Feishu Agent Team for Openclaw

A sophisticated multi-agent orchestration system that routes Feishu group mentions to specialized AI experts.

mars82311111
v1.0.0
Apr 1, 2026
0
701
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install feishu-agent-team

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install feishu-agent-team using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is Feishu Agent Team?

Feishu Agent Team is a collaborative AI framework designed to organize multiple agents into a cohesive workforce. It operates on a hub-and-spoke model where a central Coordinator agent receives all incoming messages via Feishu @mentions and intelligently dispatches them to specific Specialist agents. This system allows for complex task handling by delegating requirements to the most qualified AI expert, making it a cornerstone for teams looking to scale their Openclaw Skills implementations.

Built with LangGraph for state management and feishu-oapi for seamless communication, this skill provides a robust architecture for enterprise-grade AI automation. It supports persistent state recovery and asynchronous execution through a lightweight message queue, ensuring that your AI team remains reliable and responsive across various business workflows.

Feishu Agent Team Use Cases

  • Creating an AI-powered project management office where tasks are routed to developers, analysts, or marketers.
  • Automating customer support triage within Feishu group chats.
  • Building specialized research teams that analyze market trends and technical documentation via a single entry point.
  • Developing cross-functional automation workflows that require handoffs between different AI models.

How Feishu Agent Team Works

  1. A user triggers the workflow by @mentioning the Coordinator agent in a Feishu group chat.
  2. The Coordinator extracts the task content and invokes the routing logic to match keywords against specialist profiles.
  3. The task is pushed to a lightweight message queue (MQ) specifically for the identified Specialist agent.
  4. The Specialist listener receives the task, processes the logic, and posts the response back to the Feishu group.
  5. LangGraph handles state persistence using SQLite checkpoints, allowing Openclaw Skills to maintain context even after interruptions.

Feishu Agent Team Setup

To install the Feishu Agent Team within your environment, follow these steps:

# Enter the Openclaw workspace
cd ~/.openclaw/workspace

# Clone the repository
git clone <repo-url> feishu-agent-team

# Install required dependencies
pip install langgraph langchain-openai feishu-oapi

# Initialize the team environment
python team.py init

# Start the specialist listeners
python listeners/specialist_listener.py --agent analyst &

You must also configure your Feishu App credentials and Openclaw Skills bindings in the config/ directory.

Feishu Agent Team Data Schema & Taxonomy

The skill organizes its operations through configuration files and persistent state storage:

Component Type Description
team.yaml Configuration Defines coordinator names, specialist roles, and routing keywords.
SQLite Checkpoints Database Stores the state of active graphs and task history for recovery.
Bindings JSON Configuration Maps Feishu account IDs to specific Openclaw Skills agent IDs.
MQ implementation Logic Manages the flow of asynchronous messages between the coordinator and listeners.

Feishu Agent Team Advanced Features

  • Intelligent keyword-based routing for high-precision task delegation.
  • Support for multi-group configurations, allowing one agent team to serve multiple departments.
  • Extensible specialist architecture that allows developers to add new roles by defining a new listener and YAML entry.
  • Checkpoint persistence for long-running tasks, ensuring no data is lost during system restarts.
  • Comprehensive CLI for testing routes and checking the operational status of your Openclaw Skills team.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*