Xpersona
agentCLAWHUBUnverified

Hermes Installer

Hermes Agent 安装配置完整指南。当用户要求安装 Hermes Agent、部署 Hermes、配置模型提供商、配置飞书/Telegram/Discord 网关时使用此 Skill。触发词：安装 Hermes、部署 Hermes Agent、配置 Hermes、配置 GLM、配置 Kimi、配置 Ope...

OpenClaw
View on ClawHubHomepage

Rank

62

Safety

84

Downloads

1.9k

Updated

Oct 10, 2026

Version

1.1.7

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.9K downloads reported by the source. Last updated 10/10/2026.

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 10, 2026
Protocol compatibility
OpenClawcompatibility · observed Oct 10, 2026
Adoption signal
1.9K downloadsadoption · observed Oct 10, 2026
Latest release
1.1.7release · observed Apr 11, 2026
Handshake status
UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s176hvjm2gj04tc8c17k5qxm1s84m1w8:hermes-installer
  1. Install using `clawhub skill install s176hvjm2gj04tc8c17k5qxm1s84m1w8:hermes-installer` in an isolated environment before connecting it to live workloads.
  2. No published capability contract is available yet, so validate auth and request/response behavior manually.
  3. Review the upstream CLAWHUB listing at https://clawhub.ai/dongyu23/hermes-installer before using production credentials.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-dongyu23-hermes-installer/snapshot"

Documentation

CLAWHUB

135,424 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: hermes-installer
description: Hermes Agent 安装配置完整指南。当用户要求安装 Hermes Agent、部署 Hermes、配置模型提供商、配置飞书/Telegram/Discord 网关时使用此 Skill。触发词：安装 Hermes、部署 Hermes Agent、配置 Hermes、配置 GLM、配置 Kimi、配置 OpenRouter、配置阿里云百炼、配置腾讯云、配置火山引擎、配置阶跃星辰、Hermes 更新、Hermes 飞书配置。
metadata:
  openclaw:
    requires:
      env:
        - OPENAI_API_KEY
        - OPENAI_BASE_URL
      bins:
        - git
        - python
        - pip
        - docker
---

# Hermes Agent 安装配置指南

## 系统支持

- **Linux/macOS**：使用 `.sh` 脚本
- **Windows**：以下三种方式任选其一：
  1. **Git Bash**：安装 Git 后自带，可以直接运行 `.sh` 脚本
  2. **WSL**：Windows Linux 子系统
  3. **手动执行**：不运行脚本，直接在 PowerShell 中执行对应命令

---

## CLI 与消息平台

Hermes 有两个入口：

### 1. 终端界面（CLI）
启动交互式终端界面：
```bash
hermes
```

### 2. 消息平台（Gateway）
运行网关，通过消息平台对话：
```bash
hermes gateway start
```

**支持的平台**：Telegram、Discord、Slack、WhatsApp、Signal、Email

---

### 常用命令对照表

| 功能 | CLI 命令 | 消息平台命令 |
|------|----------|--------------|
| 开始聊天 | `hermes run` | 向机器人发送消息 |
| 设置网关 | `hermes gateway setup` | - |
| 启动网关 | `hermes gateway start` | - |
| 新对话 | `/new` 或 `/reset` | `/new` 或 `/reset` |
| 改变模型 | `/model [provider:model]` | `/model [provider:model]` |
| 设定人格 | `/personality [name]` | `/personality [name]` |
| 重试/撤销 | `/retry` 或 `/undo` | `/retry` 或 `/undo` |
| 压缩上下文 | `/compress` | `/compress` |
| 查看使用 | `/usage` 或 `/insights` | `/usage` 或 `/insights` |
| 浏览技能 | `/skills` 或 `/<skill-name>` | `/skills` 或 `/<skill-name>` |
| 中断 | Ctrl+C 或发送新消息 | `/stop` 或发送新消息 |
| 平台状态 | - | `/status` 或 `/sethome` |

---

## 从 OpenClaw 迁移

如果你是从 OpenClaw 过来的，Hermes 可以自动导入你的设置、记忆、技能和 API 密钥。

### 首次设置时
运行 `hermes setup`，设置向导会自动检测 `~/.openclaw` 并在配置开始前提供迁移建议。

### 安装后任何时间
```bash
hermes claw migrate              # 交互式迁移（完整配置）
hermes claw migrate --dry-run    # 预览将要迁移的内容
hermes claw migrate --preset user-data   # 不包含密钥的迁移
hermes claw migrate --overwrite  # 覆盖已有冲突
```

## 快速安装

### 安装前确认

在执行安装前，**必须向用户确认以下信息**：

| 确认项 | 默认值 | 说明 |
|--------|--------|------|
| **安装位置** | `~/.hermes/hermes-agent` | Hermes Agent 程序目录 |
| **配置目录** | `~/.hermes` | 配置文件和日志目录 |
| **Python 版本** | 3.11 | 虚拟环境 Python 版本 |

**确认话术：**
> 将在以下位置安装 Hermes Agent：
> - 程序目录：`~/.hermes/hermes-agent`
> - 配置目录：`~/.hermes`
>
> 请选择安装方式：
> 1. 命令行部署（推荐，需要 Python 3.11+）
> 2. Docker 部署（需要 Docker）
>
> 请回复数字或方式名称，确认安装？(y/n)

### 安装步骤

**方式一：命令行部署**
```bash
# 1. 克隆仓库
git clone https://github.com/NousResearch/hermes-agent.git ~/.hermes/hermes-agent
cd ~/.hermes/hermes-agent

# 2. 安装 uv（使用 pip，更安全）
pip install uv

# 3. 创建虚拟环境
uv venv venv --python 3.11
source venv/bin/activate
uv pip install -e ".[all]"
```

**方式二：Docker 部署**
详见 [docker-deploy.md](./docker-deploy.md)
git clone https://github.com/NousResearch/hermes-agent.git ~/.hermes/hermes-agent
cd ~/.hermes/hermes-agent

# 2. 安装 uv（使用 pip，更安全）
pip install uv

# 3. 创建虚拟环境
uv venv venv --python 3.11
source venv/bin/activate
uv pip install -e ".[all]"
```

> 提示：使用 pip 安装 uv 不需要执行远程脚本，更安全。如有需要，也可以使用 uv 的预编译二进制：https://github.com/astral-sh/uv/releases

## 配置文件

- 配置文件：`~/.hermes/config.

_meta.json

{
  "ownerId": "kn78jdwk28by2c7gg2jrr4yx6584nn0z",
  "slug": "hermes-installer",
  "version": "1.1.7",
  "publishedAt": 1775886075934
}

api-config.md

# 模型提供商 API 配置

用户提供 API Key 和模型名称后，按以下模板配置：

---

## OpenRouter（推荐，聚合 200+ 模型）

**config.yaml:**
```yaml
model:
  provider: openrouter
  default: MODEL_NAME
```

**.env:**
```bash
OPENROUTER_API_KEY=YOUR_API_KEY
```

**可用模型：**
- `anthropic/claude-sonnet-4`
- `anthropic/claude-opus-4`
- `openai/gpt-4o`
- `google/gemini-pro-1.5`
- `meta-llama/llama-3.1-70b-instruct`

**文档：** https://openrouter.ai/docs

---

## 智谱 GLM Coding Plan（推荐用于 Coding 场景）

**config.yaml:**
```yaml
model:
  provider: custom
  base_url: https://open.bigmodel.cn/api/coding/paas/v4
  default: MODEL_NAME
```

**.env:**
```bash
OPENAI_API_KEY=YOUR_API_KEY
OPENAI_BASE_URL=https://open.bigmodel.cn/api/coding/paas/v4
```

**可用模型：**
- `glm-5`
- `glm-4-plus`
- `glm-4-air`
- `glm-4-flash`
- `glm-4.7`（支持思考模式）

**重要提示：**
- **Coding Plan 端点**：`https://open.bigmodel.cn/api/coding/paas/v4`（消耗 Coding Plan 额度）
- **通用端点**：`https://open.bigmodel.cn/api/paas/v4/`（产生额外费用）

**文档：** https://open.bigmodel.cn/dev/api

---

## z.ai（GLM 国际版）

**config.yaml:**
```yaml
model:
  provider: custom
  base_url: https://api.z.ai/api/paas/v4/
  default: MODEL_NAME
```

**.env:**
```bash
OPENAI_API_KEY=YOUR_API_KEY
OPENAI_BASE_URL=https://api.z.ai/api/paas/v4/
```

**可用模型：**
- `glm-5`
- `glm-4-plus`
- `glm-4-air`
- `glm-4-flash`

**文档：** https://api.z.ai

---

## Kimi Coding Plan（推荐用于 Coding 场景）

**config.yaml:**
```yaml
model:
  provider: custom
  base_url: https://api.kimi.com/coding/v1
  default: MODEL_NAME
```

**.env:**
```bash
OPENAI_API_KEY=YOUR_API_KEY
OPENAI_BASE_URL=https://api.kimi.com/coding/v1
```

**可用模型：**
- `kimi-k2.5`（最新版，支持视觉和思考）

**重要提示：**
- **Coding Plan 端点**：`https://api.kimi.com/coding/v1`（消耗 Coding Plan 额度）
- **通用端点**：`https://api.moonshot.cn/v1`（产生额外费用）

**文档：** https://platform.kimi.com/docs/api/chat

---

## Kimi / Moonshot（通用端点）

**config.yaml:**
```yaml
model:
  provider: custom
  base_url: https://api.moonshot.cn/v1
  default: MODEL_NAME
```

**.env:**
```bash
OPENAI_API_KEY=YOUR_API_KEY
OPENAI_BASE_URL=https://api.moonshot.cn/v1
```

**可用模型：**
- `kimi-k2.5`
- `kimi-k2-thinking`
- `kimi-k2-0905-preview`
- `moonshot-v1-8k`
- `moonshot-v1-32k`
- `moonshot-v1-128k`

**文档：** https://platform.kimi.com/docs/api/chat

---

## 阿里云百炼 Coding Plan（推荐用于 Coding 场景）

**config.yaml:**
```yaml
model:
  provider: custom
  base_url: https://coding.dashscope.aliyuncs.com/v1
  default: MODEL_NAME
```

**.env:**
```bash
OPENAI_API_KEY=sk-sp-xxxxx  # Coding Plan 专属 API Key
OPENAI_BASE_URL=https://coding.dashscope.aliyuncs.com/v1
```

**重要提示：**
- **API Key 格式**：`sk-sp-xxxxx`（Coding Plan 专属）
- **Coding Plan 端点**：`https://coding.dashscope.aliyuncs.com/v1`
- **通用端点**：`https://dashscope.aliyuncs.com/compatible-mode/v1`

**控制台：** https://bailian.console.aliyun.com/cn-beijing/?tab=model#/efm/coding_plan

---

## 阿里云百炼（通用端点）

**config.yaml:**
```yaml
model:
  provider: custom
  base_url: https://dashscope.aliyuncs.com/compatible-mode/v1
  default: MODEL_NAME
```

**.env:**
```bash
OPENAI_API_KEY=sk-xxxxx
OPENAI_BA

docker-deploy.md

# Docker 部署指南

## 安装

```bash
# 1. 克隆仓库
git clone https://github.com/NousResearch/hermes-agent.git ~/.hermes/hermes-agent
cd ~/.hermes/hermes-agent

# 2. 构建镜像
docker build -t hermes-agent .

# 3. 运行容器
docker run -d -v ~/.hermes:/opt/data hermes-agent
```

---

## 升级

```bash
# 1. 进入映射目录
cd ~/.hermes/hermes-agent

# 2. 拉取最新代码
git pull origin main

# 3. 重新构建镜像
docker build -t hermes-agent .

# 4. 停止旧容器并重新运行
docker stop hermes-container 2>/dev/null || true
docker rm hermes-container 2>/dev/null || true
docker run -d --name hermes-container -v ~/.hermes:/opt/data hermes-agent
```

---

## 卸载

```bash
# 1. 停止并删除容器
docker stop hermes-container
docker rm hermes-container

# 2. 删除镜像
docker rmi hermes-agent

# 3. 删除配置目录（可选）
# rm -rf ~/.hermes
```

---

## 配置持久化

- 配置目录映射：`~/.hermes` → `/opt/data`
- 在宿主机上编辑 `~/.hermes/config.yaml` 和 `~/.hermes/.env`
- 容器重启后配置保持不变

gateway-config.md

# 网关配置（飞书/Telegram/Discord）

---

## 飞书网关配置

### 1. 创建飞书应用

1. 访问 [飞书开放平台](https://open.feishu.cn/app)
2. 创建企业自建应用
3. 记录 App ID 和 App Secret

### 2. 配置应用权限

| 权限名称 | 权限标识 |
|---------|---------|
| 获取用户信息 | `contact:user.base:readonly` |
| 接收消息 | `im:message` |
| 发送消息 | `im:message:send_as_bot` |
| 获取群信息 | `im:chat:readonly` |

### 3. 配置事件订阅

- 请求网址：`https://your-server.com/webhook/feishu`
- 订阅事件：`im.message.receive_v1`

### 4. 安装依赖

```bash
uv pip install lark-oapi aiohttp websockets
```

### 5. 配置环境变量

```bash
# ~/.hermes/.env
FEISHU_APP_ID=cli_xxx
FEISHU_APP_SECRET=xxx
FEISHU_ENABLED=true
GATEWAY_ALLOWED_USERS=ou_xxx
```

### 6. 启动网关

```bash
hermes gateway run
```

### 7. 配对用户

```bash
hermes pairing approve feishu PAIRING_CODE
```

---

## Telegram 网关配置

### 1. 创建 Telegram Bot

1. 在 Telegram 中搜索 `@BotFather`
2. 发送 `/newbot`
3. 按提示设置名称和用户名
4. 记录 Bot Token

### 2. 配置环境变量

```bash
# ~/.hermes/.env
TELEGRAM_BOT_TOKEN=123456789:ABCdefGHIjklMNOpqrsTUVwxyz
TELEGRAM_ENABLED=true
```

### 3. 配对用户

```bash
hermes pairing approve telegram PAIRING_CODE
```

---

## Discord 网关配置

### 1. 创建 Discord Bot

1. 访问 [Discord Developer Portal](https://discord.com/developers/applications)
2. 创建应用 → Bot → Add Bot
3. 记录 Bot Token
4. 生成邀请链接（Scopes: bot, Permissions: Send/Read Messages）

### 2. 配置环境变量

```bash
# ~/.hermes/.env
DISCORD_BOT_TOKEN=xxx
DISCORD_ENABLED=true
```

### 3. 配对用户

```bash
hermes pairing approve discord PAIRING_CODE
```

---

## 多网关同时运行

```bash
# ~/.hermes/.env
FEISHU_APP_ID=cli_xxx
FEISHU_APP_SECRET=xxx
FEISHU_ENABLED=true

TELEGRAM_BOT_TOKEN=xxx
TELEGRAM_ENABLED=true

DISCORD_BOT_TOKEN=xxx
DISCORD_ENABLED=true

GATEWAY_ALLOWED_USERS=ou_xxx,ou_yyy
```

---

## 用户白名单

```bash
# 多个用户用逗号分隔
GATEWAY_ALLOWED_USERS=ou_xxx,ou_yyy,ou_zzz
```

---

## 网关管理命令

| 命令 | 说明 |
|------|------|
| `hermes gateway status` | 查看网关状态 |
| `hermes gateway start/stop` | 启停网关 |
| `hermes pairing list` | 查看已配对用户 |
| `hermes pairing approve feishu CODE` | 批准飞书用户 |
| `hermes pairing approve telegram CODE` | 批准 Telegram 用户 |
| `hermes pairing approve discord CODE` | 批准 Discord 用户 |

---

## 故障排查

### 飞书连接失败

```bash
hermes gateway status
cat ~/.hermes/logs/agent.log
```

### 用户被拒绝

```bash
hermes config show | grep -A5 allowed
hermes pairing approve feishu CODE
```

Related agents

Same protocol, similar job.

Github ReposUpdated 8h 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

OPENCLAW

Machine-readable data

The same record, as JSON, for agents and crawlers.

{
  "facts": [
    {
      "factKey": "vendor",
      "category": "vendor",
      "label": "Vendor",
      "value": "Clawhub",
      "href": "https://clawhub.ai/dongyu23/skills/hermes-installer",
      "sourceUrl": "https://clawhub.ai/dongyu23/skills/hermes-installer",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-10T00:02:43.768Z",
      "isPublic": true
    },
    {
      "factKey": "protocols",
      "category": "compatibility",
      "label": "Protocol compatibility",
      "value": "OpenClaw",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-dongyu23-hermes-installer/contract",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-dongyu23-hermes-installer/contract",
      "sourceType": "contract",
      "confidence": "medium",
      "observedAt": "2026-10-10T00:02:43.768Z",
      "isPublic": true
    },
    {
      "factKey": "traction",
      "category": "adoption",
      "label": "Adoption signal",
      "value": "1.9K downloads",
      "href": "https://clawhub.ai/dongyu23/hermes-installer",
      "sourceUrl": "https://clawhub.ai/dongyu23/hermes-installer",
      "sourceType": "profile",
      "confidence": "medium",
      "observedAt": "2026-10-10T00:02:43.768Z",
      "isPublic": true
    },
    {
      "factKey": "latest_release",
      "category": "release",
      "label": "Latest release",
      "value": "1.1.7",
      "href": "https://clawhub.ai/dongyu23/hermes-installer",
      "sourceUrl": "https://clawhub.ai/dongyu23/hermes-installer",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-04-11T05:41:15.934Z",
      "isPublic": true
    },
    {
      "factKey": "handshake_status",
      "category": "security",
      "label": "Handshake status",
      "value": "UNKNOWN",
      "href": "https://www.xpersona.co/api/v1/agents/clawhub-dongyu23-hermes-installer/trust",
      "sourceUrl": "https://www.xpersona.co/api/v1/agents/clawhub-dongyu23-hermes-installer/trust",
      "sourceType": "trust",
      "confidence": "medium",
      "observedAt": null,
      "isPublic": true
    }
  ],
  "events": [
    {
      "eventType": "release",
      "title": "Release 1.1.7",
      "description": "拆分 docker-deploy.md 独立文档",
      "href": "https://clawhub.ai/dongyu23/hermes-installer",
      "sourceUrl": "https://clawhub.ai/dongyu23/hermes-installer",
      "sourceType": "release",
      "confidence": "medium",
      "observedAt": "2026-04-11T05:41:15.934Z",
      "isPublic": true
    }
  ]
}

Record generated Oct 10, 2026.

Sponsored

Ads related to Hermes Installer and adjacent AI workflows.