jev-ai

🔥🔥 Awesome Jev: open-source models, projects, benchmarks, and independent evaluations for Jev and System One models.

Deep research tool for local knowledge base.

Established strong JEV based natural language to SQL performance and well-covered semantic operators for PostgreSQL with optimized cost and latency. Reusable evidence, with native execution, parallel plans and explainable embeddings in development preview.

Jev-Mem: System-One Controlled Agentic Memory

Open infrastructure for training, evaluating, and deploying System 1 decision models across language and multimodal backbones.

A self-hosted API and web interface for Laya’s structured decision models, compatible with the TypeSafe Jev API format.

Open-source platform for creating, distributing and running sovereign EU-compliant LLMs. Verticalize any model for your domain, language and brand. AI Act ready.

Autonomous trading agents with deterministic execution. The agents propose; the system decides.

A Bangla-focused adaptation of Laya for typed decisions, classification, and routing.

A decision layer embedded into the harness tool-selection loop

WiFi Analyzer with Jev AI

A Claude Code plugin that keeps your AI agents honest. Claude plans tasks as phases with checks, and when it tries to stop, Jevflow runs them and asks Jev if the work is really done. Many agents, one plan, with a live viewer to watch it all.

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

Live TopstepX bot trading on futures, AI-graded entries (Chronos+XGBoost) with a PPO-learned trailing-stop exit.

A private, local decision-advice Skill for Codex that ranks tool choices, estimates risks, guides recovery, and checks completion evidence.

Evidence-first long-term experiment memory skill for AI coding agents, with optional Jev decision-model layers

The Awesome List of Awesome Jev Lists

Jebadiah, an open System One decision model: trainer, data builders, evals and every run record

Ask Jev over columns of data: closed-set questions, cached and joined back.

Judgment calls as one line of Python, built for TypeSafe AI's Jev and running on any small model: likely / classify / rate → YES, NO or UNSURE. Also local NLI, local LLMs, Ollama, vLLM, OpenAI.