Coding harness usage signals

Compare public signals from five ecosystems. Each view keeps its own unit, time window, coverage, and limitations, so you can inspect adoption context without confusing it with quality.

Source-separated rankings

OpenRouter attributed traffic

Traffic attributed to public coding apps using OpenRouter's app-attribution mechanism.

Token totals combine prompt and completion tokens. Tokenizers differ, attribution is opt-in, and this is not standardized work, users, or task success. Missing coverage means not mapped, never zero.

Download all signals (CSV)

Why these sources stay separate

OpenRouter tokens, Homebrew install events, package downloads, editor installs, and repository activity observe different populations. Adding them together would create a precise-looking but invalid total.

Routing
OpenRouter attributed tokens and requests over completed 1-day, 7-day, and 30-day UTC windows.
Distribution
Homebrew 30d install events, npm last-month downloads, and cumulative VS Code Marketplace installs for exact mapped artifacts.
Repository interest
GitHub stars and forks for the repository already audited by HarnessMatch, with full, client, or support scope preserved.