ai-agent

Monitor LLM with relay-pulse

Name: Monitor LLM with relay-pulse
Author: prehisle

Founders get real-time service status tracking.

intermediate⏱ 1-2 hours💵 Free (self-hosted)

1,098 stars93 forksGoGuide quality 8/10Updated 9/6/2026100% free · open source

What it is

Use relay-pulse to monitor the availability of your large language model services and get real-time updates on their status with a visual dashboard.

Real use case example

"A founder, John, uses relay-pulse to monitor the availability of her company's internal chatbot. She sets up the service to send her a daily report on the chatbot's uptime and alerts her immediately when the service goes down. With relay-pulse, John can quickly identify and address issues before they impact her customers."

Best insideClaude DesktopClaude CodeCursorGemini Code Assist

When to use it

•When you need to track the status of multiple LLM services in real-time
•When you require a visual representation of service availability for easier monitoring
•When you want to ensure high uptime and reliability for your LLM-backed applications

Ready-to-paste prompt

Run 'curl http://localhost:8080/api/services' to retrieve the status of all monitored services

Heads up: Make sure you have Go 1.17 or later installed, as the project uses Go modules and may not be compatible with earlier versions

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/relay-pulse && curl -fsSL https://workflowstacks.com/api/skills/relay-pulse/claude-skill -o ~/.claude/skills/relay-pulse/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Monitor LLM with relay-pulse works

Codeflow

Free to inspect

Monitor LLM with relay-pulse is a very large Go project (~91k lines across 392 code files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, MIT license, has a test suite.

Size

Very large codebase

~91k lines · 392 code files · days to read — use, don't read

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Go · Docker

Needs API keys (.env)

Go 66%TypeScript 32%Shell 1%CSS 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
AGENTS.md
The instructions the AI actually follows
3
cmd/server/main.go
Where the program starts running
4
go.mod
Dependencies and the commands it exposes
5
.env.example
The API keys and settings you must provide

What's in each folder

internal/Core code — the actual logic189 files

frontend/Frontend / UI191 files

cmd/Command-line entry points4 files

templates/Templates42 files

docs/Documentation10 files

notifier/Folder30 files

archive/Archived / older material19 files

scripts/Helper scripts11 files

READMEHas testsDocumentedCI checksDocker readyMIT licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/relay-pulse && curl -fsSL https://workflowstacks.com/api/skills/relay-pulse/claude-skill -o ~/.claude/skills/relay-pulse/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

prehisle

Language