Havuz

Coverage, security and code quality for coding agents

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

Fine-grained robot control with Jev, physics previews, and configurable LIBERO tasks.

Local proxy that learns your app's typed LLM decisions and answers them with a Laya head. Jev and OpenAI compatible.

TypeScript uygulamalarının `choice`, `noul` ve `score` biçimindeki sınırlı AI kararlarını farklı System One provider'ları üzerinden çalıştırmasını sağlayan bir runtime sunuyor.

Neden yükseliyor · Beş günlük repo için 60 yıldız ve son 28 günde 116 commit dikkat çekici başlangıç ilgisi ve geliştirme temposu gösteriyor. Ancak yalnızca 2 farklı yazar var; bu nedenle veriler geniş benimsemeyi veya sürdürülebilir topluluk desteğini henüz kanıtlamıyor.

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

Typed semantic decisions for Unix pipelines and CI, powered by TypeSafe AI Jev.

Meet JevEmbed — turn embeddings into decisions. Choose, score, and judge with your choice of embedding model.

A decision cache for TypeSafe Jev-class models — memoize decisions so repeats are free, deterministic, and shareable. One 2 MB binary.

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

Best Roblox Studio Instance Reviewer 2026: Typed Jev Criteria and Exact Citations

Local gateway that routes coding-agent tool decisions through Jev and can attach a read-only advisor (GPT or Claude).

Distill a repeated Jev classification task into a local model, on the fly — same answers, your hardware.

Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM i

JEV-inspired parallel decisions for CUDA LLMs. One context, many decisions. vLLM API, game-agent examples, and reproducible benchmarks.

Jeview, Jev (TypeSafe System One) API çağrılarını yerelde kaydedip canlı haritada görselleştiren bir gateway ve geliştirici aracıdır.

Neden yükseliyor · Repo 6 günde 56 yıldız almış; bu erken dönemde dikkat çektiğini gösteriyor, ancak yıldızlar kullanım veya kalite kanıtı değil. Son 28 günde 15 commit ve 1 farklı yazar bilgisi geliştirme hareketliliğine işaret etse de katkı tabanı tek kişilik. İlginin kesin nedeni verilerden anlaşılamıyor.

Claude Code / Codex / pi plugin that hands agent steps needing no text output to Jev (TypeSafe's judgment model) — measured p50 ~230 ms and

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

Agent that actually understands social platforms. Fast. Precise. Deep.

A database-agnostic Agentic GraphRAG framework using swappable System One models (local Laya / cloud Jev). A plug-and-play intelligence laye

Jev, TypeSafe's System One classifier, as a tool inside Claude Code, Codex, Pi, and OpenCode: typed classify, check, score, rank, and ask, p

Lev: Thinking Fast and Deep with Looped Decision Models. One checkpoint, multiple depths: System 1.5 decision models that think in loops, no

Go SDK and CLI for TypeSafe Jev: typed decisions (yes/no, choice, score) from a model

✨✅ The easiest decisions your code will ever make.

A 4B decision model built for Korean.

Evidence-backed knowledge graph construction with typed Jev relation decisions

ACP and MCP adapter that bridges TypeSafe Jev with any LLM — computer use and typed decisions alongside Codex, Claude, Grok, and OpenCode.

An agent skill to discover TypeSafe Jev opportunities, design typed questions, and learn from recent community experiments.

Agent-ergonomic CLI for TypeSafe's Jev: fast calibrated judgments (pick, rate, check, rank, triage, guard) from the shell

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

Voice and text control for macOS. One floating bar, live UI action selection with Jev, and a continuous observe–act–verify loop.

A custom coding harness for TypeSafe AI's Jev: an LLM proposes, Jev answers narrow questions, code decides, every step leaves a receipt.

Let Jev read every new arXiv paper each morning and surface the few you should read. Plain-English interests, calibrated probabilities, ~$0.

Command-line tool for TypeSafe AI's Jev model. Ask yes/no, multiple-choice and rubric questions about any text and get calibrated probabilit

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

Claude Code plugin that picks the model and effort for each turn (micro, low, medium, or high tier), advised by Jev, Clef, OpenAI, or a loca

Text extraction with Jev: field extraction, PII detection and exact quotes, built on TypeSafe's Jev.

Practical, tested recipes for TypeSafe's Jev decision model on OpenRouter: support triage, database indexing, file organizing, tagging, taxo

A codebase scanner that helps you not run malicous code

Jev-powered, rule-based grader for text files. Runs every rule against every line in parallel. No skimming, no missed lines.

A spatial reference explorer for creators. Local Jev query choices, metadata highlights and source-linked collections.

Voice control for macOS that acts partway through your sentence, built on Jev (TypeSafe)

jev-calibrate, Jev sorularının etiketli örneklerde karar vermeye uygunluğunu ölçen bir TypeScript CLI aracıdır.

Neden yükseliyor · Kesin yükseliş nedeni mevcut verilerden anlaşılamıyor. Repo 6 günlük, 32 yıldızlı ve son 28 günde 11 commit almış; ancak farklı yazar sayısının 1 olması aktivitenin tek geliştiricide toplandığını gösteriyor.

pijev, Jev ile yapılan sınıflandırma çağrılarında seçenek sırasının tahminleri etkilemesini azaltmak için permütasyon sonuçlarını ortalayan bir Python wrapper'ıdır.

Neden yükseliyor · Repo 5 günlük ve 34 yıldız almış; bu kısa sürede ilgi gördüğünü gösteriyor, ancak bu ilginin nedenini veya gerçek benimsemeyi belirlemek için yeterli kanıt yok. Son 28 günde 3 commit ve 1 farklı yazar olması, geliştirme etkinliğinin tek kişide toplandığını gösteriyor.

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

GTM workflows with Jev: datasets, prompts, and benchmark results.

Jev-powered decision support for OmO and senpi agents

BrowserClaw - Control your everyday Chrome browser from AI agents, without losing logins or focus

Fast browser and macOS computer use for MCP agents. Local execution, TypeSafe Jev decisions, verified outcomes.

Pluggable decision layer for the ego lite browser: one System One (Jev) call per step replaces the per-step LLM turn, and the backend can be