Graph My Keywords

What actually happens to your keywords

No API keys, no uploads, no waiting in a queue. A small language model runs inside your browser tab and groups your keywords by what they mean. Here is the whole pipeline — and five real keyword sets you can open in one click.

The pipeline

Four steps, all of them local to your machine.

STEP 1

Read the CSV

Your export is parsed in the browser. The keyword column is detected automatically — query, keyword, top queries and similar all work, with comma, semicolon or tab separators. Duplicates are dropped.

STEP 2

Turn words into meaning

Every keyword is passed through all-MiniLM-L6-v2, a sentence-embedding model that turns text into a 384-number vector. Keywords that mean similar things end up close together — even with no words in common.

STEP 3

Find the topics

Tight groups are seeded first, near-duplicate groups merged, then every keyword is assigned to its closest group. Each topic gets named after its most distinctive words, weighted so generic terms lose out.

STEP 4

Draw the map

Topics that are similar to each other get connected, and a force layout arranges the result. Bubble size is keyword count; connected groups of topics share a colour. Export the clusters as CSV or the map as a PNG.

Why "by meaning" matters

Keyword tools that group by shared words put "how to make cold brew" and "cold brew ratio" together, but miss that "iced coffee recipe" belongs with them. Embeddings catch that, which is why the clusters map to pages you would actually write rather than to string matches.

Five real examples

Each of these is a genuine keyword set run through the same pipeline you get. The counts and topic names below are the real output — open any of them to explore the live, interactive version.

Topic map of 153 coffee keywords forming 26 clusters

Coffee & brewing

A hobby niche with many distinct sub-crafts. Brewing methods separate cleanly from gear, health questions and the coffee-shop business angle.

153keywords26topics
espresso · machinefrench · presscold · brewbenefits · you
Open this example
Topic map of 85 project management keywords forming 11 clusters

Project management software

A B2B SaaS niche. Product-comparison queries split away from methodology explainers and career terms — three very different pages, three very different intents.

85keywords11topics
management · projectgantt · chartmanager · projectasana · monday
Open this example
Topic map of 78 fitness keywords forming 9 clusters

Home fitness

Training, fat loss, mobility and nutrition pull apart into their own clusters — a good illustration of one broad niche that is really four content pillars.

78keywords9topics
home · workoutloss · fatsplit · routineroutine · stretching
Open this example
Topic map of 80 personal finance keywords forming 7 clusters

Personal finance

Investing, budgeting, debt, credit and retirement are close neighbours in language but separate pages in practice. The map shows where the boundaries actually fall.

80keywords7topics
budgeting · makeemergency · fundstudent · repaymentscore · credit
Open this example
Topic map of 77 Japan travel keywords forming 6 clusters

Japan travel

Destination guides, transport, food and practical logistics. Note how city names cluster by city rather than by the word "guide" — that is meaning-based grouping doing its job.

77keywords6topics
travel · japantokyo · guidefood · japanesetickets · teamlab
Open this example

Now try your own

Export queries from Search Console, Ahrefs, Semrush or Keyword Planner and drop the CSV in. It never leaves your browser — free up to 500 keywords, and more on request.

Upload my keywords