Edict

Active
GitHub Python MIT

Description

A multi-agent orchestration system inspired by ancient governance structures, featuring 9 specialized AI agents with a real-time dashboard, model configuration, and full audit trails for complex multi-agent collaboration scenarios.

Key Features

  • 12 specialized AI agents organized as the Tang Dynasty Three Departments and Six Ministries system for checks and balances
  • Menshen (Gate Review) department provides mandatory institutional review with rejection authority before execution
  • Real-time Kanban dashboard with 10 functional panels including task tracking, agent health monitoring, and memorial archiving
  • Task intervention capabilities: pause, cancel, or resume tasks at any stage with full audit trail
  • Hot-swap LLM models per agent directly from the dashboard with ~5 second restart
  • News aggregation with automated daily tech/finance collection and Feishu push notifications

Use Cases

💡 Complex multi-agent task orchestration requiring quality gates and review workflows
💡 Teams needing real-time visibility into agent task progress and health status
💡 Scenarios requiring full audit trails and task intervention for compliance or oversight
💡 Automated news monitoring and aggregation with structured reporting
💡 Research and development workflows benefiting from institutional review mechanisms

Quick Start

Run `docker run -p 7891:7891 cft0808/sansheng-demo` to experience the dashboard with simulated data, or clone the repo, run `chmod +x install.sh && ./install.sh` for full installation (requires OpenClaw), then `chmod +x start.sh && ./start.sh` and open http://127.0.0.1:7891.

Related Projects