Document triage
Classify and route incoming documents, invoices and forms.
22 rows are filed under this pattern, 21 of them with code. Rows are listed as the catalogue orders them: official first, then rows with code, then by stars.
Filter and search them in the catalogue →
Rows marked “not Jev itself” or “shadow mode” stay listed, but they are not examples of deciding with Jev.
-
docjev
Classifies and splits PDF, DOCX and PPTX files: LiteParse extracts page text locally, then Jev picks a document's category with a choice over your rules, or for a packet answers per page a category choice and a noul on whether a new document starts there. Its report covers 40 real PDFs.written by a model
-
tax-doc-classifier
Classifies tax document pages: one request per page asks Jev two choices, page kind (7 options) and IRS form (230 plus none), and a follow-up choice for five forms' schedules; criteria come from IRS PDFs and code gates at 0.95. Its author measured no strict error on 314 filled pages.written by a model
-
Quicksilver
Claude Code skill that hands relevance calls to Jev: one noul per file, log line or ticket ('which of these files handle auth?'), asked in parallel and sorted by probability, so Claude gets a shortlist with confidences instead of reading everything.written by a model
-
formanator
Submits Forma benefit claims from the command line or an MCP client. With --category-provider jev, Jev picks the benefit and category with a choice over the pairs Forma allows plus no_match, seeing only merchant and description; under 0.5 confidence or no match it falls back to the configured LLM.written by a model
-
doc-router
Rust library that decides page by page whether a PDF needs OCR: Jev, or by default a bundled heuristic, answers one noul per page from text-layer evidence; text pages are extracted locally and only the rest go to an OCR model through LiteLLM. In the author's run, 87 of 155 pages were billed.written by a model
-
jev-capability-atlas
Independent community map, mostly in Chinese, of which tasks suit Jev and why, from test suites with saved API calls, not a leaderboard: accurate when the answer is in the given text, like which DOM element to click, and miscalibrated elsewhere (48% right at 0.819 mean confidence on DAIR Emotion).written by a model
-
pdf-race
Races three pipelines on 12 arXiv papers: Docling then Jev, Docling then Gemini 3.8 Flash, and Gemini reading the PDF, each answering four questions per paper scored against arXiv's metadata. All got 12 of 12 categories and titles; the Jev lane cost $0.0022 against $0.036 and $0.088.written by a model
-
jevmory
Local memory for coding agents: hooks store what sessions actually said as verbatim quotes, and jevmory audit asks Jev, for each line of a MEMORY.md, whether stored evidence supports or contradicts it, marking it keep, stale, wrong or unsupported. Python standard library, SQLite; grading is opt-in.written by a model
-
jev-layer
Portable System-1 decision layer for agent harnesses with host-owned routing, receipts, replay, and fail-open integrations.upstream description
-
Jev Playwright
Playwright reporter that asks Jev which existing end-to-end tests a code change could affect and skips the clearly unrelated ones before any browser starts. Sends changed paths, patches and test bodies by default; its README warns it can miss affected tests.written by a model
-
jev-document-classification
JEV Document Classification enables the rapid and cost-effective classification of text-based documents using AI, leveraging TypeSafe's "System One" model.upstream description
-
jev-score
Local-first document evaluation workspaces powered by Jevupstream description
-
jev-builder
A browser form for building requests to TypeSafe's Jev: pick a template, fill in the blanks, copy the request. No JSON, no install, runs locally.upstream description
-
jev-information-extraction
Parsing the PDF and extracting the relevant informationupstream description
-
decision-first
Agent skill for Claude Code, Codex, Cursor and more: when a step is a bounded judgment (classify, triage, rank, route, filter, verify, gate), the agent tries Jev first, via a bundled script sending noul, choice or score questions, before a regex or LLM prompt, and logs each attempt, adopted or not.written by a model
-
jev-organize
Throw in a pile of company files and get them classified and organized by department, type, sensitivity, date, counterparty and PII, with an index for AI agents. Powered by TypeSafe's Jev on OpenRouter (17¢ per 1,000 files). Zero-dependency Node CLI + Claude skill + Codex agent.upstream description
-
tiab-review-plugin
A Chrome extension that speeds up title-and-abstract screening for systematic reviews, published on the Chrome Web Store.
-
jev-boe-demo
Each morning a pipeline fetches Spain's official gazette (BOE) and asks Jev, in one call per item, a 0–3 score of how much it changes ordinary people's lives (relevant from 2), 13 category nouls (housing, jobs, tax…) kept above 0.6, and a choice of the paragraph a static site quotes as its summary.written by a model
-
jev-report
发明 RLHF 的人，这次做了个不会说话的模型：Jev 独立研究报告。52 页 PDF + 50 条中文实测复现包 + 143 条可回溯数据表upstream description
-
jev-decision-lab
A local lab for seeing what TypeSafe's Jev judgment model does on realistic business cases: typed answers, probabilities, policy in code, receipts.upstream description
-
last-exit
A cyberpunk border encounter powered by TypeSafe Jev. Bluff the guard. Inspect the receipts.upstream description
-
jevai.org community showcase cases
Nine worked community scenarios: intent routing, invoice classification, news filtering, product tagging, moderation, claim verification, CSV validation and more.