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

Strengths & Limitations

Strengths

  • Actively maintained, recent updates
  • High community interest (16.8k stars)
  • Permissive open-source license (MIT)
  • Responsive to issues, low backlog

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

GPTeam

1.7k · Python
Active A

An open-source multi-agent simulation platform where multiple LLM-powered agents collaborate on complex tasks in shared environments, with customizable roles, memory systems, and environment interaction for studying multi-agent collaboration.

pythonmulti-agentagent +3
  • · GPT-4 powered multi-agent simulation with autonomous collaboration on predefined goals
  • · Agent memory and reflection system inspired by Generative Agents research paper
  • · Spatial movement: agents move between locations and perform tasks in different environments

Ouroboros

5.8k · Python
Active A

Ouroboros is a spec-driven multi-agent framework that shifts from traditional prompting to specification-driven development, supporting multi-agent collaboration, MCP tool integration, and automated workflow orchestration for building high-quality agent systems.

multi-agentframeworkagent +4
  • · Spec-first workflow: Socratic interview → immutable seed spec → execution → evaluation
  • · Multi-runtime adapter supporting Claude Code, Codex CLI, OpenCode, Hermes, Gemini, Kiro, Copilot
  • · Three-layer architecture: Kernel (contract engine), Plugins (domain workflows), Shell (TUI cockpit)

DeepResearchAgent

3.5k · Python
Stale B

DeepResearchAgent is a hierarchical multi-agent system designed for deep research tasks and general-purpose problem solving, using a top-level planning agent to coordinate specialized sub-agents for automated task decomposition and efficient cross-domain execution.

multi-agentframeworkpython +3
  • · Hierarchical multi-agent system with top-level planning agent coordinating specialized sub-agents
  • · RSPL protocol layer modeling prompts, agents, tools, environments, and memory as versioned resources
  • · SEPL self-evolution protocol for proposing, assessing, and committing improvements with rollback support

KiwiQ

1.7k · Python
Stale B

Production-grade multi-agent orchestration platform with JSON-defined agents, multi-tier memory, and built-in observability, battle-tested on 200+ enterprise AI agents with full enterprise deployment support.

pythonmulti-agentagent +4
  • · SDK-first workflow engine with Python/JSON graph schemas compiled to LangGraph and executed via Prefect
  • · Multi-provider LLM support including OpenAI, Anthropic, Google Gemini, Perplexity, and AWS Bedrock
  • · Human-in-the-loop with real-time WebSocket streaming for workflow pause, review, and approval