Havuz

AnyJev, open LLM’lerden typed kararlar ve eşiklenebilir olasılıklar üretmek için calibration ve karar katmanları sunan bir Python kütüphanesidir.

Neden yükseliyor · Yedi günde 802 yıldız almış; dikkat çekmesinde etiket gerektirmeyen ilk seviye, az etiketle kalibrasyon iddiası ve modeli fine-tune etmeden karar endpoint’i sunma yaklaşımı etkili görünüyor. Bu ilgi benimseme kanıtı değil; verilen sonuçlar README’deki sınırlı benchmark’a dayanıyor.

Run Laya, the open-source Jev-compatible System-1 decision model, from Node.js / TypeScript via ONNX Runtime

Jev-compatible API server for open decision models. Ollama for decision models: pull and serve 29 model families (Laya, pplx-decider, Clef,

🚀🚀 A multimodal System One decision model that gives calibrated answers to typed questions about screens, photos, video and text in one forw

Classify text in PHP without an LLM bill: typed decisions in 100+ languages, self-hosted. Laravel-ready SDK for Laya, a Jev AI alternative.

System 1 decision models (Jev, Laya, Cua-S1) as brain for agents: Browser use, computer use, games and robotics

Typed-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and

A 4B decision model: calibrated probabilities for yes/no, choice and score questions over long inputs.

A zero-embedding approach to video intelligence, using Jev: contact sheets + typed decisions, as MCP tools and a skill for any coding agent.

Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a probability for every option.

Open-source, local-first social media research agent for Instagram, TikTok, and LinkedIn. Jev routes read-only steps; socai CLI captures cit

Transformers for decision models: fine-tune, load and serve calibrated decsion-model on any Hugging Face model.

Bulk classification and decision inference on one GPU: the content is read once, every question about it is scored in the same pass. OpenAI-

Open, calibrated System 1 decision models: typed choice / score / yes-no answers with a probability for every option. 400M to 80B; CPU, NVID

Decisions, not essays: a choice, a yes or no, or a score with a calibrated probability. Open weights, Jev-compatible API, adaptive thinking.

OpenJev: open-source, local alternative to Jev. System-One decision models: typed questions in, calibrated probabilities out; general decisi

Train JEV-style System 1 decision models on Qwen3.5 and Qwen3.8-27B: 24-slot decision head, KL distillation, calibration and serving. 在 Qwen

Laya decision model’i yerel ortamda denemek için web arayüzü, oyun demoları, benchmark ve agent skill sunuyor.

Neden yükseliyor · Yedi günlük yaşına rağmen 164 yıldız almış; yerel çalışan demoları, benchmark’ı ve agent skill’i tek repoda birleştirmesi projeyi keşfetmeyi kolaylaştırıyor. Ancak son 28 gündeki 8 commit’in tek yazardan gelmesi, ilginin bağımsız katkıcı tabanına dönüşüp dönüşmediğini henüz göstermiyor.

Ask your house a question, get a number back. Home Assistant integration for TypeSafe Jev: typed answers as sensors, four actions for automa

Local classification, routing, and scoring for AI agents, with option probabilities. Text + images, Python, MCP and agent skills.

Blazing fast, self-hosted structured decisions for open models with a TypeSafe AI compatible API, written in Rust.

⚡ Millisecond System-1 judgement for every tool call in DeepSeek Harness — Jev-powered risk classification & evidence-gated auto-approval. F

Local, open-source Jev alternative: browser agent decisions with Laya (System One model) on your own machine. No cloud, no API key. Playwrig

TypeSafe Jev for DeepSeek Harness, the Model Context Protocol, and plain Node: typed judgments instead of prose, offline by default.

✨✅ The easiest decisions your code will ever make.

Dohnuts builds small multimodal models for direct decisions. -> System One model

Acta: A Decision-Centric Runtime for Agents

Instinct: single-forward-pass decision models (choice / true-false / score) returning a probability per candidate

Fast, typed Python framework for Jev-as-a-Judge/Decision-model evaluation for LLMs, RAG, and AI agents along with human-label calibration.

Turn any local language model into a fast decision API with typed, probabilistic answers

The decision layer for your Rails app. A Rails-native wrapper around TypeSafe's Jev System One API: typed, calibrated decisions in your cont

openvons (open-Jev): 有限選択肢に確率で答える判断層 — テキスト / 画像 / 日本語音声コマンド

A decision model that returns calibrated answers to yes/no, choice, score and multi-label questions.

grep for meaning: ask a question about lines, logs, diffs or JSON and explore the answers live. Runs locally on CPU, one Rust binary.

Per-turn model routing for the Pi coding agent: a small judge picks the cheap or the strong tier for each message, with multi-model failover

What can Jev actually do? Reproducible experiments and research reports exploring its capabilities and limits.

A 4B decision model built for Korean.

Intent-Router, belirsiz istekleri inceleyip eksik noktaları soran ve yönlendirme öncesinde makinece okunabilir bir IntentSpec üreten bir agent skill’idir.

Neden yükseliyor · Altı günlük bir repoda 141 yıldız ve 81 commit dikkat çekiyor; ancak commit’lerin tek yazardan gelmesi, ilgiyi bağımsız geliştirme veya benimseme kanıtı olarak yorumlamayı sınırlıyor. README’deki ölçümler de küçük örneklemli (N=5 ve N=3) ve proje tarafından raporlanmış.