ArchestackBest of Open-Source AI: List on GitHub ↗3 stars (opens in a new tab)

#2727th of 28 in Agent platforms

edict

Multi-agent pipeline on OpenClaw with a mandatory review stage and live dashboard

Documentation ↗ (opens in a new tab)Repository on GitHub ↗ (opens in a new tab)
Stars
17k
License
MIT
Last commit
May 2026
Language
Python

Missed the latest GitHub check; these facts may be older.

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

Also in Agent platforms

See all 28
Also in Agent platforms
RankProjectScore
1LangflowVisual builder for AI agents and workflows, exposed as API or MCP server155.7k starsMIT81 out of 100
2daily_stock_analysisDaily LLM stock analysis for A-share, HK, US and other markets, pushed to chat apps66.4k starsMIT80 out of 100
3mindshubAgent workspace for knowledge work, with swappable open agent harnesses Live demo ↗ (opens in a new tab)39.8k starsMIT78 out of 100
#4deer-flowAgent harness that runs sub-agents, memory and sandboxed skills for long tasks83.9k starsMIT76 out of 100
#5DifyVisual builder for LLM workflows, RAG pipelines and agents, with APIs Live demo ↗ (opens in a new tab)158.5k starscustom license75 out of 100