Back to Blog
ProductJanuary 16, 2026~5 min read

Multi-Repo Docs: Per Repo or System Level? Lessons from Testing QEEK AI on Sock Shop

An alpha experiment on where docs belong (and why system-level guides win when the value is in connections).

A few days ago, I posted this on X:

“I keep running into the same question in multi-repo systems: should architecture docs live per repo, or at the system level?”

Feels like both come with different tradeoffs…

This sparked a great conversation I had with Grok (yes, xAI’s) — and Grok challenged me to test it hands-on with QEEK AI. I threw the classic Sock Shop microservices demo at it (10+ repos, polyglot languages, mixed databases, and orchestration across service boundaries).

Alpha experiment

This isn’t a benchmark. It’s a quick “does this doc style hold up under multi-repo complexity?” test, using generated docs as evidence.

01

The hero test: Sock Shop multi-repo deep dive

Sock Shop is a perfect stress test: distributed e-commerce services (carts, users, catalogue, orders, payment, shipping, front-end) split into separate repos. The real value is in the connections — flows, dependencies, and trade-offs across boundaries.

Architecture Overview
System-level fit: 9/10. Aggregates across services to show topology, persistence choices, orchestration, and risk points.
View example
Application Flows
System-level fit: 9.5/10. Checkout and cart flows only make sense end-to-end — no single repo “owns” the truth.
View example
API Documentation
System-level fit: 6/10. Useful for quick reference, but often similar to Swagger dumps — we prefer higher-level guides.
View example

Key takeaway

System-level docs excel when the value is in connections. Per-repo docs for Sock Shop services felt a bit redundant — individual repos are small and only make sense in the context of the whole. We generated repo-level docs anyway so you can judge it for yourself.

02

Single-repo contrast: FastAPI orientation

We also tested on a popular single-repo project — the FastAPI framework + its official full-stack template (the reference app that shows how to build real applications with it).

In under a minute, QEEK generated:

  • Architecture Overview (system-level map)
  • Application Flows (end-to-end user journeys)
  • Directory Structure (clean map + purposes)
  • Tech Stack (languages, deps, testing, patterns)
  • Project Overview (purpose, philosophy, flow)

This combo shows how QEEK connects framework-level patterns to concrete implementation — perfect for quick orientation and feeding to Cursor/Windsurf agents.

03

Per-repo vs system-level: what actually worked

Per-repo wins when
  • Individual repos are big/complex and you onboard one piece at a time.
  • You need runbooks, local dev notes, and “where to edit now.”
System-level wins when
  • The value is in flows and dependencies across boundaries (orchestration, failure modes).
  • Services are small and uniform — per-repo architecture docs would be redundant.

Most teams end up hybrid: system docs for the “why it all fits,” repo docs for the “how to ship this part.” In our tests, guide-style (flows + maps) built understanding faster than encyclopedia-style lists — for humans and for agents.

Related: Guide vs Encyclopedia.

What’s next for QEEK

These tests confirmed our direction: layered, intent-driven, cost-aware code intelligence — still alpha, expect weirdness, but already useful in under a minute, fully client-side.

We’d love your take: does this match your multi-repo pains? What trade-offs did we miss? Try it on your repo and roast the output.

DM @QEEK_01 or reply on X — especially if you're obsessed with long-context agents or hierarchical memory. Looking for 1–2 collaborators to make this real.

Thanks for reading. Let's keep questioning.

— May (@QEEK_01)
qeek.ai