DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Lark Claw — DSH Plugin for DeepSeek Harness
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins

dsh-lark-claw

Lark Claw

A standalone Lark/Feishu gateway and persistent cron bundle for DeepSeek Harness

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add dsh-lark-claw@0.1.5
READMECompatibilityVersions

Compatibility and provenance

Lark Claw is published as dsh-lark-claw and currently resolves to version 0.1.5. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
any
Release source
npm
Registry updated
9/12/2026

Versions

0.1.5stable
9/12/2026

Related plugins

Loading related plugins…

Latest
0.1.5
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
2.1 MB
Files
70
Surface
any
License
MIT
Source
npm
GitHub
★ 1
Weekly downloads
0
Last push
9/12/2026
View source ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue

Related plugins

More verified plugins in integrations-communication.

Acp App@deepseek-ai/dsh-acp-appThe dsh ACP profile bundle: automation-only JSON-RPC stdio and process lifecycle over dsh-baseIm@xmanrui/dsh-im把十一种 IM 渠道和公网 AI Office 接入本机 DeepSeek Harness。 Connect eleven IM channels and a public AI Office to a local DeepSeek Harness.Pocketdsh-pocketPut DeepSeek Harness in your pocket: one package, one settings page, and scan a QR code on your phone to access DSH on your computer in sync (LAN + public network, real-time screen mirroring).Chat Importdsh-chat-importImport conversation history from 25+ AI coding agents into DeepSeek Harness as resumable sessions — tool calls, reasoning and results kept intact, with reverse export and sync. | 把 25+ AI 编程 Agent 的聊天记录导入 DeepSeek Harness 继续对话,保留工具调用、推理与结果,支持反向导出与同步。

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