dsh-lark-bridge

DeepSeek Harness Notifications & Integrations Low risk

Feishu (Lark) bridge for DeepSeek Harness: one-command install, streaming progress cards with a tool panel, ask/approval button cards, attachments, and proactive feishu_send pushes.

飞书入口插件：一条命令安装，流式进度卡片带工具面板、提问/审批按钮卡片、附件处理与 feishu_send 主动推送。

How to install

DeepSeek Harness dsh plugin add @jmoksz/lark-bridge

About

DSH 飞书入口（Lark Bridge）通过**飞书机器人**远程使用 DSH（DeepSeek Harness）：在飞书里给机器人发消息，机器人交给运行在本机的 DSH agent 执行（读写文件、跑命令、搜索网页等），处理过程用**流式消息卡片**实时呈现，最终回答 sealed 进卡片回复。本质是一个 cordis 插件（@jmoksz/lark-bridge）+ 一个 DSH profile（lark）。走官方**长连接**（WebSocket），无需公网 IP、无需反向代理，在家/内网即可部署。功能与特点 🎞️ **流式回复卡片（默认开启）**：每条任务一张「🤖 DSH 处理中…」实时卡片，思考、回答草稿、**工具调用面板**（状态符号·工具名·参数摘要）随执行 PATCH 更新；完成 sealed 为绿色终态（最终回复+用时+字数），出错为红色错误态 📨 **主动推送**：agent 可用 feishu_send 工具主动向会话推送文本/卡片（中途汇报、结果分发、主动提醒） 🎴 **交互问答 & 审批卡片**：ask_user_question 与工具审批渲染为按钮卡片，点击即作答；也可直接回复编号/文字 🖼️ **附件处理**：图片/文件/视频/音频自动下载保存；视觉模型下图片直接附加给模型 📝 **富文本**：post 富文本消息自动提取纯文本 …

GitHub ↗

Recommendation signals

54 Tool quality · Based on stars, downloads, maintenance, security and docs

– User interest · Adjusted by in-site views, install copies and download clicks

54 Overall

0views

0unique visitors

0install copies

0download clicks

0outbound clicks

Links

GitHub ↗ npm ↗ Report issue ↗

Basic safety check

Findings: None
Sources: curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
Topics: bot, deepseek-harness, dsh, dsh-plugin, feishu, im-bridge, lark

Related plugins

DeepSeek HarnessClaude CodeMCP Server

Score80

openpets

alvinunreal/openpets/tree/main/packages/dsh

Bridges DeepSeek Harness lifecycle status, errors, and approval requests to a locally running OpenPets desktop companion.

☆ 1.2K ↓ 484 Notifications & Integrations ↗

MCP Server

Score76

netdata

netdata/netdata

The fastest path to AI-powered full stack observability, even for lean teams.

☆ 80.6K ↓ – Notifications & Integrations ↗

DeepSeek Harness

Score71

dsh-im

xmanrui/dsh-im

Connect IM bots to DeepSeek Harness via QR codes or bot credentials (9 channels: Feishu, WeChat, DingTalk, WeCom, QQ, Slack, Telegram, Discord, and WhatsApp).

☆ 1.5K ↓ 23.8K Notifications & Integrations ↗