Skip to content
REPOCITYAI FOR EVERYONE
AI FOR EVERYONE

AI agents that get work done

RepoCity builds AI automation for companies and for everyday life. Every agent has one task, every result is checked.

EnglishDeutschGet in touchView projects

AI automation for companies and for everyday life

The same agents that check invoices in a company also take work off your hands in everyday life.

A city where agents work

132 agents on 21 production lines in three departments. The structure follows that of a company: every line has its own quality assurance and its own trainer.

An operating system for agents

An agentic OS distributes tasks, gives agents access to knowledge and tools, limits costs and reports what is done.

What RepoCity builds

Six fields of work, one workspace. The flight leads inside.

PROJECT 1 OF 6

Intelligent Document Processing

An invoice is only booked when every decision is certain and every check passes. Built with n8n and Jev.

View project page
PROJECT 2 OF 6

Agentic Marketing

Market research with agents whose figures are verified: every figure is looked up in the cited source, and a human decides what stays.

PROJECT 3 OF 6

AI Governance Compliance Helper

Six questions lead to the classification of an AI system under the EU AI Act, with a reference to the relevant provision. Not legal advice.

Open the Compliance Helper
PROJECT 4 OF 6

Conversational AI

Voice and chat assistants that answer questions, take requests in plain language and pass them to the right place.

PROJECT 5 OF 6

Highend AI Content Production

featuring Ibtihal

Images, motion graphics, short clips, high-end videos, music, presentations and learning programmes from RepoCity's creative workshop.

PROJECT 6 OF 6

Website Setup and Design

Websites from concept to launch: research, wording, design and build. This site is the example: a flight in real-time 3D, bilingual, built with Three.js.

Daniel Hütte

Get in touch

RepoCity is my work. I am Daniel Hütte, AI engineer from Münster. My focus is AI agents and automated workflows. I am looking for a position as an AI (Agent) Engineer.

LinkedInGitHubWrite an email

A city where agents work

RepoCity is a multi-agent system built like a company. Every kind of result has its own production line. Several AI agents work on each line, and each of them has exactly one task.

A job moves from station to station. At the end of every line, quality assurance checks the result before it leaves the line. Anything uncertain goes to a human, with the reason stated.

RepoCity comprises 132 agents on 21 production lines in three departments. The structure follows that of a company: every line has its own quality assurance and its own trainer, and all of them share the same infrastructure for task distribution, knowledge base, cost control and outgoing goods.

What RepoCity builds

Intelligent Document Processing

AI document processing that asks a human when in doubt

An invoice inbox receives invoices, credit notes, reminders, delivery notes and the occasional fraud attempt. This pipeline only books an invoice when every decision is certain and every check passes. Everything else goes to a human, with the reason stated.

In a test with 250 documents, no faulty invoice was booked. Of eight systems compared, this setup was the cheapest: 0.39 US dollars per 1,000 documents, measured on 8 October 2026. Jev makes the fixed decisions, Claude Haiku 5.5 reads the amounts and writes the summary, n8n runs the steps.

  • n8n
  • Jev
  • Claude Haiku 5.5
  • Cloudflare Workers AI
  • Supabase
View project page

Agentic Marketing

Market research with agents whose figures are verified

A team of agents researching a market delivers a lot of text and a lot of figures. An unverified figure looks exactly like a verified one. This project puts three steps between research and use: every figure is looked up in the cited source, a human decides what stays, and only what is backed up is carried over.

The included example deliberately contains one invented figure. The check finds it.

  • Claude Code
  • Agent teams
  • Eight analysis skills
  • Python

AI Governance Compliance Helper

EU AI Act: is your AI a high-risk system?

The AI Governance Compliance Helper classifies an AI system under the EU AI Act. Six questions lead to the result, with a reference to the provision it is based on. The tool runs in the browser, without sign-in, and sends no data to a server. It is not a substitute for legal advice.

Open the Compliance Helper

Conversational AI

AI assistants you can talk to

Voice and chat assistants that answer questions, take requests in plain language and pass them to the right place.

Highend AI Content Production

Images, videos and music from the creative workshop

featuring Ibtihal

RepoCity's creative workshop has ten production lines: images, motion graphics, short clips, high-end videos, music, presentations, learning programmes, PDFs, postcards and screensavers.

Website Setup and Design

Websites you experience

Websites from concept to launch: research, wording, design and build. This site is the example: a flight in real-time 3D from space into the agents' workspace, bilingual, with all texts also available as an ordinary page for search engines.

  • Three.js
  • WebGL
  • Claude
  • Cloudflare

What is an agentic OS?

An agentic OS is the operating system for a team of AI agents. It distributes tasks, gives the agents access to knowledge and tools, limits costs and reports what is done.

In RepoCity, shared services do this: a task dispatcher, a knowledge base, a cost brake, a vault for credentials and an outgoing-goods desk for finished results. Every production line uses the same services.

AI for everyday life

AI for everyone means: automation is not a topic for large corporations only. The same agents that check invoices in a company also take work off your hands in everyday life. RepoCity has a department of its own for that.

Who builds RepoCity?

RepoCity is the work of Daniel Hütte, AI engineer from Münster. His focus is AI agents and automated workflows: he builds them, measures their results, looks for the errors and builds them better.

Daniel Hütte is looking for a position as an AI (Agent) Engineer.

Frequently asked questions about AI agents

What is an AI agent?
An AI agent is a program that completes a task on its own in several steps. It reads input, decides on the next step, uses tools and delivers a result.
AI agent or classic automation: which fits when?
Classic automation fits when every case runs the same way. An AI agent fits when inputs look different each time, for example documents, emails or freely worded requests. In RepoCity both work together: the agent reads and decides, ordinary program code checks the maths.
Can you have AI agents developed?
Yes. An agent is built for a specific task, with the data and tools it needs for it. The projects on this page show what that looks like.
How do you stop an agent from waving errors through?
With checks that do not come from the same model. Amounts are recalculated, figures are looked up in the source, and whatever remains uncertain is decided by a human.
What is a multi-agent system?
A multi-agent system splits a large task among several specialised agents. Each one handles a part, and another agent checks the result.
Where is RepoCity based?
In Münster in North Rhine-Westphalia, Germany. The work runs online across Germany.

Get in touch

Tell us what you are working on or what interests you about RepoCity.

Write an email

kontakt@speedofthespirit.dev