# wanikua/danghuangshang

Open-source multi-agent collaboration system inspired by Chinese governance — deploy and coordinate specialized AI agents with OpenClaw.

Repository: https://github.com/wanikua/danghuangshang
Canonical: https://ross.abutalabs.com/products/danghuangshang
Homepage: https://danghuangshang.com
Language: TypeScript
License: MIT
License Family: permissive
Topics: ai, ai-agents, clawdbot, discord, discord-bot, multi-agent, tutorial, ai-orchestration, autonomous-agents, llm, openclaw, workflow-automation, ai-collaboration, ancient-china, ming-dynasty, ai-court, imperial-china, liu-bu-zhi, san-sheng-liu-bu, six-ministries
Last push: 2026-05-22T12:41:23+00:00

## Health v2 (maintenance only)
Score: 55/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 83, release rhythm 42, longevity 13
- inputs: {"age_days": 192, "days_push": 103, "days_rel": 174, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2699, forks 253 (observed 2026-08-28T04:07:11.337018+00:00)

## What it is
Danghuangshang is an open-source multi-agent collaboration system built on the OpenClaw framework, modeling an AI 'imperial court' after Ming Dynasty governance with 18+ specialized agents (ministries) coordinated by an orchestrator. It deploys in minutes to Discord, Feishu, WhatsApp, or web, with multi-model routing, layered memory, and self-evolving prompts.

## Use cases
- coordinate multiple AI agents to run a solo startup
- deploy specialized AI agents on Discord that respond when mentioned
- automate content pipelines from research to publishing
- route tasks across Claude, GPT-4o, DeepSeek, and local Ollama models
- build an AI team with distinct roles for code, finance, marketing, and legal
- set up a self-improving agent workflow with persistent memory

## When to choose
- you want a ready-made multi-agent orchestration template with distinct role-based agents
- you want agents accessible from Discord, Feishu, WhatsApp, or web chat
- you want multi-model cost optimization and self-evolving prompts out of the box

## When to avoid
- you need a single simple chatbot without multi-agent overhead
- you prefer minimal dependencies or a framework other than OpenClaw
- you need production-grade enterprise governance or compliance guarantees

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, workflow-automation, chatbot, llm-inference, prompt-engineering
- domain: large-language-models, developer-tools, chatbots
- platform: self-hosted, cross-platform
- tags: multi-agent-collaboration, ai-orchestration, discord-bot, openclaw, agent-roles, imperial-china-theme, self-evolving-prompts, multi-model-routing, ai-agents, automation, nodejs, typescript, discord, docker

## Member repositories
- wanikua/danghuangshang (main) score 55

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:11.337018+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:16:08.109755+00:00, confidence not recorded.
  - readme: https://github.com/wanikua/danghuangshang (fetched 2026-08-28T04:07:11.337018+00:00, sha a208353c3382)
  - homepage: https://danghuangshang.com (fetched 2026-08-29T09:59:36.430045+00:00, sha 63738c01fb93)
- Data as of 2026-08-30T08:39:29.467469+00:00.