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.

How it uses Jev

JEV Document Classification is a local-first application that files root-level documents into configured category folders. It extracts readable text locally, then uses typesafe-ai/jev through Vercel AI Gateway for typed category, confidentiality, prompt-injection-risk, and subject decisions.

Getting started

Open http://localhost:5173 , enter a Vercel AI Gateway API key, choose a folder, and start classification. The application creates config/config.toml when it is missing. You may optionally save an absolute default source-folder path in Gateway settings; the local server will reopen it automatically.

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to jev-document-classification

Browse all
jev-rerank project preview
Applications
Use Jev (TypeSafe's System One model) as a calibrated reranker: one call, up to 30 documents, a probability per document. Apache-2.0.
nlgrep project preview
Applications
TypeScript CLI that finds code, docs, logs, and text by natural-language conditions using Jev Noul judgments, with probability thresholds, source lines, and cached results.
scam-shield project preview
Applications
Scam text message filter powered by TypeSafe's Jev model
jev-router project preview
Agent tooling
Cost-aware LLM router that picks the cheapest model capable of handling a query, using TypeSafe's Jev for fast classification instead of an LLM call.
n8n-nodes-jev-classification project preview
n8n community node for Jev by TypeSafe AI: classify, score and check text with calibrated probabilities. Parallel requests and multi-item batching.
slop-grader project preview
Agent tooling
Rule-based slop grader for text files powered by Jev: evaluates markdown against customizable rulesets, outputting violation flags and scores for an AI agent to auto-fix.
jev-chess project preview
Benchmarks & research
Chess moves, evaluations, persona opponents, and game classification with TypeSafe AI System One
lkclean project preview
Browser & computer use
Chrome extension that cleans up your LinkedIn feed: hides engagement bait, self-promo and off-topic posts using Jev, TypeSafe AI's typed classification model — and explains every decision.