Launches on September 27, 2026
Repositories created on this date, ranked by GitHub stars. They launched the same day, so their stars compare directly.
- 510
Jev judges every review and return, Elasticsearch aggregates the judgments, and a leashed Claude Code agent turns them into proposed catalog fixes that a person approves.
- 520
Simple personal profolio plus chat assistance with RAG and Jev
- 530
Self-hosted AI moderation bot for Telegram groups. Catches spam, ads and insults with the open Laya model running locally on CPU, or with the Jev API. Escalating mutes, appeals, admin menu. RU/EN.
- 540
Jev intent classification for Mautic form submissions
- 550
Model routing for OpenCode powered by the JEV
- 560
Jev completeness triage for OpenProject work packages
- 570
Motor determinista de normas urbanisticas chilenas (OGUC + PRC) para revisores independientes y DOM. El LLM clasifica y redacta; nunca calcula ni dictamina.
- 580
Typed Jev decisions in Redpanda Connect pipelines
- 590
One-click System One local inference API server
- 600
System-1 decision models (Jev/Laya/Kev-class) as the governance layer for an LLM agent context lifecycle: growing association graph over session segments, relevance-gated recall with Trace-as-State ordering, and plan pre-ranking — measured in solve rate, cache hit/miss tokens, cost and latency. DSH plugin + harness-agnostic proxy.
- 610
Jev decision review for Saleor product webhooks
- 620
A free streaming-first open-source redaction toolit
- 630
Model Context Protocol (MCP) server & OpenCode skill for San Francisco Early Learning For All (ELFA) preschool search, voucher calculations, and TypeSafe Jev System One evaluation
- 640
all thinkers in human history answer your questions
- 650
Turns raw smartphone reviews into per-topic star ratings (Camera, Battery, Display, etc.) using Jev LLM analysis. Real-time text-to-rating pipeline, no manual tagging needed.
- 660
Run the new wave of decision models (Laya, Decider, Kev, Jev) side by side on your Mac. Structured input in, calibrated probabilities out, with honest accuracy, calibration, latency and memory numbers.
- 670
A flight recorder for Jev decisions: a free Windows app that records, shows and lets you grade the answers your apps get from TypeSafe's Jev. Unofficial.
- 680
Instant Ticket Classification using JEV from Typesense AI
- 690
Notices your Jev decisions tilting before anything visibly breaks
- 700
A Jev-like System One model in your browser: a small language model plays a first-person shooter on your GPU, one token per move. No server.
- 710
A smart, continuous topic filter for YouTube powered by Jev.
- 720
Demo de triagem inteligente de atendimento de cartao de credito: em vez de uma IA generica decidir sozinha em texto livre, o sistema classifica o chamado e aciona regras de negocio auditaveis e controladas, evitando decisoes financeiras regulatorias tomadas as cegas por um LLM.
- 730
ZCode PreToolUse guardrail built on the shared jev-evaluator core, combining deterministic rules and TypeSafe Jev for allow, ask, and deny decisions.