# dingtalk-workspace-cli — Agent-Ready DingTalk CLI

> dingtalk-workspace-cli (dws) is DingTalk’s open-source CLI for humans and AI agents, with OAuth login and `--dry-run` request previews.

## Install

Copy the content below into your project:

## Quick Use

```bash
curl -fsSL https://raw.githubusercontent.com/DingTalk-Real-AI/dingtalk-workspace-cli/main/scripts/install.sh | sh
dws auth login --device
dws calendar event list
dws doc search --query "quarterly"
dws todo task list --dry-run
```

## Intro

dingtalk-workspace-cli (dws) is DingTalk’s open-source CLI for humans and AI agents, with OAuth login and `--dry-run` request previews.

**Best for:** Enterprise teams automating DingTalk docs, calendar, drive, and todos

**Works with:** macOS/Linux/Windows, OAuth device flow, jq filtering

**Setup time:** 8-15 minutes

### Key facts (verified)

- GitHub: 1776 stars · 108 forks · pushed 2026-05-13.
- License: Apache-2.0 · owner avatar + repo URL verified via GitHub API.
- README-verified entrypoint: `curl -fsSL https://raw.githubusercontent.com/DingTalk-Real-AI/dingtalk-workspace-cli/main/scripts/install.sh | sh`.

## Main

- Use `--dry-run` when wiring it into an agent: you can preview requests without mutating enterprise data.

- Prefer device-flow auth (`dws auth login --device`) for headless environments (SSH/CI) and browser auth for local desktops.

- Explore capability via `dws schema` — README shows jq filters to inspect tool counts and parameter schemas before calling APIs.

### Source-backed notes

- README highlights `--dry-run` and multiple output formats (`-f table/json/raw`) as human+agent friendly defaults.
- README Installation section includes a one-line curl install script and mentions Go 1.25+ for building from source.
- README Quick Start lists example commands across contacts, calendar, docs, minutes, drive, and todo tools.

### FAQ

- **Is it safe to run in production orgs?**: README stresses least-privilege and audit; still start with `--dry-run` to validate requests.
- **Do I need admin permissions?**: README notes enterprise data access may require admin authorization depending on your org setup.
- **How do agents discover tools?**: Use `dws schema` — README shows jq queries to inspect tool lists and parameters.

## Source & Thanks

> Source: https://github.com/DingTalk-Real-AI/dingtalk-workspace-cli
> License: Apache-2.0
> GitHub stars: 1776 · forks: 108

---

<!-- ZH -->

## Quick Use

```bash
curl -fsSL https://raw.githubusercontent.com/DingTalk-Real-AI/dingtalk-workspace-cli/main/scripts/install.sh | sh
dws auth login --device
dws calendar event list
dws doc search --query "quarterly"
dws todo task list --dry-run
```

## Intro

dingtalk-workspace-cli（dws）是钉钉官方开源的跨平台 CLI，面向人类与 AI agent 场景。README 给出安装脚本、OAuth 登录与 `--dry-run` 等安全预览能力。

**Best for:** 需要自动化钉钉文档/日历/网盘/待办等能力的企业团队

**Works with:** macOS/Linux/Windows；OAuth device-flow；jq 过滤

**Setup time:** 8-15 minutes

### Key facts (verified)

- GitHub：1776 stars · 108 forks；最近更新 2026-05-13。
- 许可证：Apache-2.0；作者头像与仓库链接均已通过 GitHub API 复核。
- README 中核对过的入口命令：`curl -fsSL https://raw.githubusercontent.com/DingTalk-Real-AI/dingtalk-workspace-cli/main/scripts/install.sh | sh`。

## Main

- 把它接入 agent 时优先用 `--dry-run`：先预览请求，确认无误再执行，避免误操作企业数据。

- 无头环境（SSH/CI）用 device-flow（`dws auth login --device`），本地桌面则用浏览器登录更省事。

- 用 `dws schema` 先摸清能力边界：README 展示了配合 jq 查看 tool 数量与参数 schema 的方法。

### Source-backed notes

- README 强调 `--dry-run` 以及 `-f table/json/raw` 等输出格式，便于人类与 agent 消费。
- README 的 Installation 区域提供一行 curl 安装脚本，并在源码构建部分提到需要 Go 1.25+。
- README 的 Quick Start 给出联系人、日历、文档、纪要、网盘、待办等多类命令示例。

### FAQ

- **适合直接上生产吗？**：README 强调最小权限与审计，但仍建议先用 `--dry-run` 验证请求。
- **需要管理员权限吗？**：README 提到访问企业数据可能需要企业管理员授权，取决于组织配置。
- **agent 怎么理解有哪些工具？**：用 `dws schema`。README 展示了用 jq 读取工具清单与参数的方法。

## Source & Thanks

> Source: https://github.com/DingTalk-Real-AI/dingtalk-workspace-cli
> License: Apache-2.0
> GitHub stars: 1776 · forks: 108


---
Source: https://tokrepo.com/en/workflows/dingtalk-workspace-cli-agent-ready-dingtalk-cli
Author: Script Depot