Repo · Data & extraction
Tocsin
22.8M log lines grouped into patterns, then one question each.
Open github.com ↗How builders describe it
Ateeq used Jev to solve a problem every agent eventually runs into: reading logs. Tocsin groups 22.8M log lines into 11,812 repeating patterns, then asks Jev about each pattern once — 6 minutes and 64 cents (vs $1,120 to run an LLM on every line), surfacing 123 patterns that actually needed a look.…
The decision Jev makes
Keep or drop a row, assign a label, or select one field value at a time.
Where it fits
Putting Jev next to the data: filtering rows with plain-English conditions, classifying records, labelling datasets and pulling structure out of text one small decision at a time. All 61 data & extraction projects →
Related projects
Data & extractionread-with-jevA Demo of using JEV to classify various attributes of a book, and present that to the reader to augment the reading experience.GitHub · ★ 3 · carlaiau
Data & extraction12 million source updates every six hoursA research pipeline that used to cost over a million dollars.X post · leiroData & extractionQualifying candidates with JevAn internal tool, and the limits of a rubric.X post · Prasad Pilla
Data & extractionScoring educational video segmentsJev scores segments of educational video.X post · Ziggyzonty
Data & extractiontab-jevA Jev-like model paired with a tabular foundation model.X post · jerrycxu
Data & extractionCrypto tagging, 20× fasterDopamyn’s account tagging is about 20× faster and cheaper with Jev.X post · Dopamyn