Featured

Deploy OpenClaw in 60 seconds — 20% off logoDeploy OpenClaw in 60 seconds — 20% off

Launch OpenClaw on Hostinger in about 60 seconds and keep your agent live 24/7. Our referral link gives you 20% off, no coupon code needed.

Launch on Hostinger
Run your Hermes agent on Hostinger, fully managed logoRun your Hermes agent on Hostinger, fully managed

Launch Hermes on Hostinger in one click, fully managed, no VPS knowledge needed. Use code ZACAARON10 for 10% off.

Launch on Hostinger
Crawl and scrape any site into clean data, 10% off logoCrawl and scrape any site into clean data, 10% off

Firecrawl crawls and scrapes any site into clean markdown for your agent. Get 1,000 free credits, and new users get 10% off their first purchase.

Try Firecrawl free
6,000+ web scrapers for your AI agent, start free logo6,000+ web scrapers for your AI agent, start free

Apify gives your agent live web data: 6,000+ prebuilt scrapers and actors, MCP-ready. Sign up free with $5 in usage credits.

Try Apify free
One API to scrape, enrich, and extract the internet. logoOne API to scrape, enrich, and extract the internet.

Context.dev gives your agents a single API to scrape, enrich, and extract live web data — no proxies, no parsers, no maintenance.

Start building free
SetupClaw: done-for-you OpenClaw for founders & exec teams logoSetupClaw: done-for-you OpenClaw for founders & exec teams

White-glove OpenClaw for founders and exec teams (4–50+ employees): we install, harden, integrate your tools, and maintain it — secured from day one.

Get it set up for you
SEO data APIs for your agent, $1 free credit logoSEO data APIs for your agent, $1 free credit

DataForSEO gives your agent live access to SERP results, keyword data, backlinks, and on-page SEO data through one API. New accounts get a $1 credit, good for up to 20,000 keyword or backlink lookups.

Try DataForSEO free
Reach 48,000+ AI builders

A flat monthly placement in front of developers actively installing AI tools. No lock-in, cancel anytime.

Advertise here

Summary

OpenClaw plugin exposing 0 skills.

Install to Claude Code

openclaw plugin add bigbrid2023/gooddog-v4

Run in Claude Code. Add the marketplace first with /plugin marketplace add bigbrid2023/gooddog-v4 if you haven't already.

README.md

GoodDog V1.0 — 成本感知多智能体编排系统

<p align="center"> <strong>Decompose. Route. Execute. Crystallize.</strong> </p>

GoodDog 是一个基于 OpenClaw 网关构建的成本感知多智能体编排系统。它能将复杂任务自动分解为结构化步骤蓝图,通过多臂老虎机(MAB)路由器按成本+成功率自动选择最优模型,并通过依赖图执行引擎协调跨节点的分布式执行。

---

核心能力

V5.2 成本感知 MAB 路由

  • 三层模型体系:Budget(<$0.0005/1k)、Standard($0.0005-$0.005/1k)、Premium(>$0.005/1k)
  • 按任务领域(domain)自动选择成功率最高且成本最低的模型
  • 支持自动升降级链:任务失败时自动升级到更强模型,高成功率时降级到廉价模型

Boss Mode 项目分解

  • 自然语言需求 → 结构化步骤蓝图(JSON)
  • 自动推断步骤依赖关系、并行组、预估难度
  • 每步自动分配最优模型 + 备用/升级模型链
  • 最多 12 步,严格依赖校验

依赖图执行引擎

  • 基于 DAG 的步骤调度:依赖满足 → 自动释放执行
  • 并行组内步骤可并发执行
  • 每步执行后自动记录:实际模型、token 消耗、成本、难度
  • 自动触发模型升降级链

V3.1 自结晶知识库

  • 7 表 SQLite 知识库(skills、model_perf、sessions、antipatterns、nodes、models、dependencies)
  • Sniffer 路由:任务领域 → 已批准 Skill 查找 → 确定性流水线或 Boss Mode
  • Nuwa 认知提取:从会话中提取心智模型、if-then 规则、反模式、诚实边界
  • Crystallizer:L1 约束文档 → L2 参数化模板 → L3 可执行脚本
  • Sniffer-Prime:自动检测重复成功模式,触发结晶化
  • Phase Lock 审批门:架构锁 → 制品生成 → 审批

会话挖掘

  • 自动扫描 ~/.openclaw/state/transcripts/ 中的 JSONL 会话记录
  • 从工具调用模式推断任务领域(12 个领域)
  • 检测成功/失败并引导 model_perf 数据,消除冷启动

集群管理

  • LAN 节点自动发现与注册
  • 每节点实时状态:活跃任务数、最近会话、架构信息
  • Control UI 仪表盘:集群概览 + 项目进度 + 模型层级总览

---

快速开始

# 1. 安装
git clone https://github.com/bigbrid2023/gooddog-v2.git
cd gooddog
pnpm install
pnpm build

# 2. 初始化 V3.1 知识库
cd gooddog-skills/gooddog-v31/scripts
python3 v31.py init

# 3. 导入历史会话数据(引导模型性能)
python3 v31.py import-sessions

# 4. 扫描 LAN 节点
cd ../gooddog-cluster-scan/scripts
python3 scan.py

# 5. 启动网关
cd ../../../
pnpm gateway

访问 Control UI:http://localhost:18789/

---

项目结构

gooddog/
├── src/
│   ├── gooddog/                    # V3.1 知识库 TypeScript 层
│   │   ├── v31-types.ts            # 完整类型定义
│   │   └── v31-skill-registry.ts   # 查询辅助函数
│   ├── gateway/
│   │   └── server-methods/
│   │       └── gooddog.ts          # 网关处理器(集群/项目/模型层级)
│   └── state/
│       └── openclaw-state-schema.sql  # V5.2 数据库迁移
├── ui/src/ui/
│   └── controllers/
│       └── gooddog.ts              # Control UI 控制器
├── gooddog-skills/                 # 5 个 Skill + V3.1
│   ├── gooddog-cluster-scan/       # LAN 节点发现
│   ├── gooddog-task-dispatch/      # 项目分解 + 路由 + 执行
│   ├── gooddog-worker/             # 远端任务轮询守护进程
│   ├── gooddog-v31/                # 自结晶知识库
│   └── gooddog-project-lock/       # 约束驱动项目进展
└── docs/                           # OpenClaw 文档(保留用于网关参考)

---

行为准则

GoodDog 的核心设计原则:

1. Challenge, don't flatter — 对任务分解和模型选择提出质疑,不盲从 2. Minimum steps — 最少步骤原则,避免过度分解 3. Never silent-compliance — 拒绝静默服从,有异议必须提出 4. Stay off the field — 协调者,非执行者。分解 + 路由 + 收集,不做本地推理 5. Phase Lock — 未经显式解锁,绝不修改已锁定的代码

---

许可证

MIT License — 基于 OpenClaw 构建。

Related plugins

Browse all →