One founder. Seven sites. AI agents doing the work.
The Unnamed Roads is a self-hosted AI agent studio — 7 live sites publishing daily content, tracking analytics, and running workflows autonomously. One person. No employees. ~€35/month in infra.
Built on n8n, OpenClaw, LiteLLM, Coolify, and Hetzner.
Sites running
07
all publishing daily
Monthly infra cost
€35
fully self-hosted
Content published by AI
100%
zero manual writing
Traditional team needed
8–12
editors, devs, ops
Live sites
Each site publishes AI-generated content daily, tracks analytics via Umami, and notifies via Telegram. No manual editing. No CMS logins.
Sports AI
Modern hockey analytics consulting
Modern data stack + flexible engagement model delivering on-demand hockey analytics squads for teams that want measurable tactical advantages without full-time hires.
Svarstid
2 arbetsdagar
Enterprise AI
Distributed agent infrastructure
Infrastructure layer that enables AI agents to operate inside enterprise systems—securely, locally, and at scale. On-prem, edge, and hybrid deployment.
Deployment model
Edge + on-prem
Marketing
Hyperlocal GTM loops
Physical mail plus referral mechanics that trigger when neighbors buy, spinning up viral loops for brick-and-mortar brands.
Betyg
4.8 / 5
Logistics AI
Print routing from webhook to doorstep
Two-sided print routing platform. Retailers send orders via webhook – providers accept, produce, and ship with full tracking synced back automatically.
Provider portal
app.theprintroute.com
Data Infrastructure
Validerad traningsdata med revisionskedja
Traningsdata du kan lita pa – med bevis. Multi-annotator-validering, konfidenspoang och full EU AI Act-dokumentation levererad inom 72 timmar.
Annotator-overenskommelse
92%+
Sports AI
Proactive hockey analytics research
Making Hockey Data Human. Proactive pattern detection in NHL data delivering insights to scouts, coaches, and analysts before anyone else sees them.
Premium
499 SEK/mån
Retail Tech
Snygga prisskyltar. Klart pa 5 minuter.
Ingen printer. Ingen stress. Valj design, ange pris – fa professionella prisskyltar levererade direkt till butiken pa fem minuter.
Tid fran order
5 minuter
Venture studio
AI-native solo venture studio
One founder. Seven projects. AI agents doing the work. Self-hosted on Coolify and Hetzner for ~35 EUR/month – replacing what would normally take 8-12 people.
Infrastruktur
~35 EUR/mån
Portfolio
Data engineering & full-stack development
Data Engineer in Stockholm. Modern data stack, Python automation, and scalable web solutions. n8n, Streamlit, Databricks, data chat agents.
Stack
n8n · Databricks · Python
What I'm exploring
Topics I'm actively writing about, building systems around, or experimenting with. Updated as the stack evolves.
Infra cost compression
Running 7 live sites with daily AI content for ~€35/month. Coolify + Hetzner replaces €200+/month in managed services.
GEO and Answer Engines
Structuring content so it gets cited in ChatGPT, Perplexity, and Google AI Overviews — not just ranked on page 1.
Agentic publishing loops
Research → draft → quality score → publish → IndexNow → newsletter — fully automated, no human in the loop except Telegram approval.
Daily pipeline
Every content site runs the same loop — scheduled by n8n, generated by an LLM, committed to GitHub by OpenClaw, deployed by Netlify or Vercel.
n8n reads yesterday's performance data from Minio. Groq scores topic candidates against real traffic signals.
Minio · Groq · n8n cron
LiteLLM routes the prompt to Groq or Gemini. Article is scored for quality before continuing.
LiteLLM · Groq · Gemini
THA and THB auto-publish. EIK articles send a Telegram message with inline Approve/Reject buttons.
Telegram bot · n8n webhook
OpenClaw writes the markdown file and commits to the site repo. Netlify or Vercel picks up the push and deploys in ~60 seconds.
OpenClaw · GitHub · Netlify / Vercel
IndexNow pings Google and Bing with the new URL. Newsletter dispatch fires to Listmonk subscribers.
IndexNow · Listmonk · Resend
How it runs
Three layers handle everything: research, content generation, and publishing. Each runs on a schedule with Telegram notifications and zero manual steps.
One human sets strategy, approves sensitive changes, and checks Telegram. The rest is autonomous.
Research Layer
Keyword research, NHL API data pulls, and topic scoring run every morning before content generation.
AI
Scheduling, API calls, conditional logic
Self-hosted on Coolify. Runs ~23 active workflows across all 7 sites — cron-triggered, chained, with error monitoring.
AI
Fast inference, cost-effective at scale
Scores keyword candidates by relevance and competition, then generates full article drafts. Llama 3 models.
AI
Real-time standings, game scores, player stats
Powers The Hockey Analytics and The Hockey Brain with current season data — no manual data entry.
Content Layer
Generation, formatting, and quality scoring before anything is published.
AI
Multi-model, cost tracking, fallback routing
Self-hosted LLM gateway that routes requests to Groq, Gemini, or other providers. Tracks spend per site.
AI
High quality, large context window
Used for The Hockey Brain's daily NHL articles — longer format with richer context than Groq.
AI
S3-compatible, self-hosted
Stores keyword JSONs, approved article drafts, and performance insight files between pipeline stages.
Publish Layer
From draft to live in seconds — GitHub commits, IndexNow pings, newsletter dispatch, and Telegram confirmations.
AI
Markdown write + GitHub commit in one call
Webhook server on the host machine. Receives article payloads, writes markdown files, commits to GitHub repos, and triggers Netlify/Vercel deploys.
AI
Version history, Netlify/Vercel hooks
All site content lives in GitHub repos. Every commit triggers an automatic build and deploy.
AI
Inline buttons, zero app switching
Every workflow sends a Telegram message on completion. EIK articles require inline button approval before publishing.
Stack
Every OS phase has named tools so partners can see exactly how we sense, compose, deploy, and audit autonomous ventures.
Everything runs on one Hetzner VPS managed by Coolify. No managed databases, no SaaS overhead.
Coolify
Self-hosted PaaS that manages all containers, env vars, and deploys on the Hetzner VPS.
Hetzner
CX32 VPS in Frankfurt. ~€13/month. Runs everything — n8n, LiteLLM, Minio, Umami, OpenClaw, Qdrant.
Minio
S3-compatible object storage for draft files, keyword JSONs, and performance insight data.
n8n runs 23 active workflows. Every schedule, API call, conditional branch, and Telegram notification.
n8n
Self-hosted workflow engine. Handles keyword research, content generation, publishing, analytics, and error monitoring.
Telegram
All notifications and approvals arrive here. Inline buttons for approving EIK articles without opening a browser.
OpenClaw
Webhook publish server. Receives article payloads and commits markdown to GitHub — one HTTP call per publish.
LiteLLM proxies all model calls. Groq handles speed, Gemini handles quality, costs tracked per site.
LiteLLM
Self-hosted LLM gateway. Routes to Groq, Gemini, or other providers. Tracks spend. Single endpoint for all models.
Groq
Fast inference for keyword scoring and article generation. Llama 3 models. Free tier covers most daily usage.
Qdrant
Self-hosted vector DB for semantic search and RAG experiments on article archives.
Umami tracks traffic across all 7 sites. Daily Telegram reports with week-over-week comparisons.
Umami
Privacy-first analytics. Self-hosted. Daily automated reports sent to Telegram with pageviews, referrers, and top articles.
IndexNow
Instant URL submission to Google and Bing after every article publish. No waiting for crawlers.
Listmonk
Self-hosted newsletter platform. Subscriber list synced with Resend for transactional delivery.
Numbers
Full monthly breakdown for running 7 sites with daily AI content publishing.
“One VPS running Coolify, n8n, OpenClaw, LiteLLM, Minio, Umami, and Qdrant. Everything self-hosted.”
“Groq free tier covers most article generation. Gemini API for THB. LiteLLM tracks spend per site.”
“theunnamedroads.com, thehockeyanalytics.com, thehockeybrain.com — plus Netlify/Vercel free tiers.”
What this is
A solo founder running 7 sites on self-hosted AI infrastructure.
The Unnamed Roads is a personal studio — one person, seven live sites, and an AI agent pipeline that handles everything from keyword research to publishing.
The entire stack is self-hosted on a single Hetzner VPS managed by Coolify. n8n orchestrates ~23 workflows. LiteLLM routes LLM calls to Groq and Gemini. OpenClaw commits markdown to GitHub. Netlify and Vercel deploy. Total cost: ~€35/month.
This site is where I write about what I'm building, what breaks, and what it actually costs to run AI infrastructure at this scale. No fluff. Just systems.
Fully self-hosted
Coolify + Hetzner replaces €200+/month in managed SaaS. One VPS runs everything.
Autonomous publishing
Content research, generation, and publishing run on cron schedules without manual steps.
Telegram-first ops
Every workflow completion sends a Telegram message. Approvals use inline buttons. No dashboards needed.
7
Live sites
€35
Monthly infra
23
n8n workflows
Say hello
If you're building something similar — self-hosted AI infra, multi-site content ops, n8n workflows — I'm happy to talk. No sales pitch, just notes from the field.
Also on Bluesky: @theunnamedroads.bsky.social