multi-agent-feishu 多飞书账号接入不同agent

Name: multi-agent-feishu 多飞书账号接入不同agent
Author: Zeng Guoming

在 OpenClaw Gateway 中创建多个 Agent 并绑定多个飞书账号。适用于：(1) 需要多个独立 AI 助手 (2) 不同用户使用不同 Agent (3) 需要隔离的记忆/身份场景。

Zeng Guoming

@kolikoliko

What This Skill Does

Creates multiple independent AI agents in OpenClaw Gateway, each bound to a separate Feishu (飞书) bot account. Each agent has its own workspace, memory, and identity, enabling isolated AI assistants for different users or teams.

Replaces running separate Gateway instances for each Feishu bot by allowing multiple agents with isolated memory and identity under a single Gateway.

When to Use It

Set up separate AI assistants for different departments in a company
Bind distinct Feishu bots to agents with isolated conversation histories
Assign unique agent identities to different user groups in Feishu
Run multiple AI helpers with separate knowledge bases and memory
Create per-team AI assistants that do not share context or data

Install

$ openclaw skills install @kolikoliko/multi-agent-feishu

Multi-Agent Feishu Setup

在同一个 OpenClaw Gateway 下创建多个 Agent，每个绑定不同飞书机器人。

快速开始

1. 创建 Agent

openclaw agents add <agent_id> \
  --workspace ~/.openclaw/workspace<N> \
  --bind feishu:<account_id> \
  --non-interactive

2. 添加飞书账号

编辑 ~/.openclaw/openclaw.json，在 channels.feishu.accounts 中添加：

"<account_id>": {
  "appId": "cli_xxx",
  "appSecret": "xxx"
}

3. 重启 Gateway

openclaw gateway restart

4. 配对飞书

openclaw pairing approve feishu <配对码>

验证配置

openclaw agents list --bindings

详细文档

配置字段说明 - agents.list、bindings、channels 字段详解
飞书机器人创建指南 - 如何在飞书开放平台创建机器人
多 Agent 架构图 - 架构说明和流程图
常见问题 - 配对失败、收不到消息等问题排查
备份与恢复 - 配置备份和恢复方法

Top skills in this category

self-improving agent

@pskoett

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude rea

4.0k477k

Skill Vetter

@spclaudehome

Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.

1.3k271k

Self-Improving + Proactive Agent

@ivangdavila

Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...

1.3k209k

Proactive Agent

@halthelobster

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞

831175k

Agent Browser

@matrixy

Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection

459156k