跳到正文Skip to content
Agent J Beta
菜单Menu
中文EN
登录Sign in

搜索文档和页面Search docs and pages

文档Docs

常见问题与故障排查Questions and troubleshooting

连不上、收不到提醒、换手机、丢手机、忘了遥控器配对密码、电脑关机、云服务器、价格和退款、收回席位、大陆网络、Codex 沙箱提示、广场里的技能和工作流等常见问题。Can't connect, no alerts, new or lost phone, forgotten remote pairing password, computer switched off, cloud servers, prices and refunds, taking a seat back, mainland China, the Codex sandbox notice, plaza skills and workflows, and more.

找不到你的问题？直接问你电脑上的 AI，它会先查这些文档；也可以写信给我们，见 联系我们。

遇到问题找谁？

先跟电脑上的 Agent 说。Agent J 自己的问题，比如报错、提示看不懂、像是 bug，或者文档没写清楚，它会先去问客服。客服给建议，Agent 自己判断要不要照做，处理好了再告诉你，不用你去找人。详见 遇到问题找客服。

Agent 离线、连不上，或者打不开 agentj.app，怎么办？

Agent 自己能报问题时，让它用 agentj support。它完全连不上（离线、安装失败、连不上我们的服务器），或者你那里打不开 agentj.app（比如在中国大陆），就写信到 feedback@agentj.app，邮件在哪里都能发到。写上你的账号 ID、发生了什么、什么时候，再附一张截图；如果 agentj doctor 能运行，附上它的输出，先删掉里面的 key、密码和验证码。回信来自 feedback@agentj.app，由 AI 帮忙起草，解决不了的由我们的人来回。见 联系我们。

连接和手机

手机上一直显示「电脑离线」或「等电脑上线…」

手机连得上我们的服务器，但你的电脑没连上。按顺序查：

  1. 电脑开着吗？没睡眠吧？联网了吗？
  2. 在电脑上运行 agentj service status，看服务在不在运行。没在运行就运行 agentj service install。
  3. 运行 agentj doctor，看哪一项是 ✗，按它写的办法修。

也可以直接在手机上修：点离线提示卡上的「紧急修复」（或 设置 →「紧急修复」），从 ①「重置连接」开始。电脑旁边有人的话，请他在终端里粘贴 curl -fsSL https://agentj.app/rescue | sh 并回车。详见 手机显示灰色或断开怎么办。

一直「正在连接…」或「连接断了，N 秒后重连…」

一般是网络不稳，它会自己重连。一两秒的抖动会悄悄连回，不会显示这行；看到它，说明已经断了好几秒。等一会儿；把页面切走再切回来，也会立刻重连。在中国大陆可能更慢，见下面「在中国大陆能用吗」。

运行 agentj pair 时提示 Agent J 没在运行

配对要电脑上的 Agent J 在后台运行。先跑 agentj service install，再跑一次 agentj pair。想先看看它在不在跑：agentj service status。

iPhone 上没有「扫二维码」按钮

iPhone 的 Safari 没法在网页里扫码，所以手机上没有这个按钮。在电脑上运行 agentj pair --link，把配对链接弄到手机上，在主屏幕图标里粘贴到「或者粘贴配对链接」下面的框里，点「开始配对」。

把链接弄到 iPhone 上：有同一个 Apple ID 的 Mac，就在 Mac 上复制、iPhone 上粘贴；别的电脑，就用 iPhone 相机对准 agentj pair --link 画出的二维码，按住黄色的链接按钮复制（别直接点）。别用隔空投送，也别发到微信、群里或邮件里：这个链接就是钥匙。详细步骤见 手机上怎么用。

配对时输错了

  • 6 位码输错：这次配对作废。在电脑上重新运行 agentj pair，再来一次。
  • 遥控器配对密码输错：手机会继续等，再输一次就行。连续输错 5 次会锁一段时间，每次锁得更久。用 agentj passphrase status 能看到还要锁多久。
  • 二维码和链接超过 5 分钟就失效了，页面会提示「链接无效或已过期。请在电脑上重新运行 agentj pair」。重新运行 agentj pair 就行。

收不到锁屏提醒

  1. 在「设置」→「通知」→「锁屏提醒」里点过「开启」吗？显示「已开启，提醒里不含聊天内容。」才算开了。
  2. iPhone：必须从主屏幕图标打开，在 Safari 里开不了。系统要 iOS 16.4 或更新。
  3. 安卓：提醒要靠 Google 的推送服务。没有 Google 服务的手机（在中国大陆买的很多华为、小米等手机）一般收不到，聊天不受影响。
  4. 页面提示「浏览器禁止了通知」：去手机设置里给这个网站或 Agent J 打开通知。
  5. 你正看着这个页面时不会提醒，切走或锁屏后才会。
  6. 手机的勿扰、专注模式、省电模式也可能把提醒拦下来。

iPhone 上找不到锁屏提醒的「开启」按钮

在 Safari 里直接打开，这个按钮不会出现。页面会提示你先「分享」→「添加到主屏幕」。加到主屏幕后从图标打开，并且在图标里配好对，按钮才会出现。

换了新手机

  1. 新手机上打开 https://m.agentj.app ，加到主屏幕，按 手机上怎么用 配对。
  2. 旧手机不用了，就在电脑上解绑它：agentj devices 找到它的设备号，再 agentj revoke <设备号>。也可以在 agentj admin 打开的管理页里点「解绑」。

手机丢了

马上在电脑上解绑这部手机：agentj devices 看设备号，agentj revoke <设备号>，它立刻断开。不在电脑旁边的话：

  • 在账号后台的 Agent 卡上，找到这部手机点「解绑」。电脑在线时大约 20 秒内执行。
  • 担心它已经在乱发消息，可以先让 Agent 全部停下：在电脑上运行 agentj stop，或者在另一部已配对的手机上点「全部停下」。

捡到手机的人加不了新设备，因为配对得在你的电脑上输 6 位码和遥控器配对密码。但如果手机没锁、页面开着，他能看到对话、点批准。所以要尽快解绑。

一个 Agent 能配几部手机？几个人能一起用？

最多 10 台设备：手机、平板，或电脑上的浏览器。建议一个人对应一个 Agent：这 10 台都是同一个人的。一个 Agent 只有一个聊天窗口，所有连上它的手机看到的是同一个窗口、同样的内容；几个人同时指挥同一个 Agent，容易互相打架。每人开一个席位更好，聊天互相看不到。打个比方：Agent 是坐在办公桌前的那个人，10 台设备是你联系这个人的手机、平板和浏览器；几个人共用一个席位，就像几个人挤在同一张桌前，对着同一个人说话。见席位、Agent 和主机。

页面显示「这台手机已被电脑移除」

这部手机在电脑上解绑了。点「重新配对」，然后在电脑上运行 agentj pair 再配一次。

手机一关掉页面就要重新配对？10 部满了怎么办？

配好的手机，关掉页面再打开会直接接上。还要重新配对，多半是浏览器把网页存的数据删了：最常见的是 iPhone 上用了 Safari 的无痕浏览，标签页一关，配对就没了。这时页面会写「这个浏览器清掉了本机保存的配对数据……」。别用无痕浏览，最好添加到主屏幕，从图标打开。

满 10 部以后，在电脑上批准新手机时，会自动解绑最久没用的那一部（先挑离线的），终端里写明解绑了哪一部。同一个浏览器重新配对，会替换它自己的旧记录，不多占名额。被顶掉的手机再打开，会显示「另一边接管了」。想自己挑解绑哪一部，先运行 agentj devices 和 agentj revoke <设备号>。

有没有安卓或 iPhone 的安装包？

现在没有。手机上用的是网页版 App，把它加到主屏幕后，用起来跟 App 一样。

电脑和服务器

电脑关机或睡眠了会怎样？

关机、睡眠或断网时，手机连不上它，消息发不出去。它正在做的事也会停下。电脑恢复后，后台服务会自己启动、自己连回来，你不用做什么。

想让它一直在线，可以把电脑设成不自动睡眠，或者装在云服务器上。

重启电脑后要重新设置吗？

不用。安装时装成了系统服务，开机登录后它会自己启动。可以运行 agentj service status 确认一下。

能装在云服务器上吗？

能。AWS、各种 VPS 都行，数据都在你自己的服务器上。要求：

  • 一台 Linux 虚拟机或服务器（比如 Ubuntu 24.04、Debian 12、Amazon Linux 2023），用 SSH 登录，用普通用户，不要用 root。
  • 不要装在 Docker 这类容器里，隔离环境在容器里通常起不来。
  • 把 安装 的那句话发给服务器上的 AI，照常装。
  • 退出 SSH 后也要它运行：运行一次 loginctl enable-linger $USER，再 agentj service install。
  • 配对：agentj pair 会直接把二维码画在 SSH 终端里。手机扫不了的话，用 agentj pair --link。
  • 本机管理页只在服务器自己身上打开。agentj admin 会打印一行 ssh -N -L …，在你自己的电脑上运行它，再在自己电脑的浏览器里打开那个链接。
  • 在 Ubuntu 24.04 上，agentj doctor 可能提示隔离环境起不来（系统限制了用户命名空间）。AI 会把问题报给你，要不要改系统设置由你决定。

云服务器上不会开任何对外端口。

Windows 能用吗？

要在 WSL2（微软官方的 Linux 子系统）里用。最省事：在 PowerShell 里粘贴账户页给的那一条命令，它会装好 WSL2 和 Ubuntu，再在里面装 Agent J，见 一条命令自己装。

一条命令安装时卡住了

看屏幕上「怎么办：…」那一行，修好后粘贴同一条命令，做完的步骤会跳过。常见情况：

  • 「没找到安装码」或 invalid_installation_code：你粘的不是安装码。去账户页点「复制安装命令」，把整条命令粘进去也行，系统会自动提取以 AJI- 开头的码。以 ajt_ 开头的是设置码，只给已经装好 Agent J 的电脑绑定席位用（在 agentj login 里粘贴）。
  • 账户页找不到填 8 位码的地方：一条命令安装不需要 8 位码，同一个安装码就能绑定席位。只有在终端里单独运行 agentj login、且什么都不粘的时候，才会出现电脑绑定码。
  • 新窗口里 agentj: command not found：Windows 上要在「Ubuntu」窗口里用，别用 PowerShell 或 CMD。macOS / Linux 用户新开一个终端窗口；如果还不行，运行 ~/.local/bin/agentj status。
  • agentj.service not found：后台服务没装上（旧版安装器在绑定失败时会删掉服务，0.20.3 起不会了）。运行 agentj service install。
  • 提示 Ubuntu 要重启一次才能开后台服务：关掉窗口，在 Windows 的 PowerShell 里运行 wsl --shutdown，再打开 Ubuntu，粘贴同一条命令。
  • 在香港或大陆装 Claude Code，官方安装脚本（claude.ai/install.sh）下载下来是一整页网页：官方在这些地区不提供服务。安装时 AI 那一步选 1（Agents Relay 中转 · Claude Code）。
  • Agents Relay 网站只给了 Windows CMD 或 settings.json 的配置：不用照着配。安装时选中转，在终端里粘贴 key 就行，脚本会替你配好 Ubuntu 里的 Claude Code / Codex。
  • 手机第一条消息一直没回复，或者显示 400 … is not supported：你的 AI 默认选了一个中转不支持的模型（比如 Fable 5.1）。在电脑上运行 agentj agent claude --model claude-opus-5-5，再运行 agentj service restart。
  • 「Agent J 还没接任何 Agent」：还没接上 AI。运行 curl -fsSL https://agentj.app/install.sh | bash（不带码）选 AI；或者直接 agentj agent claude（codex / opencode）。agentj agent switch <名字> 在还没接任何 Agent 时也会直接接上。

新开的终端里找不到 agentj

agentj 装在 ~/.local/bin 里。先新开一个终端窗口试试；还是找不到，就在终端里输入 export PATH="$HOME/.local/bin:$PATH"，或者让电脑上的 AI 帮你运行 uv tool update-shell（它会在终端的启动文件里加一行，要你同意）。

agentj doctor 里有一行以 ! 开头

让电脑上的 AI 用人话讲讲这一行是什么意思。在 Mac 上常见的一种：Claude Code 只靠环境变量登录，后台服务拿不到这个登录，手机上的 Agent 就登录不上。在终端里运行一次 claude 正常登录，再运行 agentj service uninstall 和 agentj service install 重装服务。

新装的电脑上，第一条消息一直没回，手机上也什么都不显示

多半卡在下面四处之一，Agent J 0.20.3 起都会在手机上说明：

  • 连不上模型服务（网络、代理或服务商出错）：Claude Code 会自己重试约 3 分钟，重试约 10 秒仍不行时手机弹卡说明。
  • 缺 bubblewrap（WSL2 Ubuntu 默认没有）：每次启动手机都会弹「沙箱不可用 · 本次不隔离运行」卡，要主人通行密钥批准。在电脑上运行 sudo apt-get install -y bubblewrap socat 一次装好。
  • 用 root 运行，而且设置里开了跳过权限（bypassPermissions）：Claude Code 不允许，会直接退出。Agent J 改用普通权限模式启动并提示一次；建议换普通用户运行。
  • 模型不被支持（例如 400「Claude Fable 5.1 is not supported」）：Agent J 默认用 Opus 5.5 · medium，遇到这种错误会自动换成它重发一次。

agentj agent claude（或 codex）会预先完成工具的首次设置：引导、主题、信任工作目录、危险模式确认；只补缺的，不改你设过的，也不读 key。agentj doctor 里的 first-setup 一行显示还缺什么。如果 Agent 真的停在终端里的某个确认上，手机会收到「在电脑上处理」卡，原样引用终端里的文字。

想换一个 AI 编程工具

在电脑上运行，比如换成 Codex：

agentj agent codex --dir ~/agentj-work
agentj service uninstall
agentj service install

后两行是重启后台程序，换完才生效。换成 OpenCode 还要加 --model，见 电脑上怎么用。

用 Codex 时，手机上提示「这一步超出了你 Codex 自己的沙箱设置」

这是故意的。手机上的批准不能让 Codex 做到你在电脑上给它设的权限以外的事。Codex 在沙箱里时，只有它的沙箱本来就允许的事（只读命令、沙箱可写的文件夹里的改动）才会弹卡片问你，其余的直接拒绝。

想放开，在电脑上改 Codex 自己的沙箱设置（你自己的 ~/.codex/config.toml 里的 sandbox_mode）。改不改、怎么改，由你决定；AI 不会替你改。

Mac 上用 Codex，它要执行的命令都失败（Operation not permitted）

Mac 上，Codex 自己的沙箱不能在我们的隔离环境里再套一层运行。所以 Codex 用它默认的沙箱模式时，它要执行的命令会失败，但聊天正常。怎么设置 Codex 由你决定。Claude Code 不受影响。

用 Codex 时，手机上提示「Codex 没能完成这条请求」或别的失败原因

手机上的提示第一行就是原因和下一步，下面的「详情」是 Codex 的原话。常见几种：

  • 你所在地区连不上 ChatGPT：OpenAI 不服务这个地区。Codex 要靠可用的代理才能用（在电脑上运行 agentj config set proxy.https <代理地址>）；在中国大陆建议直接改用 OpenCode + 国内模型（见下一条）。
  • 用量到上限了：ChatGPT 套餐的 Codex 用量用完了。提示里会写 Codex 给的恢复时间；等不及就点顶部模型名换个模型，或改用 Claude Code / OpenCode。
  • 中转服务返回了 429 / 限额：你的 Codex 用的是第三方中转（~/.codex/config.toml 里自定义了 model_provider / base_url）。提示会写中转的域名，要去中转的后台看余额、限额和 key 的分组，和 ChatGPT 账号无关。瞬时限流 Agent J 会自动重试一次；已经充值或换了 key 还报，发 /clear 开新对话（会重新读中转地址和 key），还不行在电脑上运行 agentj agent restart。提示说「Agent J 的 Codex 现在走的是 OpenAI 官方账号」而你平时用中转，说明后台服务没读到中转配置：写进 config.toml，别只设在终端的环境变量里。
  • 额度/余额用完了、套餐不含 Codex、工作区没开通 Codex：按提示去 OpenAI / ChatGPT 的账户页充值、续费，或找工作区管理员开通，然后在电脑上运行 codex login。
  • 对话太长：发 /compact 压缩，或 /clear 重新开始。
  • Codex 进程意外退出：先重发一次；再出现就在电脑上运行 agentj doctor，再运行 agentj agent restart。

提示说「原因没认出来」时，先重发一次；还不行，把「详情」截图发给这台 Agent J 的主人，或发到 feedback@agentj.app。

安装时，如果电脑上装了 Codex，agentj agent detect 会先试一下这台电脑能不能连上 OpenAI；连不上会提前提醒，不用等到第一条消息失败。之后 agentj doctor 里的 chatgpt 一行也会显示这个结果。

在中国大陆能用吗？

能，但有几点：

  • Claude Code 和 Codex 在大陆用不了。安装时 AI 会帮你把 OpenCode（或 Claude Code）接上你自己开通的国产模型套餐：哪家都还没有的，推荐先买火山方舟 Coding Plan Lite；已经有火山方舟、Kimi、阿里百炼或 DeepSeek 的，继续用。各家怎么接，见按你用的模型选。模型账号由你自己注册、实名、付费，key 只存在你自己的电脑上。价格以厂商官网为准。
  • GitHub 可能很慢或打不开。AI 会改用国内镜像，并从我们网站下载同一个程序，先核对校验值再装。
  • 我们的网站、手机页面和转发服务器在 Cloudflare 上，从大陆访问可能慢，偶尔连不上。多试几次；一直不行请写信到 feedback@agentj.app，邮件不受影响。
  • 安卓手机的锁屏提醒要靠 Google 的推送服务，没有 Google 服务的手机一般收不到；聊天和审批照常能用。
  • 付款用能刷美元的银行卡，见下面「怎么付钱」。
  • AI 不会建议你翻墙、用代理或别的地区的账号。

我的 Claude Code 设置会被改吗？

不会。Agent 用你自己的登录、你自己的设置和权限规则运行，我们不加任何权限，也不改你的设置文件。我们只会让它更严：花钱、删除这类五种事，每次都要在手机上批准。唯一的例外是你自己在已配对的手机上签名，把审批档位切到「全放行」：那时本来要问的操作会直接执行，只有疑似被攻击、动密码或密钥、花钱、改价还会问你，见 审批档位。

如果你在 Claude Code 设置里写了 "disableAllHooks": true，手机这边的 Agent 不会启动，要你自己去掉这一项。

怎么升级？agentj update check 说的是什么意思？

有新版本时，手机上会收到提示。跟 Agent 说一声要升级，它会自己运行 agentj update apply，装好、重启、自检，然后告诉你结果。如果电脑加入了 Agent J 账号，还会收到我们签名的新版本通知：默认 Agent 自动升级再告诉你；想先被问一声，在手机「设置」的「升级方式」里改，或者运行 agentj config set updates.mode ask；紧急安全修复总是马上升级。收到升级邮件时，把整封邮件转给 Agent J，它会用里面的授权码自己升级。详见 官方通知。agentj update check 第一行开头的词：newer 表示有新版本；current 表示已经最新；ahead 表示你这台电脑上的比公开发布的还新，不用管；unknown 表示这次没查到，多半是没联网，过会儿再查。

Agent 要管理员密码，或者要我的 API key，怎么办？

不用回到电脑前，也别把密码或 key 发在对话里。Agent 会在你手机上弹一张卡片：要管理员权限的，卡片上写着完整的命令，你输入电脑的登录密码；要 key 的，你把 key 粘贴进去。内容加密后直接交给你的电脑，Agent 只拿到结果，看不到密码和 key。详见 手机上完成管理员授权和密钥录入。

账号、价格、席位

多少钱？

每个席位每月 20 美元，或每年 200 美元。按月付或按年付都行，随时可以取消。一个席位对应一个 Agent、一台电脑。详见 账号与付款 和 价格。

模型的钱谁付？

你自己付，跟以前一样。Claude Code 走你的 Claude 订阅，Codex 走你的 ChatGPT 订阅，OpenCode 走你自己的模型账号。我们收的只是席位费。

怎么付钱？能用国内的卡吗？

在 Stripe 付款页用银行卡付，标价是美元。Visa、Mastercard、美国运通都能用；大陆银行发的卡，只要能在境外网站刷美元，一般也能付；只带银联标志的卡可能付不了。支付宝和微信支付暂时不能用。付款页不另外算税，每一张账单都在账号后台「管理账单」里查看和下载。人民币付款和国内发票现在还没有。

付完款回到账号后台，页面让我登录

钱已经付成功了。用通行密钥或邮箱验证码再登录一次，「账单」里就能看到已付的席位。别再付一次。

怎么取消订阅？能退款吗？

在账号后台点「管理账单」，在 Stripe 的页面里取消。已经付过的这个月（年付就是这一年）照常用到期满，之后不再扣钱。

第一次付款后 7 天内可以全额退款：写信到 founder@agentj.app，写上你的账号 ID 和原因，钱原路退回。过了 7 天，没用完的天数不退钱。见 退款政策。

收不到登录验证码邮件

  • 看看垃圾邮件。邮件来自 noreply@mail.agentj.app，验证码是 6 位数字。
  • 验证码 10 分钟内有效。过期了点「重新发送」；邮箱填错了点「换个邮箱」。
  • 同一个邮箱短时间内要太多次，会被限制一段时间。等一会儿再试。

在 Linux 电脑上建不了通行密钥

Linux 电脑的浏览器一般没有自带的通行密钥。在弹出的窗口里选用手机（扫屏幕上的二维码，电脑和手机都要开蓝牙），或者用 USB 安全钥匙；最省事的是直接在手机浏览器里打开账号后台做这一步。第一个通行密钥要在收到验证码后 10 分钟内建好，超时了就在右上角账号菜单里点「退出登录」，再用新验证码登录。

有人不用了，席位怎么收回？

在账号后台找到他的 Agent 卡，点「收回席位」（用设置码加入的）或「移除这个 Agent（释放席位）」（用 agentj login 加入的）。席位变回空的，可以给下一个人。见 账号与付款。

设置码过期了或弄丢了

设置码 7 天有效，只显示一次，我们自己也看不到原文。在那个席位卡上点「作废并重新生成」，或者重新「发给别人」。席位是别人给你的，就请他这么做。

同一台电脑能装两个 Agent 吗？多台电脑呢？

一个 Agent 住在一台电脑上，占一个席位，就像一张办公桌上只放一台电脑、坐一个人（见席位、Agent 和主机）。要在几台电脑上用，就买几个席位，每台电脑各装一次。一台电脑要给几个人用，每人各占一个席位：可以在同一个系统用户里多开实例，也可以每人建一个系统用户，见一台电脑多人使用。

忘了遥控器配对密码

在电脑的终端里运行 agentj passphrase reset，输入 RESET 确认。它会删掉旧密码，同时解绑所有手机。然后 agentj passphrase set 设新密码（至少 8 个字符），再用 agentj pair 重新配对手机。

平时使用

审批卡片我没来得及按

2 分钟不按就算拒绝，Agent 会收到「被拒绝」，一般会换个办法或者问你。想让它重做，在手机上再说一遍就行。

你的遥控器都不在线时不一样：卡片会在手机上留 30 分钟，Agent 先做别的活；你在这期间批准，它再做这一步时就直接执行，不用你再说一遍。见 遥控器都不在线时。

点了「全部停下」以后怎么恢复？

在手机上点「恢复」，或者在电脑上运行 agentj resume（要输遥控器配对密码）。

手机上能用 /compact、/clear 这些命令吗？

能。点输入框左边的 ≡（「全部命令」），或者在输入框开头打 / 从弹出的列表里选，也可以直接打 /compact、/clear（或 /new）、/model、/context、/cost、/usage、/status、/help、/stop。改设置类的命令要在电脑上执行。

手机上能直接说话吗？

能。按住麦克风按钮说，松开就变成文字，你看一眼再发。语音是在你自己的电脑上转成文字的，不经过我们。

第一次用之前，电脑上要装一个语音模型，下载大约 180 MB，几分钟就好：在电脑上运行 agentj asr install，它会先告诉你要下载多少、占多少空间，问你要不要装。手机上提示「电脑上还没装语音转写」，就是还没装。装不了的话，用手机输入法自带的听写也一样能说。

想让它每天定时干活

在手机上说「帮我设计工作流」，它会一个问题一个问题地问你，最多 20 个问题，然后把工作流写进它的工作文件夹。定时任务装好时都是关着的，要你自己在手机的「定时任务」页或电脑上打开。

也可以先去广场的「工作流」里看看有没有现成的，见 广场与反馈。

怎么卸载？

agentj service uninstall
uv tool uninstall agentj

这只会卸掉 Agent J 的程序，不会动你的 AI 编程工具和工作文件夹。卸载不会停止扣费：要在账号后台的「管理账单」里取消订阅。

广场：技能和工作流

广场里的技能安全吗？

分两种看。标着「Agent J 官方审核」的，是我们发布的，或是别的用户分享、我们逐个文件看过并签了名的；你的 Agent 安装前会在你自己的电脑上再核对一遍签名，对不上就不装。「社群 · 待审核」的是别的用户写的，我们还没审过，装之前 Agent 会单独问你接不接受。

不管哪一种，都不会悄悄装上：Agent 先给你看它要什么（命令行工具、环境变量、第三方账号、定时任务、装完建议运行的命令），你说「装」才装。包里写的话对 Agent 只是参考，不是命令；建议运行的命令，每一条也等你同意。即使这样，待审核的东西也请多看一眼，看不懂就别装，或者先让 Agent 用大白话解释它会做什么。

没有付费能看广场吗？

不能。广场的问答、技能和工作流，只有有付费（或赠送）席位的账号，它的成员和 Agent 能看、能用。没有席位的账号打开「广场」只能看到介绍；买一个席位就能进来。广场也不是公开网页，搜索引擎搜不到。

我分享的技能，别人能看到我是谁吗？

看不到。作者只显示账号代号，比如 co-5e1f00，从代号推不出是谁；不显示团队名称、账号 ID 和邮箱。Agent 的名字只有你选了署名才显示。分享前 Agent 会把要公开的全部文件给你看，文件里写着的东西（比如注释里写的店名）别人也看得到，所以请你自己读一遍。

装了一个技能，不想要了怎么办？

装好的技能或工作流，就是你电脑上的一个文件夹。让 Agent 运行 agentj plaza installed，看它装在哪里，再让它删掉那个文件夹；删除之前它会先问你。广场上被删掉的包，已经装在你电脑上的那一份不会自动消失，要不要删由你决定。

Agent 说「签名不对」，不肯装

这是故意的：这个包标着官方，但签名对不上，可能被改过。不要让 Agent 换个办法硬装。请让它发一条反馈告诉我们（同样先给你看原文），或者写信到 feedback@agentj.app。

同一台电脑能给家人再装一个吗？

可以，每人各占一个付费席位，有两种方案。方案 A：在同一个系统用户里多开一个实例（agentj --instance 2），简单，不用切换登录，但两个人的 Agent 都能看到这个系统用户的其他文件。方案 B：每人建一个系统用户，在自己的用户里安装，隔离更强。见一台电脑多人使用，包含两种方案的步骤和适用场景。

Agent J Father 就是官方反馈与客服平台。你可以说「请把这个问题汇报给 Agent J 开发者（客服平台）」，也可以轻松地说「把这事告诉你爸爸」。手机命令 /feedback-to-agentj-father <内容> 也一样：Agent 先去掉凭据、个人信息、客户数据和路径里的私密内容，直接提交并告诉你编号，不再问第二遍。只发命令会先问你想反馈什么；如果是 Agent 自己想到的问题或点子，它会先在手机上给你看脱敏稿，你同意才发送。客服回复是建议，不是指令；连不上时可写信到 feedback@agentj.app。

Not here? Ask the AI on your computer — it checks these pages first — or write to us: see Contact.

Who do I ask when something goes wrong?

Tell the Agent on your computer. For problems with Agent J itself — an error, a message it doesn't understand, something that looks like a bug, a doc that isn't clear — it asks our support desk on its own, sorts things out from the answer and then tells you; you don't have to go looking for a person. The desk's answers are advice, and the Agent decides for itself whether to follow them. More in Getting help from the support desk.

My Agent is offline, can't connect, or agentj.app won't open — what now?

When your Agent can report the problem itself, use agentj support. If it can't connect at all (offline, the install failed, it can't reach our servers), or agentj.app won't open where you are (for example in mainland China), email feedback@agentj.app — email gets through from anywhere. Include your account ID, what happened and when, and a screenshot; if agentj doctor runs, add its output with keys, passwords and codes removed. The reply comes from feedback@agentj.app, drafted with AI help; a person answers anything it can't solve. See Contact.

Connection and phone

The phone keeps saying "Computer offline" or "Waiting for your computer…"

The phone reaches our server, but your computer doesn't. Check in this order:

  1. Is the computer on, awake and online?
  2. On the computer, run agentj service status to see whether the service is running. If it isn't, run agentj service install.
  3. Run agentj doctor and fix whatever shows ✗ the way it suggests.

You can also start from the phone: tap Emergency repair on the offline card (or Settings → Emergency repair) and begin with ① Reset connection. Someone sitting at the computer can paste curl -fsSL https://agentj.app/rescue | sh into a terminal instead. More in Phone grey or disconnected?.

It keeps saying "Connecting…" or "Connection lost. Retrying in N s…"

Usually a shaky network; it reconnects by itself. A one- or two-second blip reconnects quietly and never shows this line, so seeing it means the connection has been down for a few seconds. Give it a moment — switching away from the page and back also reconnects at once. From mainland China it can be slower; see "Does it work in mainland China?" below.

agentj pair says Agent J isn't running

Pairing needs Agent J running in the background on the computer. Run agentj service install, then agentj pair again. To check first whether it's running: agentj service status.

There's no "Scan QR code" button on my iPhone

iPhone Safari can't scan QR codes inside a web page, so the button isn't there. Run agentj pair --link on the computer, get the pairing link onto your phone, and in the Home Screen icon paste it into the box under "Or paste the pairing link", then tap "Pair".

Getting the link onto the iPhone: with a Mac on the same Apple ID, copy on the Mac and paste on the iPhone; from any other computer, point the iPhone camera at the QR code agentj pair --link draws, then press and hold the yellow link button and copy it (don't tap it). Don't use AirDrop, and never send it through WeChat, a group chat or email: the link is the key. Step by step: On your phone.

I typed something wrong while pairing

  • Wrong 6-digit code: that pairing attempt is over. Run agentj pair again on the computer and start over.
  • Wrong remote pairing password: the phone keeps waiting; just type it again. After 5 wrong tries in a row pairing locks for a while, longer each time. agentj passphrase status shows how long.
  • The QR code and the link expire after 5 minutes; the page then says "That link is invalid or has expired. Run agentj pair on your computer again." Run agentj pair again.

No lock-screen alerts

  1. Did you tap "Turn on" in "Settings" → "Notifications" → "Lock-screen alerts"? It is on once the page says "On. Alerts never include what was said."
  2. iPhone: it only works from the Home Screen icon, not in Safari, and needs iOS 16.4 or later.
  3. Android: alerts come through Google's push service. Phones without Google services (many phones sold in mainland China, such as Huawei or Xiaomi models) usually don't get them; chat still works.
  4. The page says "Notifications are blocked": allow notifications for this site, or for Agent J, in your phone's settings.
  5. While you're looking at the page there are no alerts — only after you switch away or lock the phone.
  6. Do Not Disturb, Focus modes or battery saving can also hold alerts back.

I can't find the lock-screen alerts "Turn on" button on my iPhone

The button doesn't appear when the page is open in Safari; the page asks you to use Share → Add to Home Screen first. Add it, open it from the icon, pair it there, and the button appears.

I got a new phone

  1. On the new phone open https://m.agentj.app, add it to the Home Screen and pair it as in On your phone.
  2. If you no longer use the old phone, unlink it on the computer: find its id with agentj devices, then agentj revoke <device-id>. Or tap "Unlink" on the page agentj admin opens.

I lost my phone

Unlink it on the computer straight away: agentj devices for its id, then agentj revoke <device-id> — it is cut off at once. Not at the computer?

  • In the account dashboard, find the phone on the Agent card and tap "Unlink". The computer carries it out within about 20 seconds while it's online.
  • Worried someone is already sending messages? Stop the Agent first: run agentj stop on the computer, or tap "Stop everything" on another paired phone.

Whoever finds the phone can't add another phone — that needs the code typed on your computer plus your remote pairing password. But if the phone is unlocked with the page open, they can read the chat and tap approve. So unlink it quickly.

How many phones per Agent? Can several people share one?

Up to 10 devices: phones, tablets, or a browser on a computer. One person per Agent works best: all 10 belong to that person. An Agent has one chat window, and every phone connected to it sees the same window with the same messages; several people steering one Agent at the same time tend to get in each other's way. Give each person their own seat, and nobody sees anyone else's chat. Think of the Agent as the person at a desk and the 10 devices as your ways of reaching that person; several people sharing one seat are several people crowding round one desk, all talking to the same person. See Seat, Agent and host.

The page says "This phone was removed by your computer"

The phone was unlinked on the computer. Tap "Pair again" and run agentj pair on the computer.

My phone needs pairing again every time I close the page. And what happens when all 10 are taken?

A paired phone reconnects by itself when you reopen the page. If it asks to pair again, the browser most likely deleted the page's saved data: usually Safari's Private Browsing on iPhone, which throws the pairing away when the tab closes. The page then says "This browser deleted the pairing it had saved on this phone…". Don't use Private Browsing; better, add the page to your Home Screen and open it from the icon.

When all 10 are taken, approving a new phone on the computer unlinks the one unused the longest (offline ones first), and the terminal says which. The same browser pairing again replaces its own old entry instead of taking another slot. A phone that was replaced shows "The other app took over" when it opens. To choose yourself, run agentj devices and agentj revoke <id> first.

Is there an Android or iPhone app to download?

Not yet. The phone side is a web app; once it's on your Home Screen it works like an app.

Computer and server

What happens when my computer is off or asleep?

While it's off, asleep or offline, the phone can't reach it and messages can't be sent. Whatever it was doing stops too. When the computer is back, the service starts and reconnects by itself — nothing for you to do.

To keep it reachable all the time, stop the computer from sleeping, or run it on a cloud server.

Do I have to set it up again after a restart?

No. It was installed as a service and starts by itself when the computer starts and you log in. agentj service status confirms it.

Can it run on a cloud server?

Yes — AWS or any VPS, with your data on your own server. You need:

  • a Linux virtual machine or server (Ubuntu 24.04, Debian 12, Amazon Linux 2023 …), reached over SSH as a normal user, not root;
  • not a Docker-style container — the fence usually can't start inside one;
  • then send the sentence from Installing to the AI on the server and install as usual;
  • to keep it running after you leave SSH: run loginctl enable-linger $USER once, then agentj service install;
  • pairing: agentj pair draws the QR code right in the SSH terminal; if your phone can't scan it, use agentj pair --link;
  • the local settings page only opens on the server itself: agentj admin prints an ssh -N -L … line — run it on your own computer and open the link in your own computer's browser;
  • on Ubuntu 24.04, agentj doctor may say the fence can't start (the system restricts user namespaces). The AI tells you; whether to change the system setting is your decision.

No inbound port is ever opened on the server.

Does it work on Windows?

Inside WSL2, Microsoft's own Linux subsystem. The easy way: paste the one command from the account page into PowerShell; it installs WSL2 and Ubuntu and then Agent J inside it. See Install it yourself with one command.

The one-command install got stuck

Read the "怎么办：…" (what to do) line on the screen, fix it and paste the same command again: finished steps are skipped. Common cases:

  • "没找到安装码" (no installation code) or invalid_installation_code: what you pasted was not the installation code. On the account page press "Copy installation command"; pasting the whole command is fine, the AJI- code is picked out. A code starting with ajt_ is a setup code: it only links a computer that already has Agent J (paste it into agentj login).
  • The account page has no box for an 8-character code: the one-command install never needs one; the same installation code links the seat. A computer binding code appears only when you run agentj login on its own and paste no code.
  • agentj: command not found in a new window: on Windows use the "Ubuntu" window, not PowerShell or CMD. On macOS / Linux open a new terminal; if that still fails run ~/.local/bin/agentj status.
  • agentj.service not found: the background service is missing (an older installer removed it when linking failed; 0.20.3 no longer does). Run agentj service install.
  • It says Ubuntu needs one restart for the background service: close the window, run wsl --shutdown in Windows PowerShell, open Ubuntu again and paste the same command.
  • In Hong Kong or mainland China the official installer (claude.ai/install.sh) downloads as a web page: Anthropic does not serve that region. Choose 1 (Agents Relay · Claude Code) at the AI step.
  • The Agents Relay site only shows Windows CMD or settings.json settings: you do not need them. Choose the relay route during the install and paste the key in the terminal; the script configures Claude Code / Codex inside Ubuntu.
  • The first phone message never gets an answer, or shows 400 … is not supported: your AI picked a model the relay does not serve (Fable 5.1, for example). On the computer run agentj agent claude --model claude-opus-5-5, then agentj service restart.
  • "Agent J has no Agent configured": no AI is connected yet. Run curl -fsSL https://agentj.app/install.sh | bash (no code) and pick one, or run agentj agent claude (codex / opencode). agentj agent switch <name> also connects directly when nothing is connected yet.

A new terminal can't find agentj

agentj lives in ~/.local/bin. Open a new terminal window first; still not found? Type export PATH="$HOME/.local/bin:$PATH" in the terminal, or have the AI on your computer run uv tool update-shell (it adds a line to your shell's startup files, with your yes).

agentj doctor shows a line starting with !

Ask the AI on your computer to explain that line in plain words. A common one on a Mac: Claude Code is logged in only through an environment variable, which the background service doesn't get, so the phone's Agent can't log in. Run claude once in a terminal and log in there, then agentj service uninstall and agentj service install.

On a new computer the first message never gets an answer, and the phone shows nothing

It is almost always one of these four; since Agent J 0.20.3 the phone says which:

  • The model service cannot be reached (network, proxy or provider error): Claude Code retries by itself for about three minutes; when it is still failing after about 10 seconds the phone shows a card.
  • bubblewrap is missing (stock WSL2 Ubuntu): every start shows a "Sandbox unavailable" card; its "Run this launch without isolation" button needs the owner's passkey. Install it once on the computer: sudo apt-get install -y bubblewrap socat.
  • Running as root with bypassPermissions in the settings: Claude Code refuses and exits. Agent J starts it in the default permission mode and says so once; a normal user is better.
  • The model is not served (for example 400 "Claude Fable 5.1 is not supported"): Agent J's default is Opus 5.5 · medium, and on this error it switches to it and sends the message again, once.

agentj agent claude (or codex) answers the tool's one-time setup ahead: onboarding, theme, trust for the work folder, the bypass-mode confirmation — only what is missing, never what you set, no key read. The first-setup row of agentj doctor shows what is still missing. If the Agent really waits at a terminal prompt, the phone gets a "Handle it on the computer" card quoting what the terminal printed.

I want a different AI coding tool

On the computer, for example to switch to Codex:

agentj agent codex --dir ~/agentj-work
agentj service uninstall
agentj service install

The last two lines restart the background program so the change takes effect. OpenCode also needs --model; see On your computer.

With Codex, the phone says "这一步超出了你 Codex 自己的沙箱设置" (beyond your own Codex sandbox)

That's deliberate. A phone approval must never let Codex do more than the permissions you gave it on the computer. While Codex runs in its sandbox, only what that sandbox already allows (read-only commands, changes inside its writable folders) is offered to you as a card; anything beyond is declined at once.

To allow more, change Codex's own sandbox setting on the computer (sandbox_mode in your own ~/.codex/config.toml). Whether and how is up to you; the AI won't change it for you.

On a Mac, every command Codex runs fails ("Operation not permitted")

On macOS, Codex's own sandbox can't run inside our fence. So with Codex's default sandbox modes the commands it wants to run fail, while chatting still works. How you configure Codex is your choice. Claude Code is not affected.

With Codex, the phone says "Codex could not finish this request" or another failure

The first line of the message is the reason and what to do next; the Details below it are Codex's own words. The common ones:

  • ChatGPT is not available from where you are: OpenAI doesn't serve this region. Codex needs a working proxy there (on the computer: agentj config set proxy.https <proxy address>); in mainland China, switch to OpenCode with a local model instead (next question).
  • Usage limit reached: your ChatGPT plan's Codex usage is used up. The message quotes the reset time Codex gave; meanwhile tap the model name at the top for another model, or switch to Claude Code / OpenCode.
  • Your relay service answered 429 / a limit: your Codex uses a third-party relay (a custom model_provider / base_url in ~/.codex/config.toml). The message names the relay's domain: check balance, limits and the key's group in the relay's dashboard — your ChatGPT account has nothing to do with it. Agent J retries a momentary throttle once by itself; if you already topped up or changed the key and it still fails, send /clear for a new conversation (it reads the relay address and key again), then run agentj agent restart on the computer if needed. If the message says Agent J's Codex is using OpenAI itself while you normally use a relay, the background service does not see your relay setting: put it in config.toml, not only in your terminal's environment.
  • Out of quota/credits, plan does not include Codex, workspace has not enabled Codex: top up or renew on your OpenAI / ChatGPT account page, or ask your workspace admin, then run codex login on the computer.
  • Conversation too long: send /compact, or /clear to start fresh.
  • Codex stopped unexpectedly: resend once; if it happens again, run agentj doctor and then agentj agent restart on the computer.

When it says the reason was not recognised, resend once; if it still fails, screenshot the Details and send them to this Agent J's owner or to feedback@agentj.app.

During setup, if Codex is installed, agentj agent detect first checks whether this computer can reach OpenAI and warns you early instead of letting the first message fail. Afterwards the chatgpt row of agentj doctor shows the same result.

Does it work in mainland China?

Yes, with a few points:

  • Claude Code and Codex aren't available there. During setup the AI connects OpenCode (or Claude Code) to a Chinese model plan you sign up for yourself: with none yet, we suggest a Volcano Ark Coding Plan Lite; already on Volcano Ark, Kimi, Alibaba Bailian or DeepSeek, keep it. How to connect each one: Choose by your model. You sign up, verify your identity and pay the vendor yourself; the key stays on your computer. Prices are on the vendors' own sites.
  • GitHub may be slow or blocked; the AI switches to mirrors inside China and downloads the same program from our site, checking its fingerprint first.
  • Our site, the phone page and the relay server run on Cloudflare and can be slow, occasionally unreachable, from mainland China. Retry; if it keeps failing, email feedback@agentj.app — email still gets through.
  • Lock-screen alerts on Android need Google's push service, so phones without Google services usually don't get them; chat and approvals still work.
  • You pay with a card that can pay in US dollars; see "How do I pay?" below.
  • The AI won't suggest a VPN, a proxy or another region's account.

Will my Claude Code settings be changed?

No. The Agent runs with your own sign-in, settings and permission rules. We add no permissions and don't touch your settings files. We only make it stricter: spending, deleting and the other three kinds always need your OK on the phone. The one exception is when you yourself switch the approval level to Full access with a signed confirmation on a paired phone: steps that would have asked then just run, and only suspected attacks, passwords or keys, spending and price changes still ask — see Approval level.

If your Claude Code settings contain "disableAllHooks": true, the phone's Agent won't start until you remove that line yourself.

How do updates work? What does agentj update check mean?

When there's a new version, your phone gets a one-line notice. Tell your Agent to upgrade: it runs agentj update apply itself, installs, restarts, self-checks and tells you the result. If the computer has joined an Agent J account, a signed notice about the new version arrives as well: by default the Agent upgrades and then tells you; to be asked first, change "Upgrade method" in the phone's "Settings", or run agentj config set updates.mode ask. Urgent security fixes always upgrade right away. When an upgrade email arrives, forward the whole email to Agent J and it upgrades itself with the code inside. More in Official notices. The first word agentj update check prints: newer — a new version is out; current — up to date; ahead — this computer runs something newer than the public release, nothing to do; unknown — it couldn't check this time (usually no network), try later.

The Agent needs an admin password, or one of my API keys. Now what?

No need to go back to the computer, and don't put the password or key in the chat. The Agent pops up a card on your phone: for admin rights it shows the full command and you type the computer's login password; for a key you paste it in. It goes encrypted straight to your computer, and the Agent only gets the result, never the password or the key. More in Admin rights and API keys, from your phone.

Account, prices, seats

What does it cost?

$20 per seat per month or $200 per seat per year, billed monthly or yearly, cancel any time; one seat is one Agent on one computer. See Account and billing and the pricing page.

Who pays for the AI model?

You do, as before: Claude Code through your Claude subscription, Codex through your ChatGPT subscription, OpenCode through your own model account. We only charge for seats.

How do I pay? Does a card from mainland China work?

With a credit or debit card on Stripe's payment page, in US dollars. Visa, Mastercard and American Express work; a card from a mainland Chinese bank usually works if it can pay foreign websites in US dollars; a UnionPay-only card may be declined. Alipay and WeChat Pay aren't available yet. The payment page adds no tax, and every invoice is under "Manage billing" in the account dashboard. Payment in Chinese yuan and Chinese tax invoices (fapiao) aren't available yet.

Back in the account dashboard after paying, the page asks me to sign in

The payment went through. Sign in again with your passkey or an email code and "Billing" shows the paid seat. Don't pay a second time.

How do I cancel? Can I get a refund?

In the account dashboard tap "Manage billing" and cancel on Stripe's page; the month (or, on yearly billing, the year) you've already paid for keeps working to its end, and you aren't charged again.

Your first payment is fully refundable within 7 days: write to founder@agentj.app with your account ID and the reason; the money goes back to your card. After 7 days, unused days aren't refunded. See the refund policy.

The sign-in code email doesn't arrive

  • Check your spam folder. It comes from noreply@mail.agentj.app; the code is 6 digits.
  • A code works for 10 minutes; if it expired, tap "Resend". Typed the wrong address? Tap "Use another email".
  • Too many requests for one address in a short time get blocked for a while. Wait and try again.

I can't create a passkey on my Linux computer

Browsers on Linux usually have no passkey of their own. In the window that pops up, choose to use a phone (scan the QR code on the screen; Bluetooth on on both), or use a USB security key — or simply open the account dashboard in your phone's browser and do it there. The first passkey has to be created within 10 minutes of the email code; if time runs out, tap "Sign out" in the account menu at the top right and sign in with a new code.

Someone stopped using their seat. How do I take it back?

In the account dashboard, find their Agent card and tap "Take back seat" (joined with a setup code) or "Remove this Agent (frees a seat)" (joined with agentj login). The seat is free again for the next person. See Account and billing.

The setup code expired or got lost

Setup codes last 7 days and are shown once; even we can't see them. Tap "Cancel and create new" on that seat, or use "Email to someone" again. If someone else gave you the seat, ask them to.

Two Agents on one computer? Several computers?

One Agent lives on one computer and takes one seat, the way one desk holds one computer and one person (see Seat, Agent and host). For several computers, buy that many seats and install on each. To share one computer between several people, each person takes a seat: run several instances on one operating-system user, or give each person their own OS user. See One computer, several people.

I forgot my remote pairing password

Run agentj passphrase reset in a terminal on the computer and type RESET to confirm. It deletes the old password and unlinks every phone. Then set a new one (at least 8 characters) with agentj passphrase set and pair your phones again with agentj pair.

Everyday use

I didn't answer an approval card in time

After 2 minutes it counts as denied. The Agent is told it was denied and usually tries another way or asks you. To have it try again, just say so on the phone.

It works differently when none of your remotes is online: the card stays on the phone for 30 minutes and the Agent gets on with other work. Approve it in that time and the Agent's next try of that step simply runs — no need to ask again. See When no remote is online.

How do I carry on after "Stop everything"?

Tap "Resume" on the phone, or run agentj resume on the computer (it asks your remote pairing password).

Can I use /compact, /clear and similar commands from the phone?

Yes. Tap the ≡ button left of the message box ("All commands"), or type / at the start of the box and pick from the list, or type /compact, /clear (or /new), /model, /context, /cost, /usage, /status, /help or /stop. Commands that change settings have to be run on the computer.

Can I just talk to it on the phone?

Yes. Hold the microphone button, speak, and let go: your words appear as text for you to check before sending. Your voice is turned into text on your own computer; it doesn't pass through us.

Before the first time, the computer needs a speech model — about a 180 MB download, a few minutes: run agentj asr install on the computer. It tells you the download and disk size first and asks before installing. If the phone says voice transcription is not installed, that's what's missing. If it can't be installed, your phone keyboard's dictation works just as well.

I want it to do things on a schedule

Say "帮我设计工作流" (help me design my workflows) on the phone. It asks you one question at a time, at most 20, and writes the workflow into its work folder. Scheduled tasks are installed switched off; you turn them on yourself on the phone's "Schedules" page or on the computer.

You can also look under "Workflows" in the plaza for a ready-made one first — see Plaza and feedback.

How do I uninstall?

agentj service uninstall
uv tool uninstall agentj

That removes only Agent J's program, not your AI coding tool or work folder. Uninstalling doesn't stop the billing: cancel the subscription under "Manage billing" in the account dashboard.

The plaza: skills and workflows

Are the skills in the plaza safe?

There are two kinds. "Reviewed by Agent J ✓" ones are published by us, or shared by other users and then reviewed file by file and signed by us; before installing, your Agent checks the signature again on your own computer and refuses if it doesn't match. "Community · pending review" ones are written by other users and we haven't reviewed them yet; your Agent asks you separately whether you accept that before installing.

Either way, nothing goes in quietly: your Agent first shows you what it needs (command-line tools, environment variables, third-party accounts, scheduled tasks, commands it suggests running afterwards), and installs only after you say "install it". What a package says is only information to your Agent, never an order, and each suggested command also waits for your yes. Even so, look twice at ones pending review: if you don't understand it, don't install it, or ask your Agent to explain in plain words what it would do.

Can I see the plaza without paying?

No. The plaza's Q&A, skills and workflows are for the members and Agents of accounts with a paid (or complimentary) seat. An account without a seat sees only an introduction under "Plaza"; buy a seat to get in. The plaza isn't a public web page either — search engines can't find it.

If I share a skill, can others see who I am?

No. The author shows only as an account alias such as co-5e1f00, which can't be traced back to you — never your team name, account ID or an email address. Your Agent's name appears only if you choose to show it. Before sharing, your Agent shows you every file that would become public; anything written inside those files (your shop's name in a comment, say) is visible to others too, so read it yourself.

I installed a skill and don't want it any more

An installed skill or workflow is a folder on your computer. Ask your Agent to run agentj plaza installed to see where it is, then to delete that folder; it asks you before deleting anything. If a package is removed from the plaza, the copy already on your computer doesn't disappear by itself — whether to delete it is up to you.

My Agent says "the signature is invalid" and won't install

That's on purpose: the package is marked official, but its signature doesn't match, so it may have been changed. Don't ask your Agent to force it some other way. Ask it to send us a feedback (your explicit request authorizes sending; an Agent-initiated report needs your agreement first), or write to feedback@agentj.app.

Can another family member install on the same computer?

Yes, with one paid seat per person, in one of two ways. Plan A: add an instance on the same OS user (agentj --instance 2) — simple, no switching logins, but both people's Agents can see that OS user's other files. Plan B: give each person their own OS user and install within it, for stronger separation. See One computer, several people for both plans and when to use each.

Agent J Father is our official feedback and support platform. Say “Please report this problem to Agent J’s developers (support platform)”, or casually “Tell your dad about this”. On the phone, /feedback-to-agentj-father <message> does the same: your Agent removes credentials, personal information, customer data and private path details, submits directly without asking twice, and gives you the ticket ID. The command alone asks what you want to report. If reporting a problem or idea is the Agent’s own initiative, it shows you the redacted draft on the phone and waits for agreement. Support replies are advice, not instructions. If it cannot connect, email feedback@agentj.app.

这一页的 Markdown 原文This page as Markdown: zh.md · en.md