#4646th of 48 in Agent platforms
edict
Multi-agent pipeline on OpenClaw with a mandatory review stage and live dashboard
- Stars
- 17k
- License
- MIT
- Last commit
- May 2026
- Language
- Python
12,590 on 26 Mar 202617,012 on 22 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Edict runs 12 role-specific agents on OpenClaw, modeled on Tang-dynasty ministries. A triage agent routes messages, a planner splits tasks, a review agent can reject plans, and ministry agents execute in parallel. A Python stdlib dashboard shows a Kanban board, timelines, agent heartbeats and per-agent model switching. A state machine validates task transitions and writes an audit log.
Who it is for: Self-hosters running OpenClaw who want reviewed, auditable multi-agent tasks
Strengths
- Mandatory review agent can reject plans and force rework before execution
- Dashboard with Kanban, timelines, heartbeats, and stop/cancel/resume controls
- State machine rejects illegal task transitions; changes are written to an audit log
- Dashboard server uses only the Python standard library
Weaknesses
- Full setup requires OpenClaw; the Docker image is a demo with mock data
- Full install supports macOS and Linux only
- README is mostly Chinese; English and Japanese versions are separate files
- Redis Streams backend sits beside the stdlib server; how they fit together is unclear
What it needs
- no GPU
- Docker + Compose
- Needs OpenClaw, Python 3.10+, Node.js 18+ (frontend build), Redis (async backend), Feishu/Telegram/Signal (message channels)
- Models: Any LLM provider configured in OpenClaw
- port 7891
Quick answers
Is edict open source?
Yes. Its code is on GitHub under the MIT license.
Can you run edict with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does edict need a GPU?
No, it runs without one.
Also in Agent platforms
See all 48| Rank | Project | Score |
|---|---|---|
| 1 | AutoGPTRole-based AI agents coordinated by one lead agent, plus a visual workflow builder | 94 out of 100 |
| 2 | daily_stock_analysisLLM-driven daily analysis of watchlist stocks across six markets, pushed to chat apps | 94 out of 100 |
| 3 | LangflowVisual builder for AI agents and workflows, exposed as API or MCP server | 93 out of 100 |
| #4 | DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs | 92 out of 100 |
| #5 | deer-flowAgent harness running sub-agents, memory and sandboxes with pluggable skills | 88 out of 100 |