cft0808/edict

Project overview

An AI multi-agent orchestration architecture that enforces mandatory institutional review, real-time task monitoring, and intervention capabilities. It requires an existing OpenClaw installation, Python 3.10+, and an LLM API key to operate.

Project type

Workflow

Use cases

Coding & Development · Automation

Deployment

Refer to project documentation

License

MIT

Best for

• Developer and enterprise teams who require mandatory institutional review, plan rejection, and real-time intervention for multi-agent workflows.
• AI engineers managing agents on macOS or Linux environments who need to monitor agent health and task status via a web GUI.

Key capabilities

• A web dashboard providing a Kanban board for task status, agent health monitoring, and task intervention (pause/cancel/resume).
• Supports adding, viewing, and removing remote or local skills for specific agents via UI or CLI.

Limitations and risks

• Full operation requires the OpenClaw platform to be pre-installed.

Getting started

• Setup is rated medium difficulty. Users must clone the repository, run the ./install.sh script, and execute ./start.sh. This process requires Python 3.10+ and a pre-installed OpenClaw platform.

Evidence and sources

• GitHub project description: 🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails
• README: [MIT](LICENSE) · 由 [OpenClaw](https://openclaw.ai) 社区构建
• README: 然后你拿到一坨不知道经过了什么处理的结果，无法复现，无法审计，无法干预。
• README: 这不是花哨的 metaphor，这是**真正的分权制衡**
• README: **✅ 叫停 / 取消 / 恢复**

Reviewed at: 2026-07-17T14:07:52Z