jgrep
jgrep is a CLI semantic grep that calls TypeSafe's Jev/System One decision model to judge lines or diff hunks by description, returning probabilities instead of generated text.
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.
Ranked by GitHub Stars
Ranked by recent Star growth and update activity
jgrep is a CLI semantic grep that calls TypeSafe's Jev/System One decision model to judge lines or diff hunks by description, returning probabilities instead of generated text.
watfile classifies document text via TypeSafe AI Jev (System One) and sorts files into category folders. Supports PDF/text, with Jev cloud API and local laya backends.
A CLI and GitHub Action that uses the TypeSafe Jev decision model via OpenRouter to triage pull requests in under a second at ~$0.0001 per PR. Includes tests, benchmark, and a GitHub Action.
Agent-ergonomic CLI for TypeSafe's Jev, offering calibrated judgments via pick/rate/check/rank/triage/guard commands, with safety hooks, GitHub Action, and benchmarks.
jfind is a command-line tool that uses TypeSafe AI's Jev model to find files by natural-language descriptions, with local filtering and probability scoring.
jevgrep is a CLI that pipes text to TypeSafe AI's Jev model and asks a yes/no question, returning only matching lines. Works with tail -f, includes benchmarks, and costs about $0.004 per 1,000 lines.
ask-jev is a Python stdlib CLI that delegates bounded advisory decisions to TypeSafe AI's Jev/System One model (Choice, Noul, Score, batch, purify). It targets AI coding agents and CLI pipelines, with fail-open fallback and explicit remote consent.
Jev-powered, rule-based grader for text files. Runs every rule against every line in parallel. No skimming, no missed lines.
jsort is a Python CLI that ranks texts along a plain-English dimension using pairwise comparisons judged by TypeSafe's Jev model, fitting a Bradley-Terry scale.
Fast semantic code search powered by TypeSafe Jev. Find relevant files, line ranges, and snippets using natural language.
A command-line interface for TypeSafe AI's Jev evaluation model, taking typed questions and returning structured JSON answers.
Docket is a Go terminal app that uses TypeSafe Jev to classify documents, assess sensitivity and urgency, and determine whether action is required.