agent-relay
Connect agents across OpenClaw instances via relay. Messages delivered instantly via webhook when offline, queued for 7 days. No persistent connection needed.
Best use case
agent-relay is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Connect agents across OpenClaw instances via relay. Messages delivered instantly via webhook when offline, queued for 7 days. No persistent connection needed.
Teams using agent-relay should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/cross-instance-relay/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How agent-relay Compares
| Feature / Agent | agent-relay | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Connect agents across OpenClaw instances via relay. Messages delivered instantly via webhook when offline, queued for 7 days. No persistent connection needed.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
SKILL.md Source
# Agent Relay
Cross-instance agent messaging. Send a message to any agent on any OpenClaw instance — delivered instantly via webhook push, or queued if unreachable.
## Setup
Set these environment variables:
```
RELAY_URL=https://your-relay.up.railway.app
RELAY_TEAM_TOKEN=your-shared-team-token
RELAY_TEAM_ID=your-team-name
RELAY_INSTANCE_ID=unique-instance-name
```
## Register your webhook (do this once)
Register your OpenClaw webhook so the relay can push messages to you instantly:
```bash
curl -X PUT "$RELAY_URL/webhooks" \
-H "Authorization: Bearer $RELAY_TEAM_TOKEN" \
-H "Content-Type: application/json" \
-d "{\"teamId\": \"$RELAY_TEAM_ID\", \"instanceId\": \"$RELAY_INSTANCE_ID\", \"url\": \"https://your-openclaw-host/hooks/agent\", \"token\": \"your-openclaw-hooks-token\"}"
```
Optional: add `"agentId": "main"` to route to a specific agent.
Once registered, any message sent to your instance will automatically trigger your agent via the webhook. No polling or WebSocket needed.
## Send a message
```bash
curl -X POST "$RELAY_URL/publish" \
-H "Authorization: Bearer $RELAY_TEAM_TOKEN" \
-H "Content-Type: application/json" \
-d "{\"teamId\": \"$RELAY_TEAM_ID\", \"from\": \"$RELAY_INSTANCE_ID\", \"to\": \"target-instance\", \"message\": \"hello\"}"
```
Response includes delivery status:
- `{"delivered":1,"queued":false,"webhook":null}` — delivered via WebSocket
- `{"delivered":0,"queued":true,"webhook":{"fired":true,"status":200}}` — offline, queued + webhook fired
## Broadcast to all
```bash
curl -X POST "$RELAY_URL/publish" \
-H "Authorization: Bearer $RELAY_TEAM_TOKEN" \
-H "Content-Type: application/json" \
-d "{\"teamId\": \"$RELAY_TEAM_ID\", \"from\": \"$RELAY_INSTANCE_ID\", \"message\": \"hello everyone\"}"
```
## Poll inbox (fallback)
If webhooks aren't set up, poll for queued messages:
```bash
curl "$RELAY_URL/messages?teamId=$RELAY_TEAM_ID&instanceId=$RELAY_INSTANCE_ID" \
-H "Authorization: Bearer $RELAY_TEAM_TOKEN"
```
Add `&peek=true` to read without consuming.
## Check inbox count
```bash
curl "$RELAY_URL/messages/count?teamId=$RELAY_TEAM_ID&instanceId=$RELAY_INSTANCE_ID" \
-H "Authorization: Bearer $RELAY_TEAM_TOKEN"
```
## List connected instances
```bash
curl "$RELAY_URL/instances?teamId=$RELAY_TEAM_ID" \
-H "Authorization: Bearer $RELAY_TEAM_TOKEN"
```
## List registered webhooks
```bash
curl "$RELAY_URL/webhooks?teamId=$RELAY_TEAM_ID" \
-H "Authorization: Bearer $RELAY_TEAM_TOKEN"
```
## How it works
1. You send a message to another instance via `POST /publish`
2. If they're connected via WebSocket → instant delivery
3. If they're offline → message queued (7-day TTL) + webhook fired on their OpenClaw instance
4. Their agent wakes up, processes the message, and can reply back through the relay
No persistent connections required. Just register your webhook once and forget about it.
## WebSocket (optional)
For real-time bidirectional streaming:
```
wscat -c "wss://your-relay/ws?teamId=my-team&instanceId=my-instance&token=my-token"
```
Queued messages auto-delivered on connect.
## Self-hosting
Open source: https://github.com/aaravgarg/agent-relay
Deploy on Railway, Fly, or any Node 18+ host. Requires `TEAM_TOKEN` and `REDIS_URL`.Related Skills
captcha-relay
Human-in-the-loop CAPTCHA solving with two modes: screenshot (default, zero infrastructure) and token relay (requires network access). Screenshot mode captures the page with a grid overlay, sends it to the human, and injects clicks based on their reply. Token relay mode detects CAPTCHA type + sitekey, serves the real widget on a relay page for native solving, and injects the token via CDP.
claude-relay
Relay operator for Claude Code via tmux across multiple projects. Use when the user wants to start/continue a Claude Code terminal session, send prompts, read output, or manage background Claude sessions by project name/path.
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.