CowAgent

Active
GitHub Python MIT

Description

CowAgent (formerly chatgpt-on-wechat) is a powerful AI assistant framework built on LLMs with autonomous planning, tool use, long-term memory, multi-agent collaboration, and multi-channel integration for WeChat, Feishu, DingTalk, and more.

Key Features

  • Three-tier memory architecture — Context→Daily→Core memory system with automatic Deep Dream distillation and hybrid keyword+vector retrieval
  • Skill system — One-click install from Skill Hub or create custom skills through natural language conversation
  • Multi-channel integration — Supports WeChat, Feishu, DingTalk, WeCom, QQ, Telegram, Slack and 10+ platforms
  • Autonomous task planning — Automatically decomposes complex tasks and executes step-by-step, looping tools until goal is reached
  • Structured knowledge management — Auto-curates knowledge into Markdown Wiki with visual knowledge graph browsing
  • Multi-model routing — Route Claude, GPT, Gemini, DeepSeek, Qwen to different functions with one-click Web console switching

Use Cases

💡 Enterprise WeChat/Feishu smart assistant: Deploy AI assistants on enterprise messaging platforms for automated customer and internal support
💡 Personal knowledge management: Automatically organize personal knowledge bases through conversation records with searchable long-term memory
💡 Automated workflow orchestration: Connect external services via Skill system for cross-platform automated task processing
💡 Multi-channel customer service bots: Provide consistent AI customer service across WeChat, DingTalk, web and other channels simultaneously

Quick Start

# Linux / macOS one-line install
bash <(curl -fsSL https://cdn.link-ai.tech/code/cow/run.sh)

# Docker deployment
curl -O https://cdn.link-ai.tech/code/cow/docker-compose.yml
docker compose up -d

# Access Web console
# http://localhost:9899

# Service management
cow start | stop | restart
cow skill install <name>

Related Projects