observability📊

AI Observability Stack

Monitor every agent, workflow, and model call

Complete observability for AI systems: Prometheus + Grafana + Loki + Tempo + Pyroscope. Pre-built dashboards for n8n, Hermes, OpenCode, Ollama, Open WebUI. Alerts for: model latency, token costs, error rates, queue depths, GPU memory. One deploy, zero config.

Deploy Time3-5 minutes (scripted)

RequirementsVPS with 4GB+ RAM, 30GB+ disk (more for retention)

Compliance✓ Paddle Compliant

Choose Your Tier Ask a Question

What's Included

✓Prometheus (metrics) + Alertmanager

✓Grafana (dashboards + alerting)

✓Loki (logs) + Promtail

✓Tempo (traces) + OpenTelemetry collector

✓Pyroscope (profiling)

✓Pre-built dashboards: n8n, Hermes, OpenCode, Ollama, RAG

✓Cost tracking (token usage per model/agent)

✓Alert rules: latency, errors, costs, queue, GPU

Choose Your Tier

One-time payment. Lifetime access. Optional maintenance.

Starter

79€one-time

Deployment: Self-serve

Ideal for getting started

Deploy script (full stack)
5 core dashboards
Standard alert rules
30-day retention

Choose Starter

Pro

199€one-time

Deployment: Assisted

Support: 30 days included

Ideal for getting started

Everything in Starter
Custom dashboards (3)
Advanced alerts (cost anomalies, drift)
Long-term retention (1yr)
LogQL/MetricsQL training

Get Started

Enterprise

499€one-time

Deployment: Managed

Support: 90 days included

Ideal for getting started

Everything in Pro
HA setup (Thanos/Cortex)
Custom metrics exporters
SLA + on-call rotation help
Team training (2h)

Choose Enterprise

All tiers include: full source code, deploy scripts, documentation, GitHub repo access. No recurring fees unless you choose Sérénité maintenance (€149/mo).

Requirements & Deployment

Server Requirements

VPS with 4GB+ RAM, 30GB+ disk (more for retention)

Recommended: Hetzner CX42 (8GB RAM, 160GB SSD, ~€32/mo) or Contabo VPS L (16GB RAM, 800GB SSD, ~€39/mo)

Deployment Process

Purchase — Checkout via Paddle, instant access to private repo
Provision — Create VPS (we recommend Contabo/Hetzner) or use existing
Deploy — Run bash deploy.sh on your server (5-15 min)
Configure — Add API keys via Web UI or .env file
Run — Services start on boot. Access dashboards via HTTPS.

Frequently Asked Questions

Do these run on my server or yours?

100% on YOUR server (VPS, bare metal, cloud VM). You get root access, the deploy scripts, and full control. We never see your data, API keys, or logs.

What if I don't have a server?

We recommend Hetzner CX42 (8GB RAM, 160GB SSD, ~€32/mo) or similar. You provision it, give us root (for managed tiers) or run the script yourself (starter). You pay the provider directly.

Are there recurring fees to you?

No. One-time payment for the product. Optional: Sérénité maintenance at €149/mo (updates, health checks, backup audits, 1h support/mo). Cancel anytime.

How does deployment work?

Starter: you run `bash deploy.sh` on your server (5-15 min). Pro: we hop on a call, you share screen/SSH, we run it together. Enterprise: you give us temporary SSH, we deploy, harden, test, hand over with runbook.

What models do the agents use?

Default: NVIDIA NIM (free tier, 40 req/min). Optional: Ollama (local, free), OpenAI/Anthropic API (your keys, your bill), or any OpenAI-compatible endpoint. You choose at deploy time.

Is this Paddle-compliant?

Yes. Every product is a SOFTWARE PRODUCT (deployable stack, templates, scripts, config). You pay for infrastructure automation, not AI-generated output. No human services, no outbound marketing, no prohibited categories.

Can I customize after purchase?

Absolutely. You get the source: Docker Compose files, scripts, configs, workflow JSON, agent skills. Modify anything. Starter/Pro include docs for self-modification. Enterprise includes custom dev hours.

What happens after support period ends?

You keep everything forever. No license expiration. Renew Sérénité (€149/mo) for continued updates/health checks, or manage yourself. We provide upgrade guides for major versions.