bihangchi9-creator/lark-agent-bridge

Name: bihangchi9-creator/lark-agent-bridge
Author: bihangchi9-creator

Collection合集 Native原生 ⭐ 33 NOASSERTION Markets & Collections市场与合集 Notifications & Remote通知与远程

A native DeepSeek Harness (dsh) plugin bridging dsh coding agents to Feishu/Lark group chats — one group, one project directory.

Project Overview项目介绍

Edited by Zhiwei Agent (zhiwei)由知微Agent(zhiwei)编辑

Lark Agent Bridge is a native DeepSeek Harness plugin that connects local coding agents to Feishu/Lark group chats. It natively runs as an in-process Cordis plugin for DSH, and also can run as a standalone daemon that spawns CLI agents like traex or codex, attaches to a running IDE window via Unix socket, or loads a custom user-built custom agent adapter. Each Feishu group chat is mapped to a unique isolated local working directory and a pinned agent runtime, so different groups never interfere with each other’s work or agent conversations.

To use the bridge, you send a message or attach files and images in a Feishu group, and the bridge forwards the content to the pinned agent for that group. The agent processes the request using its own tools and persistent project context, then streams the response back to a live-updating Feishu group chat in real time. This tool is built for development teams that use Feishu for internal collaboration and want to run multiple parallel local coding agents directly within their existing group workflow, without switching between local different tools.

Lark Agent Bridge requires Node.js version 22.19.0 or higher, a working DeepSeek Harness installation, and a valid DeepSeek API key to run. On first launch, if no Feishu credentials exist, it automatically runs a QR registration wizard that lets you scan a code in the Feishu app to complete setup. It enforces attachment limits of 5 files per message, 10MB max for images, 20MB max for other files, and stale attachments are automatically deleted after 7 days. The project is released under the open source MIT license, and includes three pre-built permission tier presets for DSH.

本项目是专为 DeepSeek Harness 开发的原生插件，用于将本地编码代理对接至飞书（Lark/Feishu）群聊，实现飞书消息触发代理运行、代理回复流式返回飞书聊天窗口的功能。它支持四种运行时接入模式：DSH 进程内插件、CLI 守护进程生成 traex/codex、IDE 套接字接入和自定义代理模块，每个飞书群对应独立的工作目录和固定绑定的运行时。

用户可在飞书群内发送文本消息和图片、文件附件，插件会自动将其转发给当前群绑定的编码代理，并将代理的处理结果流式返回至飞书聊天窗口。不同群聊之间工作区完全隔离，不会互相干扰对方的文件或对话状态，团队可以在多个群聊同时运行多个不同项目的编码代理实例。适合需要在飞书团队协作场景下接入本地编码代理的开发团队使用。

本项目依赖 Node.js 22.19.0 以上版本、可运行的 DeepSeek Harness 实例和 DeepSeek API 密钥，首次运行会自动弹出二维码注册飞书应用，无需手动配置。附件支持单消息最多 5 个附件，图片不超过 10MB，其他文件不超过 20MB，过期文件 7 天后自动清理。项目采用 MIT 许可证开源，内置三种不同权限等级的工具预设。

View on GitHub在 GitHub 查看

Send to your DSH发给你的 DSH 安装

请帮我安装这个 DSH 插件。安装前先完成【兼容性检查 + 安全性检查】，检查通过再动手。

插件：lark-agent-bridge（bihangchi9-creator/lark-agent-bridge）
仓库：https://github.com/bihangchi9-creator/lark-agent-bridge
本站详情页：https://www.yhbd.top/plugins/bihangchi9-creator-lark-agent-bridge/
本站登记：类型 collection · 归类 原生 DSH 插件 · 许可证 NOASSERTION · ⭐ 33 · 最近提交 2026-09-18 · 主语言 TypeScript

按下面顺序执行，每步先把结论告诉我，再进入下一步：

【1 兼容性检查】
① 我这边：DSH 版本、Node 版本、操作系统、当前 profile（web / desktop）。
② 读它的 README、package.json、插件 manifest，列出它要求的 DSH 版本 / Node 版本 / 操作系统 / 外部依赖 / 需要另外先装的运行时。
③ 逐条比对，结论只写「满足 / 不满足 / 未知」三种；不满足的给出可行替代方案。
④ 检查是否和我已装的插件冲突：命令名重复、skill / tool 重名、端口占用、重复注册的 MCP server。

【2 安全性检查】
① 仓库可信度：和上面「本站登记」是否一致；star / fork 数、创建时间、最近提交，是否归档或长期停更。
② 安装脚本：逐行看 package.json 的 preinstall / install / postinstall，以及 install.sh、setup.ps1 之类脚本。出现 curl|bash、下载后直接执行、混淆代码、访问与插件功能无关的域名，立刻停下来告诉我，不要继续装。
③ 依赖：列出新增依赖，标出无人维护、或与知名包拼写近似的可疑包（typosquatting）。
④ 权限与副作用：它会读写哪些目录、访问哪些域名、需要哪些 DSH 权限（filesystem / network / shell / clipboard 等），以及怎么卸载和回滚。
⑤ 如果它要求 sudo / 管理员权限，或权限明显超出功能所需，先停下来问我。

【3 安装】
上面两步没有「不满足」和「高危项」时才执行；用官方推荐方式安装，不要自行提权。

【4 汇报】
用表格输出：检查项 / 结论 / 依据 / 是否需要我决策。拿不准的一律写「未知」并说明要我怎么确认——不要猜，也不要替我决定。

Send this message to DSH in your current session: it verifies compatibility and security first (answering met / not met / unknown item by item) and only installs once everything checks out — it will stop and ask you if it finds a high-risk item. The box scrolls; the copy is the full prompt. CLI install commands may not be accurate across systems, so DSH is the safer route.把上面这条消息直接发给当前会话里的 DSH：它会先核对兼容性与安全性（逐条给「满足 / 不满足 / 未知」），确认没问题再安装，有高危项会停下来问你。框内可滚动，复制到的是完整提示词；安装命令不一定准确，发给 DSH 更稳。

Pre-install check安装前体检Compatibility · Security兼容性 · 安全性 1 note1 项提示

33 stars - an early-stage project星标 33，属于早期项目

DSH walks through these 9 checksDSH 会逐条核对这 9 项

Compatibility兼容性

DSH, Node, OS and profile requirementsDSH 版本 / Node 版本 / 操作系统 / profile 是否满足要求
External dependencies and runtimes (Electron / Python / Docker, ...)外部依赖与运行时（Electron / Python / Docker 等）是否齐备
Conflicts with installed plugins: command names, skill / tool names, ports, duplicate MCP registration与已装插件是否冲突：命令名、skill / tool 重名、端口占用、重复 MCP 注册

Security安全性

Repo matches the facts registered here; archived or abandoned?仓库是否与页面登记一致，是否归档或长期停更
Safety of preinstall / install / postinstall and install.sh / setup.ps1preinstall / install / postinstall 与 install.sh、setup.ps1 是否安全
curl|bash, download-then-execute, obfuscation, unrelated domains → stop immediatelycurl|bash、下载即执行、混淆代码、无关域名 → 立刻停止
Typosquatting or unmaintained packages among the new dependencies新增依赖里有没有 typosquatting 或无人维护的包
Requested permissions vs. what the feature actually needs申请了哪些权限、是否超出功能所需（filesystem / network / shell / clipboard）
Any sudo / admin requirement, plus uninstall and rollback是否要求 sudo / 管理员权限，以及卸载与回滚方式

Anything uncertain must be marked unknown with a note on how to confirm it. This site's signal screen is a static snapshot, not a security audit.拿不准的必须标「未知」并说明要我怎么确认。本站的信号筛查是静态快照，不能替代安全审计。

Or use CLI install (for developers)或使用命令行安装（适合开发者）

CLI Install命令行安装

dsh plugin --profile web add github:bihangchi9-creator/lark-agent-bridge

把 bihangchi9-creator/lark-agent-bridge 加入你的 DSH 配置（web profile）即可启用。

READMEREADME

20.0 KB · 缓存于 2026-09-18 19:38:21 · 20.0 KB

Lark Agent Bridge

_{npm package: @bihangchi9/lark-agent-bridge · git repo: lark-agent-bridge}

A Feishu / Lark bridge for local coding agents — one group, one conversation, one pinned runtime. Bridges dsh (in-process plugin), CLI agents (traex / codex, spawned by a daemon), an IDE window (attached over a socket), or a custom agent — behind one gateway.

中文 README

Send a message in a Feishu chat, and a real coding agent — with its own tools, its own project directory, and its own persistent conversation — answers you right there. Each group chat is an isolated workspace pinned to exactly one runtime, so a team can run several projects (and several agents) in parallel, one per group.

What it does

Feishu ⇄ your agent. Inbound Feishu messages drive a live agent; the reply streams back onto a live-updating Feishu message. The agent is whichever runtime this chat is pinned to (dsh / CLI / IDE / custom).
Four host classes, one contract. Every runtime implements the same AgentAdapter: dsh runs in-process as a plugin; CLI spawns traex/codex; IDE attaches a running window; custom loads your own module. They never silently replace each other.
One group, one conversation, one pinned runtime. Every chat id maps to a stable directory (<workspaceRoot>/<chatId>) and one runtime chosen with /agent. Different groups never touch each other's files, and a message is never broadcast to several agents. If the pinned runtime is down (e.g. an IDE window closed), that chat fails closed instead of retargeting.
Persistent per-chat sessions. A chat's conversation survives restarts (policy-fingerprint-gated resume-or-create; /new really clears it).
Files and images. Send them to the bot and the bridge stores each message in an isolated .attachments/<messageId>/ folder, then gives the paths to the agent. Limits: 5 attachments per message, images ≤10 MB, other files ≤20 MB; names are sanitized and stale files are swept after 7 days. Whether an image can actually be interpreted depends on the selected model's vision support.
Zero-config setup. On first launch, if no credentials exist, a QR registration wizard runs — scan it in the Feishu app and it connects automatically. No portal spelunking.
Slash commands. /help, /new, /where, /models, /agent, and /whoami manage each chat locally; owner-only /agent, /model, /preset, /allow, and /disallow change shared chat state. /agent pins this chat to one installed runtime and never silently retargets.

Showing the opening section of the README — the full document lives in the repository以上为 README 开头摘要，完整文档在仓库内 · View the full README on GitHub →在 GitHub 查看完整 README →

渲染基于仓库 bihangchi9-creator/lark-agent-bridge 的 README.md。在 GitHub 查看原文 →