Even Realities G2 智能眼镜连接 OpenClaw 网关桥接器部署指南

even-g2-bridge by daaab/openclaw-skills

1 周安装量

1 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/daaab/openclaw-skills --skill even-g2-bridge

物联网自动化云服务

🇨🇳中文介绍

Even Realities G2 × OpenClaw 桥接器

部署一个 Cloudflare Worker，用于连接 Even Realities G2 智能眼镜与您的 OpenClaw 网关。

功能概述

G2 眼镜 → (语音转文字) → CF Worker → OpenClaw 网关 → 完整智能体
                                ↓                              ↓
                          G2 显示屏 (文本)             Telegram (富媒体内容)

简短任务 (聊天、提问)：网关响应 → 显示在 G2 上
长时任务 (编写代码、文章)：G2 显示"正在处理中..." → 结果发送至 Telegram
图像生成 ：DALL-E 生成 → 发送至 Telegram (G2 无法显示图像)
备用方案 ：如果网关不可用，则回退至直接调用 Claude API

先决条件

Even Realities G2 眼镜及 Even 应用 (v0.0.7+ 版本，支持"添加智能体"功能)
已启用 HTTP API 的 OpenClaw 网关
Cloudflare 账户 (免费套餐即可)
Anthropic API 密钥 (备用)
可选：OpenAI API 密钥 (用于图像生成)、Telegram 机器人令牌 (用于富媒体内容推送)

设置步骤

1. 启用 OpenClaw 网关 HTTP API

在您的 OpenClaw 主机上，启用聊天补全端点：

openclaw config set gateway.http.endpoints.chatCompletions.enabled true
openclaw gateway restart

验证：

curl -X POST https://YOUR_GATEWAY_URL/v1/chat/completions \
  -H "Authorization: Bearer YOUR_GATEWAY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model":"openclaw","messages":[{"role":"user","content":"hi"}]}'

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

2. 部署 Cloudflare Worker

将 scripts/worker.js 复制到您的项目，然后部署：

# 安装 wrangler
npm install -g wrangler

# 登录 Cloudflare
wrangler login

# 部署
wrangler deploy

或者使用 Cloudflare 仪表板：Workers & Pages → 创建 → 上传 worker.js。

# 必需项
wrangler secret put GATEWAY_URL      # 您的 OpenClaw 网关 URL
wrangler secret put GATEWAY_TOKEN    # 您的网关认证令牌
wrangler secret put G2_TOKEN         # G2 眼镜认证令牌 (您自行设定)
wrangler secret put ANTHROPIC_API_KEY # 网关不可用时的备用密钥

# 可选项 (用于向 Telegram 推送富媒体内容)
wrangler secret put TELEGRAM_BOT_TOKEN
wrangler secret put TELEGRAM_CHAT_ID

# 可选项 (用于图像生成)
wrangler secret put OPENAI_API_KEY

在 Even 应用 → 设置 → 添加智能体：

名称：您的智能体名称 (例如，"云端龙虾")
URL ：https://YOUR_WORKER.workers.dev
令牌：您上面设置的 G2_TOKEN

curl -X POST https://YOUR_WORKER.workers.dev \
  -H "Authorization: Bearer YOUR_G2_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model":"openclaw","messages":[{"role":"user","content":"Hello, who are you?"}]}'

G2 将语音转换为文字，以 OpenAI 聊天补全格式发送
Worker 通过 G2_TOKEN 进行身份验证
Worker 对请求进行分类：
- 图像生成 → 调用 DALL-E + 发送至 Telegram (立即向 G2 返回确认)
- 长时任务 → 立即向 G2 返回确认 + 后台调用网关 → 结果发送至 Telegram
- 简短任务 → 代理转发至网关 → 结果返回给 G2
网关运行完整的智能体循环 (记忆、工具、技能)
响应内容经过过滤后显示在 G2 上 (URL、代码块等内容将发送至 Telegram)

双层令牌认证：

G2 --[G2_TOKEN]--> Worker --[GATEWAY_TOKEN]--> Gateway

G2 仅知晓 G2_TOKEN — 如果眼镜丢失，只需更换此令牌
GATEWAY_TOKEN 始终保存在 Worker 密钥中，不会暴露给眼镜
网关 HTTP API 应置于认证之后 (令牌或密码模式)

576×136 像素，单色绿屏，约 48 字符宽度
仅支持文本 (无图像，无 Markdown 渲染)
Worker 自动过滤：URL → [链接]，代码块 → [代码]，长文本 → 截断
无法显示的内容将转发至 Telegram

编辑 worker.js 中的任务分类正则表达式：

isLongTask() — 触发后台处理的模式
isImageGenRequest() — 触发 DALL-E 的模式

G2 显示"未授权" ：检查 Worker 密钥和 Even 应用中的 G2_TOKEN 是否匹配
"网关未配置" ：确认 GATEWAY_URL 和 GATEWAY_TOKEN 密钥已设置
简短任务超时 ：网关可能响应较慢；可增加 SHORT_TIMEOUT 值 (CF Workers 最长约 25 秒)
Telegram 未收到推送 ：检查 TELEGRAM_BOT_TOKEN 和 TELEGRAM_CHAT_ID 密钥
网关返回 404 ：确保 OpenClaw 配置中 chatCompletions.enabled: true 并已重启

🇺🇸English

Even Realities G2 × OpenClaw Bridge

Deploy a Cloudflare Worker that connects Even Realities G2 smart glasses to your OpenClaw Gateway.

What It Does

G2 Glasses → (voice→text) → CF Worker → OpenClaw Gateway → Full Agent
                                ↓                              ↓
                          G2 display (text)            Telegram (rich content)

Short tasks (chat, questions): Gateway responds → displayed on G2
Long tasks (write code, articles): G2 shows "Working on it..." → result sent to Telegram
Image generation : DALL-E generates → sent to Telegram (G2 can't show images)
Fallback : If Gateway is down, falls back to direct Claude API

Prerequisites

Even Realities G2 glasses with Even app (v0.0.7+ with "Add Agent" support)
OpenClaw Gateway with HTTP API enabled
Cloudflare account (free plan works)
Anthropic API key (fallback)
Optional: OpenAI API key (image gen), Telegram bot token (rich content delivery)

Setup

1. Enable OpenClaw Gateway HTTP API

On your OpenClaw host, enable the chat completions endpoint:

openclaw config set gateway.http.endpoints.chatCompletions.enabled true
openclaw gateway restart

Verify:

curl -X POST https://YOUR_GATEWAY_URL/v1/chat/completions \
  -H "Authorization: Bearer YOUR_GATEWAY_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model":"openclaw","messages":[{"role":"user","content":"hi"}]}'

2. Deploy Cloudflare Worker

Copy scripts/worker.js to your project, then deploy:

# Install wrangler
npm install -g wrangler

# Login to Cloudflare
wrangler login

# Deploy
wrangler deploy

Or use the Cloudflare Dashboard: Workers & Pages → Create → Upload worker.js.

3. Set Secrets

# Required
wrangler secret put GATEWAY_URL      # Your OpenClaw Gateway URL
wrangler secret put GATEWAY_TOKEN    # Your Gateway auth token
wrangler secret put G2_TOKEN         # Token for G2 glasses auth (you choose)
wrangler secret put ANTHROPIC_API_KEY # Fallback when Gateway is down

# Optional (for Telegram delivery of rich content)
wrangler secret put TELEGRAM_BOT_TOKEN
wrangler secret put TELEGRAM_CHAT_ID

# Optional (for image generation)
wrangler secret put OPENAI_API_KEY

4. Configure G2 Glasses

In Even app → Settings → Add Agent:

Name : Your agent name (e.g., "Cloud Lobster")
URL : https://YOUR_WORKER.workers.dev
Token : The G2_TOKEN you set above

5. Test

curl -X POST https://YOUR_WORKER.workers.dev \
  -H "Authorization: Bearer YOUR_G2_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"model":"openclaw","messages":[{"role":"user","content":"Hello, who are you?"}]}'

Architecture

Request Flow

G2 converts speech → text, sends as OpenAI chat completion format
Worker authenticates via G2_TOKEN
Worker classifies request:
- Image gen → DALL-E + Telegram (immediate G2 ack)
- Long task → immediate G2 ack + background Gateway call → Telegram
- Short task → proxy to Gateway → return to G2
Gateway runs full agent loop (memory, tools, skills)
Response filtered for G2 display (no URLs, code blocks → Telegram)

Security

Two-layer token auth:

G2 --[G2_TOKEN]--> Worker --[GATEWAY_TOKEN]--> Gateway

G2 only knows G2_TOKEN — if glasses are lost, change only this token
GATEWAY_TOKEN stays in Worker secrets, never exposed to glasses
Gateway HTTP API should be behind auth (token or password mode)

G2 Display Limitations

576×136 pixels, monochrome green, ~48 chars wide
Text only (no images, no markdown rendering)
Worker auto-filters: URLs → [link], code blocks → [code], long text → truncated
Non-displayable content forwarded to Telegram

Customization

Edit the task classification regex in worker.js:

isLongTask() — patterns that trigger background processing
isImageGenRequest() — patterns that trigger DALL-E

Troubleshooting

G2 says "Unauthorized" : Check G2_TOKEN matches in Worker secrets and Even app
"Gateway not configured" : Verify GATEWAY_URL and GATEWAY_TOKEN secrets are set
Timeout on short tasks : Gateway may be slow; increase SHORT_TIMEOUT (max ~25s for CF Workers)
No Telegram delivery : Check TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID secrets
Gateway returns 404 : Ensure chatCompletions.enabled: true in OpenClaw config + restart

Weekly Installs

Repository

daaab/openclaw-skills

GitHub Stars

First Seen

Today

Security Audits

Gen Agent Trust HubPass SocketFail SnykWarn

Installed on

zencoder1

amp1

cline1

openclaw1

opencode1

cursor1

Azure 升级评估与自动化工具 - 轻松迁移 Functions 计划、托管层级和 SKU

79,900 周安装