GitHub

Split-screen demo where Jev detects Pix-payment scams and traces the fraud chain.

Discord bot demo that lets users converse with Jev-backed typed behavior.

Community playground with editable Jev use cases, games, dilemmas, challenges, and A/B comparisons.

Drone-swarm simulation using Jev for reflex decisions and collision avoidance.

AI-town simulation where Jev selects character actions and responses.

StarCraft agent experiment using Jev for fast tactical decisions.

PDF reader that uses Jev Noul judgments to highlight lines matching a natural-language question.

Windows WeChat assistant that reads and redacts conversations before Jev classifies them.

Browser extension that uses Jev to identify and fold ads and selected topics on social platforms.

Android WeChat module that uses Jev to show emotion probabilities, implied meaning, and communication suggestions.

Four decision-quality applications where Jev answers structured questions and deterministic code keeps final authority.

Exchange deposit and withdrawal risk-triage gateway where Jev triages and deterministic code adjudicates.

Crypto decision dashboard that uses Jev to classify market state and risk.

WeChat plugin that uses Jev to analyze message intent, emotion, and reply posture locally.

Intraday trading bot where Jev ranks Nifty 50 candidates and deterministic code controls position sizing and risk.

Stock-analysis application that uses Jev for structured market judgments.

Windows WeChat reply assistant that uses local OCR and Jev to classify intent before presenting three manual-send replies.

macOS voice and text control where Jev selects UI actions in an observe–act–verify loop.

Indexed browser automation where Jev selects a control and Playwright executes it.

Code and document search CLI combining BM25 recall with Jev verification and calibrated reranking.

Portable Jev router for cost-aware Codex subagent model and reasoning selection.

Natural-language linter that uses Jev to evaluate code against plain-language rules.

Claude Code plugin that uses Jev for rule checks, verbatim compaction, and prompt routing.

Jev-native agent design with top-k proposals, fallback decisions, memory, and replanning.

MCP proxy that uses Jev to screen agent tool calls and tool results.

MCP tools that expose Jev for verification, screening, classification, reranking, review, gating, and scoring.

Local multi-upstream router for the Jev protocol with a Rust backend and React interface.

Site search that recalls candidates locally, then uses Jev to score and rerank them.

Agentic GraphRAG pipeline with swappable local Laya or cloud Jev decision models.

Probability-tree and graph runtime for verifiable multi-step Jev decisions.

Jev-shaped classification wrapper over OpenAI-compatible clients that returns probabilities and confidence.

Open-weight Jev-inspired decision model fine-tuned from Qwen3.5 4B.

Local Jev-compatible typed decisions from unstructured state in one forward pass.

Local Jev-compatible proxy that learns an application’s typed decisions and serves them with a Laya head.

Training and inference stack for calibrated Jev-style choice models with dynamic candidate sets.

Open visual decision model that encodes an image once and answers multiple structured questions.

Solar Mini–based local model for Jev-style typed decisions.

Open-weight Jev alternative that returns typed decisions with probabilities in one forward pass.

Open-model semantic-if engine for local Jev-style decisions.

Go SDK and CLI for TypeSafe Jev typed yes/no, Choice, and Score decisions.