经 AI Skill Hub 精选评估,Larkway 获评「强烈推荐」。这款Agent工作流在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 8.0 分,适合有一定技术背景的用户使用。
Larkway 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
Larkway 是一套完整的 AI Agent 自动化工作流方案。通过可视化的节点编排,将复杂的多步骤任务拆解为清晰的自动化流程,实现全程无人值守的智能处理。支持与数百种外部服务和 API 无缝集成,适合构建数据处理管线、业务自动化和 AI 辅助决策系统。
# 方式一:npm 全局安装 npm install -g larkway # 方式二:npx 直接运行(无需安装) npx larkway --help # 方式三:项目依赖安装 npm install larkway # 方式四:从源码运行 git clone https://github.com/chuckwu0/larkway cd larkway npm install npm start
# 命令行使用
larkway --help
# 基本用法
larkway [options] <input>
# Node.js 代码中使用
const larkway = require('larkway');
const result = await larkway.run(options);
console.log(result);
# larkway 配置说明 # 查看配置选项 larkway --config-example > config.yml # 常见配置项 # output_dir: ./output # log_level: info # workers: 4 # 环境变量(覆盖配置文件) export LARKWAY_CONFIG="/path/to/config.yml"
Turn your Claude Code or Codex subscription into a Feishu (Lark) agent your whole team can @-mention.
🌐 larkway.dev · 中文版
---
You @ the bot in a Feishu thread. It runs on your machine — reading your real codebase, executing commands, opening MRs — and posts the result back. You define what the agent knows and what it can do. Larkway just carries the messages.
Current release: v0.3.46
---
```
You can also just tell Claude Code / Codex: "set up Agent Team for me" — running larkway tasklist-init with no arguments already does the right thing for every bot configured on this machine.
larkway doctor reports each bot's task-handle status (configured/scope health) as part of its regular checks. Full design, configuration knobs, and platform-fact writeups: docs/task-handle.md.
---
larkway ui opens a local management dashboard (127.0.0.1 + token); create bots, edit memory, watch live logssession_id; the agent remembers what it did in prior turnslarkway doctor validates Codex state directory writability before start---
lark-cli — Feishu long-connection client and message utilities: npm i -g @larksuite/cli, then lark-cli auth login (the agent uses it to read thread history and attachments; larkway doctor checks it's present)glab + git — for bots that open MRs (optional for read-only bots)---
Install globally with npm:> npm i -g larkway >
```bash
larkway doctor # lists missing dependencies; --fix auto-installs some
larkway init # CLI wizard: scan QR code → name the bot → pick a backend
```
---
Turn a Feishu topic into a task and the agent will claim it, then keep its whole lifecycle in sync on its own — completion, failure/reopen, stall wake-ups, handoff-break detection between collaborating bots, and overdue nudges — no extra prompting needed.
```bash
整合Claude Code/Codex,增强团队协助能力
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
AI Skill Hub 点评:Larkway 的核心功能完整,质量优秀。对于自动化工程师和运维人员来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | larkway |
| Topics | ai-agentchatbotclaudecodextypescript |
| GitHub | https://github.com/chuckwu0/larkway |
| License | MIT |
| 语言 | TypeScript |
收录时间:2026-07-08 · 更新时间:2026-07-08 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端