DeepSeek Harness Plugin Hub

发布与管理完整 Harness Profiles,发现适合你的插件。

探索

插件目录环境预设文档中心动态

社区

发布插件联系我们报告问题

相关链接

Plugin Hub GitHubDeepSeek Harness 官方项目系统状态隐私说明
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

独立、非官方社区项目,与 DeepSeek 官方无隶属、授权或背书关系。

Lark Claw — DeepSeek Harness 插件(DSH Plugin)
DeepSeek Harness Plugin Hub
ProfilesPlugins分类动态文档登录管理 Profiles
ProfilesPlugins分类动态文档登录
← Plugins

dsh-lark-claw

Lark Claw

用于 DeepSeek Harness 的独立 Lark/Feishu 网关和持久化 cron 套件

插件会安装到这里;不确定时保持 web。

npx -y @deepseek-ai/dsh plugin --profile web add dsh-lark-claw@0.1.5
README兼容性版本

兼容性与来源证明

Lark Claw 以 dsh-lark-claw 发布,当前版本为 0.1.5。Plugin Hub 会校验它的 manifest,并保存精确安装来源,便于复现安装结果。

DSH 兼容范围
*
运行环境
any
发布来源
npm
Registry 更新时间
2026/9/12

版本

0.1.5stable
2026/9/12

相关插件

正在加载相关插件…

最新版
0.1.5
DSH
*
HMR
重启进程
Tree shaking
未声明可安全裁剪
解包体积
2.1 MB
文件数
70
Surface
any
许可证
MIT
发布源
npm
GitHub
★ 1
周下载
0
最近提交
2026/9/12
查看源码 ↗
README Badge

点击下方 Badge 复制 Markdown,粘贴到 README 即可。

这是你的 Plugin?认领权益 · 优先安全扫描

验证 package.json 声明的 GitHub 仓库,即可管理这个公开页面。认领后,Hub 会优先安排当前版本的安全扫描,并在通过后公开展示结果。

认领这个 Plugin →
报告问题

相关插件

继续浏览 integrations-communication 分类下经过校验的插件。

Im@xmanrui/dsh-im将十一种 IM 渠道和一个公网 AI Office 接入本地 DeepSeek Harness。DSCODE@toddzheng024/dscode-bundle完整的 DeepSeek 编码代理,支持持久化 shell、Ultra 协作和自动权限审查。Acp App@deepseek-ai/dsh-acp-appdsh ACP 配置文件包:基于 dsh-base 的仅限自动化的 JSON-RPC stdio 和进程生命周期管理Im Connect@michengai/dsh-im-connectDeepSeek Harness IM 助理:把本机 agent 接到微信、企微、钉钉、飞书、QQ、Telegram,会话与网页任务分列。

README

dsh-lark-claw

English | 中文

Use DeepSeek Harness from Lark or Feishu and let your bot handle tasks.

Lark and Feishu connected to DeepSeek Harness

Message the bot directly or mention it in a group to explore a project, analyze a file, or schedule a reminder. Follow progress in a live card and continue the conversation in the same topic.

  • Ongoing conversations: Keep context per topic and continue after a service restart.
  • Live progress: See responses and tool activity directly in chat.
  • Images and files: Ask about a screenshot or reply to a file message to process it.
  • Scheduled tasks: Set one-time reminders or recurring tasks in natural language.

Quickstart

You need dsh 0.1.2-rc.1 or later, Node.js ^22.19.0 or >=24.0.0, pnpm, and a Lark/Feishu app. Make sure your model and API key already work in dsh.

Configure the app in the Lark/Feishu developer console:

  • Enable the bot capability.
  • Select long-connection event delivery and subscribe to im.message.receive_v1.
  • Grant the app-identity permissions needed to receive, send, read, and download message resources. Responding to group messages without a bot mention also requires im:message.group_msg.
  • Publish the app or add test users to its availability scope. Add the bot to each group where it will be used.

Install the plugin:

dsh plugin --profile feishu add dsh-lark-claw

Without an explicit version, this installs the npm latest release. To upgrade an existing installation, run the command below and then restart the running dsh --profile feishu process:

dsh plugin --profile feishu update dsh-lark-claw@latest

dsh plugin uses pnpm to manage the profile. If the required version is not yet on npm, follow the local source installation instructions.

Configure your bot:

Use the example configuration to fill in ~/.dsh/config.yaml (or the directory set by DSH_HOME). Merge the required fields if you already have a configuration.

  • Enter your app's App ID and App Secret.
  • Set the users and groups allowed to use the bot. ou_xxx is a user open_id and oc_xxx is a chat_id. The example enables a direct-message allowlist, so leaving its placeholder rejects every direct message.
  • Choose an absolute workspace path for the bot's files and configure an available model.

See the configuration guide for field descriptions.

Start:

dsh --profile feishu

Keep the process running. Send the bot a direct message or mention it in an allowed group; once it replies, you're ready.

Usage

Work on a task

@bot Look through this project and explain how to run it.

The bot shows progress in a card. Reply in the same topic to continue working on the task. Group messages require a bot mention by default.

Ask about images and files

Send an image with your question. Image understanding requires a model that accepts image input.

If a file must be sent separately, send it first, then use Lark/Feishu's reply action on that file message and mention the bot:

@bot Summarize this file and highlight what needs my attention.

File format support depends on the Agent's available tools.

Schedule a reminder

@bot Remind me to check project progress at 9 a.m. every weekday.

You can also ask it to list or delete reminders. Scheduled tasks are saved, but the service must be running when they are due.

Approvals and questions

When an operation needs permission, the bot posts an Allow once / Reject card in the same topic. Questions appear as choices or text fields; submitting an answer continues the task. Only the user who started the current task can respond. Requests expire after ten minutes by default.

Enable card interaction callbacks in your Feishu app first; see interaction setup.

Commands

CommandAction
/helpShow help
/statusCheck the current conversation's status
/stopStop the current task
/resetStart a new conversation in the current topic

More documentation

  • Configuration, updates and background operation
  • Scheduled task API
  • Attachment storage
  • Local development
  • Release maintenance

License

MIT