Token导航 LogoToken导航TokenDH.com
开发需要联网clawhub未标认证来源可访问clear审计提醒

clawdiocommsclawdiocomms 开发

Agent Skill

clawdiocomms 用于补充开发相关能力,适合在 OpenClaw 中需要让 Agent 承接开发相关任务时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

总安装

41,834

周安装

1,797

GitHub Stars

公开资料未说明

下载量

14,664
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:clawdiocomms(clawdiocomms 开发)
来源仓库:https://github.com/jameseball/clawdiocomms
安装命令:
openclaw skills install clawdiocomms
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install clawdiocomms

简介

适用于 AI 代理的与传输无关的安全 P2P 通信。噪音 XX 握手、XChaCha20-Poly1305 加密、连接同意、人工验证。无 WebSocket — 可通过 Telegram、Signal 或任何消息传输进行工作。

SKILL.md

name
clawdio
version
2.2.0
description
Secure P2P communication for AI agents via Telegram. Simple onboarding: create "Clawdio Hub" group, add bot, share keys. Noise XX handshake, XChaCha20-Poly1305 encryption, connection consent, human verification.

Clawdio

Secure peer-to-peer communication for AI agents using Telegram as transport. Create a "Clawdio Hub" group, add your bot, and you're ready to connect with other agents securely. Agents perform Noise XX handshake over Telegram, then communicate via encrypted channels.

When to Use

  • Secure agent-to-agent communication via Telegram
  • Task delegation between agents on different machines
  • Distributed AI workflows requiring encrypted P2P messaging
  • Cross-platform agent coordination without port forwarding

Why Telegram

  • Always online — No port forwarding, NAT, or server setup
  • Reliable delivery — Messages queue when peers offline
  • Universal access — Works from anywhere with internet
  • Battle-tested — Handles billions of messages daily
  • OpenClaw integration — Simple message tool for send/receive
  • Offline resilience — Messages delivered when peer comes back online

Quick Onboarding

First Time Setup (Your Agent)

  1. Install Clawdio: clawhub install clawdiocomms
  2. Create a Telegram group called "Clawdio Hub"
  3. Add your OpenClaw bot to the group
  4. Send your agent the group ID (or agent auto-detects it)
  5. Your agent generates your identity and you're ready

Connecting to a Peer

  1. Share your public key with your friend
  2. Your friend does the same setup on their end
  3. Your friend shares their public key + their Clawdio Hub group ID with you
  4. Your agent creates a topic/thread in your Clawdio Hub for this peer (e.g. "James <> Alex")
  5. Connection request sent — friend's agent asks for consent
  6. Friend approves
  7. Noise XX handshake happens over Telegram messages in the dedicated topics
  8. You're connected — encrypted comms flowing

Human Verification (Optional but Recommended)

  1. Meet in person
  2. Both run: compare 6-word verification codes
  3. If they match, mark as human-verified

Technical Setup

cd projects/clawdio && npm install && npx tsc

Quick Start

const { Clawdio } = require('./projects/clawdio/dist/index.js');

// Create two nodes
const alice = await Clawdio.create({ autoAccept: true });
const bob = await Clawdio.create({ autoAccept: true });

// Wire transport (agents decide HOW to send)
alice.onSend((peerId, msg) => bob.receive(alice.publicKey, msg));
bob.onSend((peerId, msg) => alice.receive(bob.publicKey, msg));

// Connect (Noise XX handshake)
const aliceId = await bob.connect(alice.publicKey);

// Send messages
await bob.send(aliceId, { task: "What's the weather?" });
alice.onMessage((msg, from) => console.log(msg.task));

Using with Telegram (via OpenClaw)

const node = await Clawdio.create({ owner: 'James' });

// Send via Telegram
node.onSend((peerId, base64Message) => {
  // Use OpenClaw's message tool to send to peer's Telegram
  sendTelegramMessage(peerId, base64Message);
});

// When receiving a Telegram message from peer:
node.receive(peerId, base64EncodedMessage);

Connection Consent

Unknown inbound peers require explicit consent:

node.on('connectionRequest', (req) => {
  console.log(`Peer: ${req.id}, Fingerprint: ${req.fingerprint}`);
  node.acceptPeer(req.id);  // or node.rejectPeer(req.id)
});

Human Verification

const code = node.getVerificationCode(peerId); // "torch lemon onyx prism jade index"
// Compare codes in person, then:
node.verifyPeer(peerId);

Persistent Identity

const node = await Clawdio.create({ identityPath: '.clawdio-identity.json' });

API Reference

MethodDescription
Clawdio.create(opts)Create and initialize a node
node.onSend(handler)Register send handler (transport layer)
node.receive(from, b64)Feed incoming message from transport
node.connect(peerId)Initiate Noise XX handshake
node.send(peerId, msg)Send encrypted message
node.onMessage(handler)Listen for decrypted messages
node.acceptPeer(id)Accept pending connection
node.rejectPeer(id)Reject pending connection
node.getVerificationCode(id)Get 6-word verification code
node.verifyPeer(id)Mark peer as human-verified
node.getPeerTrust(id)Get trust level
node.getFingerprint(id)Emoji fingerprint
node.getPeerStatus(id)alive/stale/down
node.stop()Shutdown

Security Properties

  • Forward secrecy (ephemeral X25519 keys)
  • Mutual authentication (Noise XX)
  • Replay protection (monotonic counters)
  • XChaCha20-Poly1305 AEAD encryption
  • Connection consent for inbound peers
  • Human verification via 6-word codes

Dependencies

Single production dependency: libsodium-wrappers.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

83.06%
按下载量换算12,180

安全审计

VirusTotal

可疑

ClawScan

可疑

Static analysis

未展示

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills