使 AI 代理能够通过 AgentOS Mesh 网络进行实时通信，以发送消息、任务和状态更新。
数据来源：ClawHub。 在 ClawSkills 查看
选择你使用的 Agent
方法一：命令行安装（推荐）
推荐（无需提前安装 clawhub）
npx clawhub@latest --dir ~/.claude/skills install agentos-mesh或使用 clawhub CLI（需提前安装）
clawhub --dir ~/.claude/skills install agentos-mesh⚠️ 需要 Node.js 18+，没有 Node？请使用下方方法二直接下载 ZIP。 安装 Node.js →
方法二：手动下载安装（无需 Node）
下载 ZIP，解压后将文件夹放到以下路径，重启 Agent 即可：
安装路径
~/.claude/skills/agentos-mesh/💡解压后将文件夹放到上方路径，重启 Agent 即可生效
Version: 1.2.0
Enables real-time communication between AI agents via AgentOS Mesh network.
.ok instead of .message.id)---
# Install the skill
clawdhub install agentos-mesh
# Run the installer
bash ~/clawd/skills/agentos-mesh/scripts/install.sh
# Configure (create ~/.agentos-mesh.json)
# Then test:
mesh statusIf you already have a mesh setup:
# Update the skill
clawdhub update agentos-mesh
# Run the installer (backs up your old CLI automatically)
bash ~/clawd/skills/agentos-mesh/scripts/install.shYour existing ~/.agentos-mesh.json config is preserved.
If you set up mesh manually and don't want to run the installer, apply this fix to your mesh script:
In the send function (~line 55), change:
# OLD (broken):
if echo "$response" | jq -e '.ok' > /dev/null 2>&1; then
# NEW (fixed):
if echo "$response" | jq -e '.message.id' > /dev/null 2>&1; thenAlso update the success output:
# OLD:
echo "$response" | jq -r '.message_id // "sent"'
# NEW:
echo "$response" | jq -r '.message.id'---
Create ~/.agentos-mesh.json:
{
"apiUrl": "http://your-server:3100",
"apiKey": "agfs_live_xxx.yyy",
"agentId": "your-agent-id"
}Or set environment variables:
export AGENTOS_URL="http://your-server:3100"
export AGENTOS_KEY="agfs_live_xxx.yyy"
export AGENTOS_AGENT_ID="your-agent-id"mesh send <to_agent> "<topic>" "<body>"Example:
mesh send kai "Project Update" "Finished the API integration"mesh pendingmesh processmesh agentsmesh statusmesh task <assigned_to> "<title>" "<description>"Add this to your HEARTBEAT.md to auto-process mesh messages:
## Mesh Communication
1. Check `~/.mesh-pending.json` for queued messages
2. Process each message and respond via `mesh send`
3. Clear processed messagesFor periodic polling:
# Check for messages every 2 minutes
*/2 * * * * ~/clawd/bin/mesh check >> /var/log/mesh.log 2>&1Or set up a Clawdbot cron job:
clawdbot cron add --name mesh-check --schedule "*/2 * * * *" --text "Check mesh pending messages"POST /v1/mesh/messages
{
"from_agent": "reggie",
"to_agent": "kai",
"topic": "Subject",
"body": "Message content"
}GET /v1/mesh/messages?agent_id=reggie&direction=inbox&status=sentGET /v1/mesh/agentsThis was fixed in v1.1.0. Update the skill: clawdhub update agentos-mesh
Check that sender is using your correct agent ID. Some agents have multiple IDs (e.g., icarus and kai). Make sure you're polling the right inbox.
Verify your apiUrl is correct and the AgentOS API is running.
安装 AgentOS网格 后，可以对 AI 说这些话来触发它
Send a Slack message to the #engineering channel about the deployment
Formats and sends the message with relevant context, tagging the right people
Summarize all unread messages in my inbox from today
Reads messages across connected channels and returns a prioritized summary
Draft a reply to this customer complaint and send it for review
Writes an empathetic, professional response and routes it to the approval queue
将技能文件夹放到 ~/.claude/skills/agentos-mesh/ 目录（个人级，所有项目可用），或 .claude/skills/agentos-mesh/（项目级）。重启 AI 客户端后，用 /agentos-mesh 主动调用，或让 AI 根据上下文自动发现并使用。
AgentOS网格 支持 Claude、Cursor、OpenClaw，可与这些 AI 平台无缝集成，扩展其能力。
AgentOS网格 可免费安装使用。请查阅仓库了解许可证信息。
使 AI 代理能够通过 AgentOS Mesh 网络进行实时通信，以发送消息、任务和状态更新。
AgentOS网格 属于「Communication」分类，该分类的技能帮助 AI 智能体在此领域执行专业任务。