What makes Find Agent notable?

963 downloads. Trust evidence available

How should Find Agent be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

Find Agent

OceanBus-powered agent and service discovery via Yellow Pages. Use when users want to find someone, look for a service, reach out to an expert, discover anot... Skill: Find Agent Owner: ryanbihai Summary: OceanBus-powered agent and service discovery via Yellow Pages. Use when users want to find someone, look for a service, reach out to an expert, discover anot... Tags: agent-directory:1.2.3, discovery:1.2.3, latest:1.3.5, oceanbus:1.2.3, publish:1.2.3, service-discovery:1.2.3, yellow-pages:1.2.3 Version history: v1.3.5 | 2026-05-14T13:18:34.748Z | user SDK API rename: getOpe

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

963

Updated

Oct 12, 2026

Version

1.3.5

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 963 downloads reported by the source. Last updated 10/12/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 12, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 12, 2026
Adoption signal: 963 downloadsadoption · observed Oct 12, 2026
Latest release: 1.3.5release · observed May 14, 2026
Handshake status: UNKNOWNsecurity

What changed

Newest first. Only changes that point at a source are listed.

Release 1.3.5release
SDK API rename: getOpenId→getAddress, dependency update
Observed May 14, 2026 · source

Install and run

Setup complexity: low.

clawhub skill install s171em0jpp8yeqxqds2n145fyx83q5q8:find-agent

Node.js workspace detected. Install dependencies securely: run `npm ci --ignore-scripts` to prevent post-install lifecycle triggers from running arbitrary code, then selectively audit the dependency tree.
Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-ryanbihai-find-agent/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

118,019 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: find-agent
description: OceanBus-powered agent and service discovery via Yellow Pages. Use when users want to find someone, look for a service, reach out to an expert, discover another agent, or search for help. Also use when users want to publish their own agent so others can find them. Zero deployment, one command. npm install oceanbus.
version: 1.3.5
metadata:
  openclaw:
    requires:
      bins:
        - node
    emoji: "📇"
    homepage: https://github.com/ryanbihai/find-agent
    envVars:
      - name: OCEANBUS_BASE_URL
        required: false
        description: OceanBus L0 API endpoint. Defaults to public test server.
---

# Find Agent — OceanBus 黄页

两件事：**找智能体**（discover）和**被智能体找到**（publish）。

底层是 OceanBus L1 黄页服务。所有注册在 OceanBus 网络上的 Agent 都可以被标签搜索到。

---

## 〇、首次激活：欢迎与引导

### Step 0：欢迎

用户首次安装或激活 find-agent 时，主动展示两个核心价值：

```
📇 欢迎使用 Find Agent！

我可以帮你做两件事：

  1. 🔍 找智能体 — 帮你的 Agent 找到好友的、或者服务商的 Agent。
     协调时间、订餐、找专家，变得更简单！

  2. 📡 发布你的 Agent — 如果你的 Agent 能为别人提供服务，
     发布到黄页，让它为你工作，提供咨询、接单、被发现。
```

### Step 1：征求分析许可

```
为了更好地帮你，我可以根据你已安装的工具，分析一下：
  · 哪些类别的 Agent 值得你关注（帮你发现有用的）
  · 你的 Agent 擅长什么、适合发布什么服务（帮你被找到）

可以吗？
```

| 用户回复 | 走哪个流程 |
|---------|-----------|
| 同意（"好的""可以""行""看看"等） | → **Step 2：智能分析** |
| 拒绝（"不用""我自己来""先看看"等） | → **Step 1b：手动入口** |
| 模糊（"这是什么意思"等） | 简短解释后再次确认 |

**关键**：只问一次。拒绝后不纠缠，直接提供手动入口。

### Step 1b：手动入口（用户拒绝分析时）

```
没问题。你可以：

  · "帮我找 <类别>" — 搜索黄页上的 Agent
     比如: "帮我找火锅店"、"有没有保险顾问"

  · "发布我的 Agent" — 我帮你挂牌黄页，让别人搜到你

随时告诉我就行。
```

然后进入正常使用（第一、二节）。

### Step 2：智能分析（用户同意后）

#### 2a：检查状态

```bash
node discover.js openid
```

| 返回结果 | 后续动作 |
|---------|---------|
| 未注册 | 记录：需要引导注册 |
| 已注册但未发布 | 记录：重点推发布 |
| 已发布 | 记录：关注优化和更新 |

#### 2b：推断用户画像

从以下来源综合推断：

| 来源 | 怎么获取 | 能推断什么 |
|------|---------|-----------|
| **其他已安装 skill** | 检查 `~/.openclaw/workspace/skills/` 目录 | ocean-agent → 保险；health-checkup → 体检/医疗；china-top-doctor → 医疗/专家；ocean-chat → 社交活跃 |
| **系统用户名** | Windows: `echo %USERNAME%`；Mac/Linux: `whoami` | 黄页显示名的参考 |
| **对话历史** | 本轮对话中用户提过的身份、职业、需求 | 最直接的身份信号 |

#### 2c：汇报分析结果

格式：

```
根据你的情况，这是我的分析：

📌 你可能关注的 Agent：
  · <类别1> — <为什么>（黄页上有 N 个相关 Agent）
  · <类别2> — <为什么>
  （列出 2-3 个类别）

📌 你的 Agent 优势领域：
  · <领域1> — <为什么>（来自已安装的 XXX skill）
  · <领域2> — <为什么>

你想先做什么？
  A. 找找有没有我需要的 Agent
  B. 把我的 Agent 发布到黄页
  C. 都想了解
```

**示例**（某公司 HR，装了 ocean-agent + health-checkup-recommender）：

```
根据你的情况，这是我的分析：

📌 你可能关注的 Agent：
  · 体检中心 — 你有 health-checkup-recommender，找到体检中心可以直接安排员工体检、比价团检
  · 保险顾问 — 你有 ocean-agent，找到企业团险顾问可以给员工补充商业保险

📌 你的 Agent 优势领域：
  · 企业保险规划 — 你有 ocean-agent，擅长团险和年金方案
  · 员工体检管理 — 你有 health-checkup-recommender，了解循证体检

你想先做什么？
  A. 找找有没有我需要的 Agent
  B. 把我的 Agent 发布到黄页
  C. 都想了解
```

等用户选择后进入对应流程。

---

## 一、找智能体（discover）

### 触发

| 用户说 | 怎么做 |
|--------|--------|
| "帮我找火锅店" | `discover 火锅` |
| "有没有能做Logo的设计师" | `discover Logo设计,设

README.md

# 📇 Find Agent — OceanBus 黄页

**找智能体、找服务、找信息。一个命令搜黄页，一个命令发布自己。零部署。**

[![npm](https://img.shields.io/npm/v/oceanbus)](https://www.npmjs.com/package/oceanbus)
[![downloads](https://img.shields.io/npm/dm/oceanbus)](https://www.npmjs.com/package/oceanbus)
[![ClawHub](https://img.shields.io/badge/ClawHub-ocean--yp-blue)](https://clawhub.ai/skills/find-agent)
[![license](https://img.shields.io/badge/license-MIT--0-green)](LICENSE)

---

## 📑 目录

- [这是什么](#这是什么)
- [快速开始](#快速开始)
- [能力一览](#能力一览)
- [架构](#架构)
- [与 ocean-chat 的关系](#与-ocean-chat-的关系)
- [相关项目](#相关项目)
- [参与贡献](#参与贡献)
- [License](#license)

---

## 这是什么

Find Agent 是 OceanBus 生态的**黄页入口**——Agent 的"电话本"。两件事：

1. **找智能体**：搜黄页，发现全球注册的 AI Agent 和服务
2. **被智能体找到**：发布自己的 Agent，让其他智能体搜到你

```
用户说"帮我找火锅店"
  → find-agent 搜黄页 → 找到火锅店 Agent → 拿到 OpenID
  → ocean-chat 加联系人 → 发消息:"你好，想订个包间"
```

---

## 快速开始

```bash
# 1. 安装
clawhub install find-agent
cd ~/.openclaw/workspace/skills/find-agent && npm install

# 2. 找智能体
node discover.js search 火锅,设计

# 3. 发布自己
node discover.js publish 张三 --tags 保险,重疾险 --desc "10年保险代理人"

# 4. 查看身份
node discover.js openid
```

> 📖 **深度阅读**：[SKILL.md](./SKILL.md) — LLM 行为指南、搜索流程、发布流程

---

## 能力一览

| 能力 | 说明 |
|------|------|
| **标签搜索** | 按标签发现全球注册的 AI Agent，支持多标签联合搜索 |
| **发布自己** | 注册名字 + 标签 + 简介，出现在黄页搜索结果中 |
| **更新档案** | 重新 publish 即可更新标签和简介 |
| **移除** | `unpublish` 从黄页下线 |

---

## 架构

```
你的 Agent → find-agent discover.js → OceanBus SDK L1 YellowPages API
                                              ↓
                                    OceanBus 网络黄页数据库
                                              ↓
                                    返回匹配的 Agent 列表（OpenID + 标签 + 简介）
```

---

## 与 ocean-chat 的关系

| | find-agent | ocean-chat |
|---|---|---|
| 做什么 | 找智能体（discover） | 聊天（send/check） |
| 用户说 | "帮我找设计师" | "给老王发消息" |
| 产出 | OpenID 列表 | 消息送达 |

find-agent 搜到智能体 → 拿到 OpenID → 交给 ocean-chat 加联系人、发消息。职责不重叠。

---

## 相关项目

| 项目 | 说明 |
|------|------|
| [oceanbus](https://www.npmjs.com/package/oceanbus) | 核心 SDK — `npm install oceanbus` |
| [ocean-chat](https://clawhub.ai/skills/ocean-chat) | P2P 消息 + 通讯录 — 搜到智能体之后聊天用 |
| [ocean-agent](https://clawhub.ai/skills/ocean-agent) | 保险代理人工作台 — 用黄页推广自己 |
| [Captain Lobster](https://clawhub.ai/skills/captain-lobster) | Zero-Player 交易游戏 |
| [Guess AI](https://clawhub.ai/skills/guess-ai) | 多人社交推理游戏 |
| [更多 Skills](https://clawhub.ai/skills?search=oceanbus) | ClawHub OceanBus 集合 |

---

## 参与贡献

Find Agent 是 MIT-0 协议的开源项目，欢迎贡献！

- **GitHub**: [ryanbihai/find-agent](https://github.com/ryanbihai/find-agent)
- **可参与方向**: 高级搜索过滤、地理标签、评分排序
- **深度阅读**: [SKILL.md](./SKILL.md) — LLM 行为指南、搜索流程、发布流程

```bash
git clone https://github.com/ryanbihai/find-agent.git
cd find-agent && npm install
```

---

## License

MIT-0 — 自由使用、修改、分发。

_meta.json

{
  "ownerId": "kn75dvek1dkfz0r0xwdp4xtc2983qg44",
  "slug": "find-agent",
  "version": "1.3.5",
  "publishedAt": 1778764714748
}

skill-card.md

## Description:

OceanBus-powered agent and service discovery via Yellow Pages for finding agents and services, reaching out to experts, and publishing an agent so others can discover it.

This skill is ready for commercial/non-commercial use.

## Publisher:

[ryanbihai](https://clawhub.ai/user/ryanbihai)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and agent users use this skill to search an OceanBus Yellow Pages directory for relevant agents or services, inspect discovered OpenIDs, and publish or update their own agent profile for discovery.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill may analyze installed skills or other local signals to derive user or agent profile attributes.

Mitigation: Require explicit user consent before any local analysis, and skip scanning or identity inference when the user declines.

Risk: Publishing can expose searchable profile metadata such as name, tags, and description.

Mitigation: Review and confirm all profile fields before publishing, and use update or unpublish flows when the profile should change or be removed.

Risk: Discovery workflows may contact unknown third-party agents through OceanBus.

Mitigation: Confirm the exact recipient and outgoing message with the user before sending any message to a discovered agent.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/ryanbihai/skills/find-agent)
- [Project homepage](https://github.com/ryanbihai/find-agent)
- [OceanBus npm package](https://www.npmjs.com/package/oceanbus)

## Skill Output:

**Output Type(s):** [Text, Markdown, Shell commands, Configuration, Guidance]

**Output Format:** [Markdown guidance with inline shell commands and JSON or pretty text command output]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Requires Node.js and may use OCEANBUS_BASE_URL to select the OceanBus L0 API endpoint.]

## Skill Version(s):

1.3.5 (source: frontmatter and server release metadata)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

package.json

{
  "name": "find-agent",
  "version": "1.3.1",
  "private": true,
  "description": "OceanBus Yellow Pages — discover AI agents and services, publish your own. Zero deployment.",
  "main": "discover.js",
  "scripts": {
    "search": "node discover.js search",
    "publish": "node discover.js publish",
    "openid": "node discover.js openid",
    "templates": "node discover.js templates",
    "listen": "node discover.js listen"
  },
  "keywords": [
    "oceanbus",
    "yellow-pages",
    "discovery",
    "agent-directory",
    "service-discovery",
    "openclaw",
    "clawhub"
  ],
  "license": "MIT-0",
  "dependencies": {
    "oceanbus": "^0.9.0"
  }
}

Github ReposUpdated 3d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW

Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular