HomeProjectsArticlesPK BoardAbout
Explore Projects

agency-agents-zh

Active
GitHub Shell MIT

Description

agency-agents-zh is a community-maintained knowledge base and tutorial hub for AI agent development, RAG, and LLM engineering.

Key Features

  • 215 plug-and-play AI expert role definitions covering 18 departments across engineering, design, marketing, and more
  • 50 China-market original agents for platforms like Xiaohongshu, Douyin, WeChat, Bilibili, Feishu, and DingTalk
  • Compatible with 17 AI coding tools: Claude Code, Cursor, Copilot, OpenClaw, Gemini CLI, and more
  • Each agent includes identity definition, key rules, workflows, and deliverables — not just generic prompts
  • Agency Orchestrator for multi-agent collaboration with DAG parallel execution and breakpoint resume
  • OpenClaw integration with SOUL.md + AGENTS.md + IDENTITY.md split for natural multi-agent orchestration

Use Cases

💡 Deploying specialized AI roles for Chinese market digital marketing and platform operations
💡 Building multi-agent workflows combining engineering, design, and product experts
💡 Quickly prototyping AI-assisted projects with pre-configured expert personas
💡 Integrating Feishu and DingTalk enterprise workflows with dedicated AI integration agents

Strengths & Limitations

✅ Strengths

  • • Actively maintained, recent updates
  • • High community interest (20.2k stars)
  • • Permissive open-source license (MIT)
  • • Responsive to issues, low backlog

Tags

agency-orchestrator agent-definitions ai-agents ai-roles chinese claude multi-agent

Categories

🧠 Multi-Agent ⚡ Agent Tools

Quick Start

git clone https://github.com/jnMetaCode/agency-agents-zh.git && ./scripts/install.sh --tool claude-code
Visit GitHub Visit Website

Related Projects

open-multi-agent

6.9k · TypeScript
Active A+

From a goal to a task DAG, automatically. TypeScript-native multi-agent orchestration with MCP and live tracing. Three runtime dependencies.

agent-frameworkai-agentsanthropic +5
  • · Goal-driven coordinator: a single runTeam() call decomposes goals into a task DAG and executes it automatically
  • · Mix any LLM providers in one team: 12 built-in providers plus any OpenAI-compatible endpoint (Ollama, vLLM, Groq, etc.)
  • · Extended thinking / reasoning support across Anthropic, Gemini, and OpenAI with cross-provider reasoning preservation
View full details → View on GitHub

Agent Skills for Context Engineering

17.9k · Python
Active A

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems.

agentmulti-agentframework +2
  • · Covers 15 context engineering skills from foundational concepts to advanced cognitive architectures for systematic AI agent knowledge building
  • · Platform-agnostic design, applicable to Claude Code, Cursor, and any agent platform supporting custom instructions
  • · Progressive disclosure architecture: loads only skill names and descriptions at startup, activating full content on demand
View full details → View on GitHub

DATAGEN

1.8k · Python
Active A

DATAGEN: AI-driven multi-agent research assistant automating hypothesis generation, data analysis, and report writing.

research-agentmulti-agentlanggraph +1
  • · Multi-agent system with 8 specialized agents: hypothesis, process, visualization, code, searcher, report, quality review, and note taker
  • · AI-driven hypothesis generation and validation with automated research direction optimization
  • · Interactive data visualization and custom report generation with automated insight extraction
View on GitHub

AI Berkshire

16.1k · Python
Active A+

An AI-era value investing research framework based on Claude Code/Codex, integrating methodologies of four masters (Buffett, Munger, Duan Yongping, Li Lu) with multi-agent parallel research.

value-investingclaude-codemulti-agent +2
  • · Multi-agent parallel - simultaneously call multiple Claude Code/Codex instances to analyze different dimensions in parallel
  • · Four-master methodology - built-in investment frameworks and decision checklists from Buffett, Munger, Duan Yongping, Li Lu
  • · Deep financial analysis - auto-parse 10-K, 10-Q, annual reports, extract key financial metrics
View full details → View on GitHub