi Code 或通义千问 Qwen Code；Kimi Code 用 Kimi 会员，Qwen Code 用阿里云百炼的套餐，用 OpenCode 时可以配阿里云百炼、火山方舟、DeepSeek、智谱这类模型。模型的钱你直接付给模型公司。
- 手机上怎么用：手机上是网页版 App，加到主屏幕后像普通 App 一样用。你和 Agent 的聊天是端到端加密的，只有你的手机和你的电脑能解开，我们看不到；唯一的例外写在 数据安全页。
- 多件事怎么管：你只跟一个主 Agent 说话。它背后可以有很多条工作流，每条有自己负责的 Agent，由主 Agent 派活、看报告、出了问题去修。定时任务在你的电脑上跑，装好默认不跑，你在手机上点头才开始。
- 价格：每个席位每月 $20，或每年 $200，见 价格页。
逐个看不同
Claude Code（含 Remote Control）
| 维度 | 事实 | 出处 |
|---|---|---|
| 是什么 | Anthropic 的编程 Agent，有命令行、桌面 App、网页版和手机 App 里的 Code 标签页 | Desktop 文档 |
| Remote Control | 用手机或网页连上你电脑上正在跑的 Claude Code 会话；文件、工具和配置都留在你的电脑上，电脑要开着，进程要一直运行 | Remote Control 文档 |
| 传输 | 只从你的电脑向外发请求，不开端口；消息经 Anthropic 的服务器转发，文档写的是 TLS 加密 | 同上 |
| 谁能用 | Pro、Max、Team、Enterprise；不支持 API key | 同上 |
| 云端 | 云端会话跑在 Anthropic 管理的虚拟机里，合上电脑也继续跑；Routines 可以在云端定时运行，最短间隔 1 小时 | 网页版文档、Routines 文档 |
| 数据 | 个人用户可以选择数据是否用于改进模型 | 数据使用说明 |
| 价格 | Pro $20/月，Max $100 或 $200/月 | 价格页 |
和 Agent J 的不同：Remote Control 是 Claude Code 自带的手机窗口，订阅里就有，不用另付钱；如果你只用 Claude Code、只想在手机上接着一个会话干，它就够用。Agent J 不绑定一家：Claude Code、Codex、OpenCode 都能接，换模型不用换手机上的用法。另一处不同是管法：Remote Control 是你逐个打开会话、逐个盯；Agent J 是你只跟一个主 Agent 说话，由它去管背后的工作流和定时任务。
OpenAI Codex
| 维度 | 事实 | 出处 |
|---|---|---|
| 是什么 | OpenAI 的编程 Agent，有桌面 App、命令行（开源，Apache-2.0）、IDE 扩展、云端和 ChatGPT 手机 App | Codex 文档、GitHub |
| 手机遥控 | ChatGPT 手机 App 可以连到运行 Codex 的 Mac、Windows 电脑或 SSH 主机：开新任务、看进度、批准命令、看改动；电脑要开着、在线 | Remote 文档 |
| 传输 | 官方说经过一层安全中转，不把电脑直接暴露在公网；是否端到端加密，官方未公布 | Remote connections 文档 |
| 定时 | 桌面版的定时任务在你的电脑上跑，电脑要开着、App 要运行 | Automations 文档 |
| 价格 | Plus $20/月起；命令行、IDE 和云端从 Plus 起 | 价格页 |
和 Agent J 的不同：Codex 的手机遥控只遥控 Codex，用 OpenAI 的模型和你的 ChatGPT 账号。Agent J 可以把 Codex 当成干活的工具之一，同时也能接 Claude Code 或 OpenCode；你在手机上面对的是一个主 Agent，而不是一个个 Codex 任务。
OpenClaw（小龙虾）
| 维度 | 事实 | 出处 |
|---|---|---|
| 是什么 | 开源的个人 AI 助手（MIT 许可），跑在你自己的电脑上；因为标志是龙虾，中文网友把装它叫养龙虾 | GitHub、新华网报道 |
| 在哪干活 | 你自己的笔记本、服务器或 VPS，状态、记忆和凭据都在你的机器上，中间没有托管服务 | 官方文档 |
| 模型 | 任意模型，用你自己的 key | 同上 |
| 手机上怎么用 | 通过你已经在用的聊天软件：WhatsApp、Telegram、Slack、Signal、iMessage 等 20 多种 | GitHub |
| 多 agent / 定时 | 多 agent 路由，支持定时任务和 webhook | 官方文档 |
| 安全 | 官方要求把收到的消息当成不可信输入；没配沙箱时，工具直接在你电脑上执行 | GitHub |
| 价格 | 免费，没有付费档，默认不收集使用数据 | 官方文档 |
和 Agent J 的不同：OpenClaw 自己就是一套完整的 Agent 程序，直接接模型；Agent J 不另起一套，而是用你已经装好的 Claude Code、Codex 或 OpenCode 干活。手机这一头也不一样：OpenClaw 借用第三方聊天软件，消息要经过这些平台；Agent J 用自己的网页版 App，聊天端到端加密，需要批准的事以审批卡片的形式弹出来。OpenClaw 免费，但要你自己装、自己配、自己维护；Agent J 收席位费，装的时候由你电脑上的 AI 一步步带着装。
Hermes Agent（Nous Research）
提示：Hermes 这个名字也是 Nous Research 一个开源模型系列的名字。这里说的是 Agent 产品 Hermes Agent。
| 维度 | 事实 | 出处 |
|---|---|---|
| 是什么 | 开源的 Agent（MIT 许可），会从经验里自己总结技能、跨会话记住你 | 官网、GitHub |
| 在哪干活 | 你自己的电脑、VPS、Docker 等，也可以用 Nous Portal 一键托管到云上 | 同上、Nous Portal |
| 模型 | 不绑定厂商，可接 OpenRouter、OpenAI、Anthropic 等 | GitHub |
| 手机上怎么用 | 通过 Telegram、Discord、Slack、WhatsApp、Signal、邮件 | 同上 |
| 多 agent / 定时 | 有子 Agent，内置定时任务 | 同上 |
| 隐私 | 官方页面没有写遥测和隐私政策，官方未公布 | — |
| 价格 | 本体免费；Nous Portal 订阅 $20、$100、$200/月 | Nous Portal |
和 Agent J 的不同：跟 OpenClaw 类似，Hermes Agent 是一套独立的 Agent 程序，手机入口借用聊天软件。Agent J 用你已有的 AI 编程工具干活，手机上用自己的加密通道和审批卡片。
Meta Muse
| 维度 | 事实 | 出处 |
|---|---|---|
| 是什么 | Meta 的个人 AI agent，会替你发邮件、订行程、填表、结账，关了 App 也继续干 | Meta 发布文章（2026-09-08） |
| 在哪干活 | 每个用户一台在 Meta 云上的专属虚拟机；只有用户持有密钥的加密版虚拟机，官方说今年晚些时候上线 | 同上 |
| 模型 | Meta 自己的 Muse Spark | 同上 |
| 手机上怎么用 | iOS、Android、网页、WhatsApp；Mac 版可以读本机的信息、邮件和备忘录 | 同上、Mac 版帮助 |
| 安全 | 另有一个 Sentinel agent，Muse 做的事要它批准才能出网 | Meta 发布文章 |
| 隐私 | 对话和虚拟机里的数据不给 Meta 的广告系统；模型训练可以选择退出 | 同上 |
| 地区与价格 | 只在美国，18 岁以上；有免费档和订阅档 | 同上 |
和 Agent J 的不同：Muse 跑在 Meta 的云上，用 Meta 的模型。你不用碰电脑，它也全天在线，适合办个人杂事。Agent J 不托管：AI 在你自己的电脑或服务器上，用你自己的工具和文件干活。适合想让 AI 动自己的代码、文件和工作流的人。
Grok Bot（xAI）
| 维度 | 事实 | 出处 |
|---|---|---|
| 是什么 | 一组全天在线的 Agent，每个都有自己的云端电脑，登录你现有的工具替你办事，要批准时再来找你 | Introducing Grok Bot（2026-08-11） |
| 多 agent | 可以同时开多个 Bot，让其中一个当总管（官方叫 chief of staff）管其他 Bot；Bot 之间能发消息、拉群协作 | 同上、Designing Grok Bot |
| 在哪干活 | 每个 Bot 在云上自己的电脑里；企业版每个用户的环境相互隔离，默认没有访问权限 | Grok Bot for Enterprise |
| 模型 | xAI 自己的 Grok | xAI 新闻 |
| 定时 | Grok 里的自动化可以按天、按周等时间运行，所有人可用；收到邮件时触发要 SuperGrok | Automations in Grok |
| 隐私 | Grok Bot 专门的数据与训练条款，官方未公布 | — |
| 价格 | 含在 SuperGrok、Cursor Pro 和 Cursor Teams 等方案里，Bot 用量单独计算；SuperGrok 的美元价格官方方案页未列出 | More plans |
和 Agent J 的不同：Grok Bot 让一个主 Bot 管其他 Bot，和 Agent J 让主 Agent 管工作流，是同一个思路。不同在于 Grok Bot 跑在 xAI 的云上、用 Grok 模型；Agent J 跑在你自己的机器上，用你自己选的 AI 编程工具和模型。
OpenAI dots
| 维度 | 事实 | 出处 |
|---|---|---|
| 是什么 | OpenAI 放在 ChatGPT 里的全天在线 Agent，可以同时推进多件事，会从你的反馈里学习 | Introducing dots（2026-09-29） |
| 在哪干活 | 每个 dot 有自己的云端电脑和浏览器；你的电脑默认和它分开，你授权后它才能连上 | 同上 |
| 模型 | GPT-6 Astra | 同上 |
| 手机上怎么用 | 在 ChatGPT 桌面、网页和手机上给它发消息或打电话，Slack、Teams 也能发；第一个 dot 要在桌面上创建 | 同上 |
| 多 agent | 现在先有一个主 dot；专项 dot 在企业试点 | 同上 |
| 审批 | 自动审查会决定哪些动作可以继续、哪些要你批准；改密码这类事永远留给你自己 | 同上 |
| 价格 | 第一个 dot 含在 Pro（$100/月起）或 Business Premium 里 | 同上、价格页 |
和 Agent J 的不同：dots 是 OpenAI 替你托管的助理，跑在 OpenAI 的云上，起步价是 Pro 的 $100/月。Agent J 不托管，用你自己的电脑和你已有的订阅；Plus 档的 Codex、Pro 档的 Claude 都能接。
怎么选
- 不想碰电脑、要它全天在线办个人杂事：Meta Muse、OpenAI dots、Grok Bot 这类云端托管的更省事。
- 只用一家工具、只想在手机上接着一个会话干：Claude Code 的 Remote Control 或 Codex 的手机遥控，订阅里就有。
- 愿意自己装、自己维护，想用聊天软件当入口：OpenClaw、Hermes Agent，免费开源。
- 已经在用 Claude Code、Codex 或 OpenCode，想让一个主 Agent 替你管好几条工作流，在手机上派活、批准、看报告：这正是 Agent J 要做的。
想先看需要准备什么，读 Agent J 是什么；准备好了，去 安装指南。
People ask us: Claude Code already has a phone remote, OpenAI just launched dots, Meta has Muse, and everyone seems to be running OpenClaw. So how is Agent J different?
The short answer: they are the same kind of product as Agent J. All of them try to turn AI from something that answers a question into something that gets a job done for you. Where they differ is whose computer the AI works on, whose model it uses, how you direct it from your phone, and how you keep track when there are many jobs at once.
Note: Everything below about other products comes from their official pages, checked on 2026-10-05, with a source on every row. Where the vendor says nothing, we say it is not published; press reports are used only where marked. These products change every week, so their own sites have the final word. What we say about Agent J covers only what is live today.
What they share: a manual for putting AI to work
Our positioning article uses an analogy: the model is the blade, and the way of putting it to work is the martial-arts manual. Every product below is a manual, each with its own style:
- they organize the model, tools and steps so the AI keeps working on its own instead of answering one message at a time;
- most let you hand out work and check progress from your phone;
- all of them stop and ask when a decision belongs to you;
- most can run jobs on a schedule, such as a report every morning.
So the choice isn't whether you get AI. It is which of the differences below matters most to you.
At a glance
| Product | Where the AI works | Whose model | On your phone | Starting price (official) |
|---|---|---|---|---|
| Agent J | Your own computer or your own cloud server | The Claude Code, Codex, OpenCode, Kimi Code or Qwen Code you already use, with your own model account | Web app on your Home Screen | $20 per seat per month, or $200 a year; models paid separately |
| Claude Code (with Remote Control) | Your computer, or Anthropic's cloud VMs | Anthropic's Claude | Claude mobile app, claude.ai/code | Included in Pro, from $20/month |
| OpenAI Codex | Your computer, or OpenAI's cloud sandboxes | OpenAI's models | ChatGPT mobile app | CLI and cloud from Plus, $20/month |
| OpenClaw | Your own computer, server or VPS | Any model, with your own key | Chat apps such as WhatsApp and Telegram | Free and open source; models paid separately |
| Hermes Agent | Your own machine, or optional Nous Portal hosting | Any model | Chat apps such as Telegram, Discord and WhatsApp | Free and open source; hosting from $20/month |
| Meta Muse | A dedicated VM in Meta's cloud | Meta's Muse Spark | Muse app, web, WhatsApp | Free tier and paid tiers |
| Grok Bot (xAI) | Computers in xAI's cloud | xAI's Grok | Grok app | Included in SuperGrok and other plans, usage billed separately |
| OpenAI dots | A computer and browser in OpenAI's cloud | OpenAI's GPT-6 Astra | ChatGPT app | Included in Pro, from $100/month |
Sources are in each section below.
Agent J, for reference
- Where it works: your own computer (Mac or Linux; Windows needs WSL2 first) or your own cloud server. We don't host the AI for you.
- Whose model: Agent J isn't a model. It works through the Claude Code, Codex, OpenCode, Kimi Code or Qwen Code already signed in on your computer; Kimi Code runs on a Kimi membership, Qwen Code on an Alibaba Cloud Model Studio (Bailian) plan, and with OpenCode you can use Bailian, Volcano Engine Ark, DeepSeek or Zhipu GLM. You pay the model company directly.
- On your phone: a web app you add to your Home Screen. Your chats with your Agent are end-to-end encrypted: only your phone and your computer can read them, not us. The one exception is explained on the data security page.
- Many jobs at once: you talk to one main Agent. Behind it sit as many workflows as you need, each with its own Agent in charge, and the main Agent hands out work, reads the reports and fixes what breaks. Scheduled jobs run on your computer, install switched off, and start only when you say yes on your phone.
- Price: $20 per seat per month, or $200 a year. See pricing.
One by one
Claude Code (with Remote Control)
| Topic | Fact | Source |
|---|---|---|
| What it is | Anthropic's coding Agent: CLI, desktop app, web, and a Code tab in the mobile app | Desktop docs |
| Remote Control | Connects your phone or browser to a Claude Code session running on your machine; files, tools and settings stay on your computer, which must stay on with the process running | Remote Control docs |
| Transport | Outbound requests only, no open ports; messages go through Anthropic's servers, and the docs describe TLS | Same |
| Who can use it | Pro, Max, Team and Enterprise; API keys aren't supported | Same |
| Cloud | Cloud sessions run on Anthropic-managed VMs and keep going when your laptop is closed; Routines run in the cloud on a schedule, at most once an hour | Web docs, Routines docs |
| Data | Individual users choose whether their data is used to improve the models | Data usage |
| Price | Pro $20/month; Max $100 or $200/month | Pricing |
How Agent J differs: Remote Control is Claude Code's own phone window and comes with the subscription at no extra cost. If you only use Claude Code and just want to continue one session from your phone, it is enough. Agent J isn't tied to one vendor: it works with Claude Code, Codex and OpenCode, and switching models doesn't change how you use your phone. The other difference is how you manage the work. With Remote Control you open and watch each session yourself; with Agent J you talk to one main Agent, and it looks after the workflows and scheduled jobs behind it.
OpenAI Codex
| Topic | Fact | Source |
|---|---|---|
| What it is | OpenAI's coding Agent: desktop app, open-source CLI (Apache-2.0), IDE extension, cloud, and the ChatGPT mobile app | Codex docs, GitHub |
| Phone remote | The ChatGPT mobile app connects to a Mac, Windows PC or SSH host running Codex: start tasks, follow progress, approve commands, review changes; the computer must stay awake and online | Remote docs |
| Transport | A secure relay layer, in OpenAI's words, so the machine isn't exposed to the internet; whether it is end-to-end encrypted is not published | Remote connections docs |
| Scheduling | Desktop automations run on your computer, which must be on with the app running | Automations docs |
| Price | From Plus at $20/month; the CLI, IDE and cloud need Plus or higher | Pricing |
How Agent J differs: the Codex phone remote controls Codex only, with OpenAI's models and your ChatGPT account. Agent J can use Codex as one of its tools, alongside Claude Code or OpenCode, and on your phone you deal with one main Agent rather than a list of Codex tasks.
OpenClaw
| Topic | Fact | Source |
|---|---|---|
| What it is | An open-source personal AI assistant (MIT) that runs on your own computer; in China, setting one up is nicknamed raising a lobster, after its logo | GitHub, Xinhua report |
| Where it works | Your own laptop, server or VPS; state, memory and credentials live on your machine, with no hosted service in the middle | Docs |
| Models | Any model, with your own key | Same |
| On your phone | Through chat apps you already use: WhatsApp, Telegram, Slack, Signal, iMessage and 20+ more | GitHub |
| Agents and scheduling | Multi-agent routing, scheduled jobs and webhooks | Docs |
| Safety | Incoming messages are to be treated as untrusted input; without a sandbox, tools run directly on your computer | GitHub |
| Price | Free, no paid tier, no telemetry by default | Docs |
How Agent J differs: OpenClaw is a complete Agent program of its own that talks to models directly. Agent J doesn't add another one; it works through the Claude Code, Codex or OpenCode you already have. The phone side differs too: OpenClaw borrows third-party chat apps, so your messages pass through those platforms, while Agent J has its own end-to-end encrypted web app, where anything that needs your OK appears as an approval card. OpenClaw is free, but you install, configure and maintain it yourself; Agent J charges per seat, and the AI on your computer walks you through the install.
Hermes Agent (Nous Research)
Tip: Hermes is also the name of a Nous Research open model family. This section is about the Agent product, Hermes Agent.
| Topic | Fact | Source |
|---|---|---|
| What it is | An open-source Agent (MIT) that turns experience into skills and remembers you across sessions | Website, GitHub |
| Where it works | Your own computer, a VPS, Docker and more, or one-click hosting on Nous Portal | Same, Nous Portal |
| Models | Not tied to a vendor: OpenRouter, OpenAI, Anthropic and others | GitHub |
| On your phone | Through Telegram, Discord, Slack, WhatsApp, Signal or email | Same |
| Agents and scheduling | Subagents and a built-in scheduler | Same |
| Privacy | No telemetry or privacy statement on the official pages; not published | — |
| Price | The Agent is free; Nous Portal plans at $20, $100 and $200/month | Nous Portal |
How Agent J differs: like OpenClaw, Hermes Agent is a separate Agent program with chat apps as its phone side. Agent J works through the AI coding tool you already have and uses its own encrypted channel and approval cards on your phone.
Meta Muse
| Topic | Fact | Source |
|---|---|---|
| What it is | Meta's personal AI agent: it sends email, books trips, fills in forms and checks out for you, and keeps working after you close the app | Meta announcement (2026-09-08) |
| Where it works | A dedicated VM per user in Meta's cloud; a version encrypted with a key only you hold is promised for later this year | Same |
| Model | Meta's own Muse Spark | Same |
| On your phone | iOS, Android, web and WhatsApp; the Mac app can read your Messages, Mail and Notes | Same, Mac help |
| Safety | A separate Sentinel agent has to approve anything Muse sends to the internet | Meta announcement |
| Privacy | Conversations and VM data aren't shared with Meta's ad systems; you can opt out of model training | Same |
| Availability and price | US only, 18+; free and paid tiers | Same |
How Agent J differs: Muse runs in Meta's cloud on Meta's model, so you never touch a computer and it is always on, which suits personal errands. Agent J hosts nothing: the AI works on your own computer or server, with your own tools and files, which suits people who want AI working on their own code, files and workflows.
Grok Bot (xAI)
| Topic | Fact | Source |
|---|---|---|
| What it is | A team of always-on agents, each with its own cloud computer, signed in to your tools and coming back to you only for approvals | Introducing Grok Bot (2026-08-11) |
| Many agents | Run several Bots at once with one as chief of staff over the others; Bots can message each other and work in group chats | Same, Designing Grok Bot |
| Where it works | Each Bot on its own computer in the cloud; on Enterprise, each user's environment is isolated with no access by default | Grok Bot for Enterprise |
| Model | xAI's own Grok | xAI news |
| Scheduling | Automations in Grok run daily, weekly and so on for everyone; email triggers need SuperGrok | Automations in Grok |
| Privacy | Data and training terms specific to Grok Bot are not published | — |
| Price | Included in SuperGrok, Cursor Pro and Cursor Teams plans, with Bot usage billed separately; SuperGrok's dollar prices aren't listed on the official plans page | More plans |
How Agent J differs: Grok Bot letting one Bot run the others is the same idea as Agent J's main Agent running your workflows. The difference is that Grok Bot runs in xAI's cloud on Grok, while Agent J runs on your own machine with the AI coding tool and model you choose.
OpenAI dots
| Topic | Fact | Source |
|---|---|---|
| What it is | OpenAI's always-on Agent inside ChatGPT; it pushes several projects forward at once and learns from your feedback | Introducing dots (2026-09-29) |
| Where it works | Each dot has its own cloud computer and browser; your computer stays separate unless you choose to connect it | Same |
| Model | GPT-6 Astra | Same |
| On your phone | Message or call it in ChatGPT on desktop, web and mobile, or message it in Slack and Teams; your first dot is created on desktop | Same |
| Many agents | One primary dot for now; specialist dots are in an enterprise pilot | Same |
| Approvals | Auto-review decides which actions go ahead and which need you; things like password changes always stay with you | Same |
| Price | Your first dot is included in Pro (from $100/month) or Business Premium | Same, Pricing |
How Agent J differs: dots is an assistant OpenAI hosts for you in its cloud, starting with Pro at $100 a month. Agent J hosts nothing and uses your own computer and the subscriptions you already have; Codex on Plus and Claude on Pro both work.
Which one fits
- You don't want to deal with a computer and want an always-on helper for personal errands: a cloud-hosted product such as Meta Muse, OpenAI dots or Grok Bot is simpler.
- You use one tool and just want to continue a session from your phone: Claude Code's Remote Control or the Codex phone remote, included in your subscription.
- You're happy to install and maintain things yourself and want a chat app as the front door: OpenClaw or Hermes Agent, free and open source.
- You already use Claude Code, Codex or OpenCode and want one main Agent to run several workflows for you, with tasks, approvals and reports on your phone: that is what Agent J is built for.
Read What Agent J is for the prerequisites, or go to Installing when you're ready.