Skip to content
AgentOpen-source agent

edict

Multi-agent system modelled on an imperial court, with review steps and a dashboard

Pricing
Open source
Platforms
self-hosted, Web
GitHub stars
17.1K
Last commit
2 months ago
Language
Python
License
MIT

About edict

edict is an open-source agent for multi-agent frameworks. It is available on self-hosted and Web.

Edict (the Chinese name means three departments and six ministries) arranges 12 agents into a court hierarchy: a triage role sorts tasks, one department plans, another reviews and can veto, another dispatches, and six ministries execute in parallel. The README says this adds institutional review beyond CrewAI and a live dashboard beyond AutoGen.

A Docker one-liner starts the dashboard with preloaded mock data for trying it without OpenClaw. The README is primarily in Chinese with English and Japanese versions, and the licence is MIT.

What it does

Court-style roles
12 agents with planning, review and execution roles.
Review and veto
A review department can reject plans.
Parallel execution
Ministries run tasks concurrently.
Live dashboard
Kanban-style board of tasks.
Docker demo
One command starts a demo with mock data.

Good for

  • Auditable multi-agent task flows
  • Trying a review-gated agent workflow
  • Watching agent progress on a board
  • Studying role-based agent architecture

Pricing

Open source

Free, MIT

Prices change. Check openclaw.ai before you buy.

edict FAQ

Do I need OpenClaw?

Not for the demo; a docker run command starts a mock-data dashboard.

What languages is the README in?

Chinese, with English and Japanese versions.

Licence?

MIT.

Is edict free?

Yes. edict is open source, so you can use and self-host it for free.

What are the best alternatives to edict?

The closest alternatives to edict are AutoGPT, hermes-agent, deepseek-harness, dify and langchain.

Alternatives to edict

  1. AutoGPT

    Agent

    Hosted team of AI Experts for content, sales and research, coordinated by Otto

    • Free trial
    • Hosted agent
    • 188K GitHub stars
    • AI models and LLM tooling
  2. Open-source self-improving agent with memory, scheduling and many chat gateways

    • Freemium
    • Open-source agent
    • 264K GitHub stars
    • AI models and LLM tooling
  3. Open-source agent harness from DeepSeek, built on a plugin architecture

    • Open source
    • Open-source agent
    • 282K GitHub stars
    • Multi-agent frameworks
  4. dify

    Agent

    Visual platform for building and deploying agentic workflows and knowledge pipelines

    • Freemium
    • Agent framework
    • 161K GitHub stars
    • Workflow automation
  5. Python library for building agents from a model, tools, prompt and middleware

    • Open source
    • Agent framework
    • 150K GitHub stars
    • AI models and LLM tooling
  6. Open-source super agent harness that researches, codes and creates with sandboxes

    • Open source
    • Open-source agent
    • 85.4K GitHub stars
    • AI models and LLM tooling