doloop decorations paints an expert's reading order onto the file you already have open. It dims the connective tissue, lights the code that carries the decisions, and marks where to start, computed from the whole repo. Deterministic, local, zero tokens. We do not build an editor. We decorate the one you already use.
The honest answer is no, and it is worth being precise about why, because the three things that look like this are each doing something else.
IDEs render the novice's gaze: universal rules, equal weight, you crawl it yourself. AI assistants render a prose summary: stochastic, token-costly, bound to a keyhole. The deterministic, whole-repo, codebase-relative expert's gaze, greying the connective tissue, lighting the code that carries the work, naming the doors in this repo, is in neither box.
Universal rules, every symbol equal. You crawl it.
A prose summary. Stochastic, token-costly, a keyhole into a big repo.
The expert's gaze, precomputed, deterministic, whole-repo, painted onto the file you have open.
Deterministic and comprehension-first was in neither box. That unowned quadrant is where doloop stands.
All deterministic, all local, zero tokens. It rides VS Code's and Cursor's own decoration surface, so there is nothing new to learn and nothing leaves your machine.
doloop decorations is complementary, not a replacement. It will not answer your specific question or explain the semantics in prose. That is the assistant's job, and the read view hands off to it: read the map here, ask for the story there. What doloop does that nothing else is set up to do is play a deterministic, whole-codebase, show-don't-tell game. We are not claiming to have settled how a person comes to understand a codebase. We are the only ones standing in the place where that question gets a reproducible answer.
It runs unmodified in VS Code and Cursor (same extension API). Bring nothing but the editor you already use.
Routes you to a real page, asks when ambiguous, or refuses. No model on the answer path, so it never invents.