DingTalk-Real-AI/dingtalk-workspace-cli

DingTalk Workspace is an officially open-sourced cross-platform CLI tool from DingTalk. It unifies DingTalk’s full suite of product capabilities into a single package, is designed for both human users and AI agent scenarios.

What it solves

DingTalk Workspace CLI (dws) provides a command-line interface to access and manage DingTalk enterprise data. It bridges the gap between human developers and AI agents, allowing them to interact with DingTalk services (like calendars, documents, and contacts) through a terminal rather than a GUI.

How it works

Built in Go, the tool uses OAuth device-flow authentication to securely connect to DingTalk organizations. It provides a structured set of commands for various DingTalk products. For AI agents, it offers structured JSON responses and a built-in "Agent Skill" system (available in mono or multi-product layouts) that allows LLMs to understand the CLI's capabilities and execute tasks via natural language through tools like Claude Code or Cursor.

Who it’s for

  • Developers and Power Users: Those who prefer the command line for managing enterprise tasks.
  • AI Agent Developers: Those building agents that need to interact with DingTalk enterprise data.
  • Enterprise Admins: Admins who need to manage CLI access and authorization for their organization.

Highlights

  • AI-Native Design: Includes a schema command to provide agents with a compact, normative view of command contracts and constraints.
  • Zero-Trust Security: Implements OAuth device-flow, domain allowlisting, and least-privilege scoping to ensure all actions are audited.
  • Multi-Profile Support: Allows users to stay logged in to multiple DingTalk accounts and organizations simultaneously.
  • Flexible Output: Supports multiple output formats including table, JSON, and raw text, with a --jq flag for precise data extraction.
  • Safe Execution: Features a --dry-run mode to preview requests before they are executed.

Related

  • Project
    googleworkspace/cli

    A unified CLI for all Google Workspace APIs that dynamically generates its command surface, providing structured JSON output for both humans and AI agents.

  • Project
    ttguy0707/CyberClaw

    An enterprise-grade transparent agent architecture that eliminates AI "black box" operations through two-phase tool execution, full behavior auditing, and a secure sandbox.

  • Project
    TesslateAI/OpenSail

    An open-source platform for building and managing agentic software and AI workflows, turning recurring business processes into durable, controlled automations.

  • Dispatch
    Designing Agent-Native CLIs: 10 Principles for the AI Era

    Explore the shift toward designing command-line interfaces specifically for AI agents, focusing on predictability, structured output, and mechanical consistency.

  • Project
    Ed1s0nZ/CyberStrikeAI

    CyberStrikeAI is an open‑source Go platform that lets security teams drive penetration‑testing workflows with natural‑language prompts. An Eino‑based agent interprets intent, runs a curated set of 100+ security tools, records evidence, and stores the whole attack chain for replay. The system includes a web UI, role‑based access control, RAG knowledge base, optional C2/WebShell, and plugins for Burp Suite and browsers. One‑click deployment (`run.sh`) builds the server, creates a Python virtual environment, and starts an HTTPS service. It is licensed under Apache 2.0 and intended for authorized, ethical testing only.