Every number on olud.ai comes from a public, verifiable source and is refreshed automatically. This page explains where the data comes from, how tools are selected, how comparisons are built — and what we will never do.
Stars, activity and repository metadata for 10,000+ open-source AI projects are pulled directly from the official GitHub API and refreshed automatically, every day. We also track star velocity over time to surface projects that are trending, not just big.
Model lists, context windows and per-token pricing for open-weight and commercial models come from the OpenRouter API, refreshed every hour. We keep a price history so changes are visible over time, not silently overwritten.
The tools directory and the alternatives guides are curated by hand: every entry is checked against its repository and official site before publication (license, activity, install path, what it is genuinely good at).
English is the source of truth. The five other languages (FR, DE, ES, IT, PT) are machine-translated from the English pages and regenerated whenever the source changes. Model names and prices are intentionally left untranslated.
A tool enters the directory only if it meets all of these criteria:
For each tool we publish the same structured facts: category, license, local execution, language, ease of use, what it's best for, and its strongest points. Suggestions are welcome through the submission page and are reviewed manually against the same criteria.
Head-to-head pages (X vs Y) are only generated between tools of the same category, from a single structured feature matrix — both sides of a comparison are always evaluated on identical criteria, from identical data. Model comparison tables use the same live OpenRouter feed as the pricing pages, so a price you see in a comparison is the same price you see everywhere else on the site, at the same timestamp.
On each tool page you will find an Olud Pulse score out of 100 (and its 1-to-5 star equivalent). It measures one thing: real-world adoption momentum, from public, verifiable signals — never our opinion, never a paid placement.
Up to five signals feed the score, depending on what exists for each tool: GitHub stars (total), star velocity (stars gained over the last 7 days), Docker Hub pulls (cumulative), PyPI downloads (last 30 days) and npm downloads (last 30 days).
The method: for every signal, each tool is ranked against the other curated tools, and its position in that ranking becomes a percentile. Its Pulse is the average of those percentiles across the signals it actually has — a library that only lives on PyPI is not penalised for having no Docker image. Tools tied on a signal share the same rank. A signal measured at zero counts as last place, not as missing data. Scores are recalculated every morning from fresh data.
Honest limits: Pulse measures adoption, not quality — a well-marketed tool can outrank a brilliant niche one. Tools without any public footprint (no open repository, no public package) have no score at all rather than a made-up one; that is why a few pages show no Pulse block. Read the score together with the number of signals shown beside it: 183 of our 230 measured tools are only visible on GitHub, and a Pulse built on one signal does not mean the same thing as a Pulse built on four. Docker Hub covers 15 tools, PyPI 39, npm 13.
We also don't editorialize numbers: stars, prices and dates are shown as the source APIs report them. When something is wrong — it happens, upstream data isn't perfect — tell us and we'll fix the source or the pipeline, not just the page.
Read more about the project on the About page, or reach out — corrections and suggestions make the site better for everyone.
About this project →