edict and clawe

The OpenClaw Multi-Agent Orchestration System (A) provides the core agent execution engine with 9 specialized agents and audit trails, while Clawe (B) serves as a complementary coordination and workflow management layer—they're designed to work together as complements rather than competitors.

edict
60
Established
clawe
48
Emerging
Maintenance 20/25
Adoption 10/25
Maturity 11/25
Community 19/25
Maintenance 10/25
Adoption 10/25
Maturity 9/25
Community 19/25
Stars: 8,807
Forks: 757
Downloads:
Commits (30d): 42
Language: Python
License: MIT
Stars: 665
Forks: 77
Downloads:
Commits (30d): 0
Language: TypeScript
License: AGPL-3.0
No Package No Dependents
No Package No Dependents

About edict

cft0808/edict

🏛️ 三省六部制 · OpenClaw Multi-Agent Orchestration System — 9 specialized AI agents with real-time dashboard, model config, and full audit trails

Implements a 12-agent orchestration system modeled on Tang Dynasty imperial bureaucracy with mandatory review gates (门下省) that enforce quality control before task execution—unlike CrewAI/AutoGen which lack institutional checks. Built on OpenClaw with React 18 frontend (zero backend dependencies), offering real-time Kanban dashboard, per-agent LLM hot-swapping, complete audit trails with task intervention capabilities, and integrated news aggregation with Feishu webhooks.

About clawe

getclawe/clawe

Multi-agent coordination system: think Trello for OpenClaw agents.

Leverages Convex for persistent backend state and Anthropic/OpenAI for agent reasoning, with agents waking on cron schedules to process Kanban-style tasks through a CLI interface. Each agent maintains isolated workspaces with persona definitions (SOUL.md, HEARTBEAT.md) while sharing context through symlinked team state files. Real-time notifications and task updates flow through a dedicated watcher service that coordinates the multi-agent workflow across Docker-containerized squadhub gateway, backend, and web dashboard.

Scores updated daily from GitHub, PyPI, and npm data. How scores work