larksuite/cli

The official Lark/飞书 CLI tool, maintained by the larksuite team — built for humans and AI Agents. Covers core business domains including Messenger, Docs, Base, Sheets, Calendar, Mail, Tasks, Meetings, and more, with 200+ commands and 20+ AI Agent Skills.

What it solves

lark-cli is the official command-line interface for Lark/Feishu, designed to bridge the gap between human developers and AI Agents. It simplifies the process of interacting with the Lark Open Platform by providing a structured, secure, and optimized way to manage business domains like messaging, documents, calendars, and spreadsheets without needing to write complex API integrations from scratch.

How it works

The tool uses a three-layer command architecture to balance ease of use with full platform coverage:

  1. Shortcuts: High-level, human- and AI-friendly commands (prefixed with +) that use smart defaults and structured output.
  2. API Commands: 100+ curated commands mapped 1:1 to official platform endpoints.
  3. Raw API Calls: Direct access to over 2,500 Lark Open Platform APIs for full flexibility.

It includes 26 pre-defined "Skills" (modular capability sets) that allow AI Agents to operate Lark features (e.g., lark-calendar, lark-im) with zero extra setup. It handles authentication via OAuth and stores credentials securely using OS-native keychains.

Who it’s for

  • Individual Developers: Those who want to manage their Lark workspace via the terminal.
  • AI Agent Developers: Those building agents that need to perform actions within Lark (e.g., reading docs, sending messages, managing tasks).
  • Enterprise IT/ISVs: Organizations embedding the CLI into their own platforms with centralized credential management and audit logging.

Highlights

  • Agent-Native Design: Built-in structured skills and optimized parameters to maximize AI call success rates.
  • Wide Coverage: Supports 18 business domains including Messenger, Docs, Base, Sheets, Slides, Calendar, Mail, and OKRs.
  • Secure by Default: Features input injection protection, terminal output sanitization, and risk-control signals to detect anomalous activity.
  • Flexible Output: Supports multiple formats including JSON, pretty-print, table, ndjson, and CSV.
  • Rapid Setup: Interactive guided configuration and login process designed to get users running in minutes.

Related

  • Project
    deepcoldy/botmux

    A bridge that allows you to remotely control AI programming CLIs from Lark/Feishu, streaming terminal output as interactive cards and providing a web terminal for mobile and desktop access.

  • Project
    cso1z/Feishu-MCP

    An MCP server and CLI tool that enables AI agents to read, create, and edit Feishu (Lark) documents, manage tasks, and query user information.

  • Project
    zarazhangrui/lark-coding-agent-bridge

    A lightweight bot that bridges Feishu/Lark messenger with local Claude Code or Codex CLI, enabling chat-based interaction with local coding agents.

  • Project
    About-Intelligence/soku-cli

    A command-line interface that gives AI agents secure access to marketing and growth tools, allowing them to query data and automate campaigns with human-approved guardrails.

  • Project
    withoneai/cli

    A CLI tool that gives AI agents authenticated access to 750+ platforms via a single interface, eliminating the need to manage multiple API keys and OAuth flows.