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.
Sponsors
These products pay for the directory. Want yours up here?
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.
jevql is a CLI/SDK that adds Jev semantic predicates, choices, and scores to ordinary Postgres SQL. It calls TypeSafe AI's System One model via the Jev API and supports Go, TypeScript, Python, MCP, and HTTP.
A Kotlin DSL and client for TypeSafe's Jev model, enabling typed questions and answers.
Gut is an Elixir library that maps subjective input to a fixed value and supports configuring the TypeSafe Jev evaluation model.
Community-maintained Java SDK for the TypeSafe AI System One (Jev) API. Implements the System One wire contract with core, Kotlin, Spring Boot starter, and Spring AI bridge; published to Maven Central.
One card in the feed, every sixteen, on every page of it. $50 a week, cancel any week.
Async Python client for the TypeSafe Jev System One decision model. Send typed questions and get probabilities and choices back, no text to parse.
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.
An autonomous triage engine and benchmark powered by TypeSafe AI's Jev System One model, demonstrating high-speed email classification with calibrated confidence.
Mock Jev API decisions with MSW for deterministic tests without real API calls.
CLI and MCP tools for agents using TypeSafe Jev to make fast typed decisions: route, triage, guard, grep, rank, compact, and judge. Includes runnable use-case demos and an offline evaluation script.
A lightweight script that adapts vLLM services to a Jev-style interface, enabling Choice, Score, and Noul decisions via logprobs.
An n8n community node that classifies, scores, and checks text with TypeSafe AI's Jev/System One model, supporting parallel requests and multi-item batching.