jevframe: Semantic AI for pandas/Polars via TypeSafe Jev
jevframe is a Python library that uses TypeSafe Jev to classify text, analyze sentiment, and score pandas/Polars rows with complete probability distributions.
OPEN SOURCE · CURATED REPOSITORIES
Curated Jev SDKs, tools, demos, integrations, benchmarks, and research projects. Repository metrics come from GitHub; titles, summaries, and categories are editorial.
Sponsors
These products pay for the directory. Want yours up here?
Ranked by GitHub Stars
Ranked by recent Star growth and update activity
jevframe is a Python library that uses TypeSafe Jev to classify text, analyze sentiment, and score pandas/Polars rows with complete probability distributions.
Interactive demo that uses TypeSafe's Jev model to answer questions and extract information from PDF text.
A web app that uses TypeSafe Jev to analyze privacy policies and provide plain-language answers, confidence scores, and source excerpts.
A Python tool that uses TypeSafe Jev (System One) to scan old hard drives and identify files of value.
Uses TypeSafe Jev to judge a year of posts from any public Telegram channel, producing a card with ad, clickbait, and emotional-pressure metrics. Runs as a single Cloudflare Worker.
One card in the feed, every sixteen, on every page of it. $50 a week, cancel any week.
Independent JavaScript tool that calls TypeSafe AI's Jev API to resolve ambiguous joins between French public datasets, returning auditable candidates and review cases. Includes a local demo and tests; no live performance benchmark is claimed.
DataJev is a Python data-agent framework that uses TypeSafe AI's Jev (System One) as the controller for LLM-driven analysis. It emits CONTINUE / SWITCH / VERIFY / STOP decisions and includes a CLI, offline smoke tests, and run traces.
A Python CLI and library that applies a qualitative codebook to open-ended text using TypeSafe AI's Jev (System One), with a review queue, confidence intervals, and inter-rater reliability metrics.
A web app that scores cybersecurity CVs with TypeSafe's System One model JEV on Cloudflare Workers, classifying against NICE, ECSF and SFIA, with every number traceable to the question that produced it.
CLI tools that export Telegram group chats, segment conversations into threads, and score dispute intensity using TypeSafe AI's Jev (System One) model. Includes user profile generation and conflict analysis.