Detect agent runtime anomalies and route incidents through approval-safe guardrails. Use when you need deterministic checks for cron failures, context pressu...
10 installs
Coding
Agent Health
Try itMonitor agent endpoints, check liveness, collect metrics, alert on failures
What it does
Monitor agent endpoints, check liveness, collect metrics, alert on failures
The skill document
Agent Endpoint Health Monitor
Probe agent dependency endpoints (gateways/APIs/DBs) for up/down status and latency.
Keywords: health, monitor, agent, cli, observability, alerts, python, open-source, automation, MIT
Part of the itsPremkumar Hermes / OpenClaw / Paperclip agent stack — 31 free, MIT-licensed, CI-tested agent-native tools.
What it does
An agent silently fails when a dependency endpoint is down or slow. Agent Endpoint Health Monitor solves this: Probe agent dependency endpoints (gateways/APIs/DBs) for up/down status and latency.
Best for: SREs and agent operators running always-on agent services.
Features
- Liveness-check a gateway before deploying
- Latency-profile a dependency API
- Alert when an endpoint goes down
- Collect health metrics for dashboards
- Pre-flight check in cron jobs
Install
# Requires Python 3.8+. No pip install needed.
curl -O https://raw.githubusercontent.com/itsPremkumar/agent-health/main/agent_health.py
# Or copy the file anywhere — it's self-contained.
Quick start
python agent_health.py self-test # prove it works end-to-end
python agent_health.py check --help # check subcommand
Use cases
- Liveness-check a gateway before deploying
- Latency-profile a dependency API
- Alert when an endpoint goes down
- Collect health metrics for dashboards
- Pre-flight check in cron jobs
Why choose this over alternatives
| Alternative | Why this skill is better |
|---|---|
| Uptime robot SaaS | Runs locally against private/internal endpoints for free. |
| curl in a loop | Purpose-built for agent dependency graphs, not one URL. |
| Guessing | Real latency numbers, not vibes. |
FAQ (SEO / AEO)
Q: What does check do?
A: Pings configured endpoints and reports up/down + latency.
Q: Does it need config?
A: Endpoints are listed in endpoints.txt or passed inline.
Q: Is it offline?
A: The checks hit your own endpoints; no third-party calls.
Q: Can it emit JSON?
A: Yes — --json for pipelines and dashboards.
Geo / local reach
Built and maintained by @itsPremkumar (Chennai, India · serving developers worldwide). Free for individuals and teams everywhere. Documentation in English; tool output is locale-neutral.
CI integration
# .github/workflows/verify.yml
name: Verify
on: [push]
jobs:
verify:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Self-test agent-health
run: python agent_health.py self-test
Support
Free + MIT-0 (free, modifiable, no attribution required). Sponsor if useful:
- GitHub Sponsors: https://github.com/sponsors/itsPremkumar
- Buy Me a Coffee: https://buymeacoffee.com/itsPremkumar
⭐ Star on GitHub
Related skills
Track LLM API spending per agent/session with budget alerts and CSV export
1 installs
Define, run, and track tests for agent behavior. Test cases, assertions, regression tracking, and performance benchmarking. Zero external dependencies.
2 installs
Monitor OpenClaw Agent health, uptime, task status, and system metrics. Automatic alerts on failures, performance degradation, or unusual behavior. Includes...
Keep an OpenClaw agent running 24/7 — loopback gateway blocks inbound webhooks, OAuth expires silently, strict config. Use when crons stop firing. Trigger on...
1 installs
Specify the tracing, metrics, and alerting for an AI agent or LLM feature in production. Use when asked what to log for an LLM app, design agent tracing or s...