Deep research tool for local knowledge base.
Evidence-first long-term experiment memory skill for AI coding agents, with optional Jev decision-model layers
Windows port of Laya typed-decision AI (ONNX Runtime + DirectML) — Core ML/Apple Neural Engine alternative with first-class Arabic support. No text generation, no hallucination, runs on any DX12 GPU.
decision-first data cleaning system powered by Jev
Jebadiah, an open System One decision model: trainer, data builders, evals and every run record
When Jev meets LLM — Transparent proxy that makes AI coding agents 3× faster and 80% cheaper. Cut response times from 2.4s to 890ms with Line J architecture.
Decision model on a Qwen3-0.6B backbone with LoRA: fused decision endpoint (/v1/systemone) + OpenAI-compatible chat completions with thinking, SSE streaming and vLLM-style sampling, running on Apple Silicon MPS.
Dockerized REST service, jev-compatible, that serves the Laya model (convaiinnovations/laya) for use from non-Python apps.
A Proxy that enables zero-shot system one typed-decisions endpoint for decoder only models served with vLLM or Sglang or Openrouter (Experimental)
Reproducible Laya-CoreML vs Jev benchmark for zero-shot intent classification on Banking77, ArBanking77, and CLINC150. Includes paired accuracy and per-dataset results.
Security & calibration middleware for System 1 AI models like jev & laya
Jev Guard is a real-time Windows process monitoring application powered by TypeSafe's Jev AI model. It tracks newly launched processes, logs event metadata (paths, command lines, and parent processes) to a local SQLite database, and classifies risk levels—labeling events as benign, suspicious, or malicious on a live interactive dashboard.
Adapt language models to Jev-style structured questions.
This repository contains a GitHub issue classifier built on Jev, TypeSafe AI's System One model. It labels every new issue with typed values and calibrated confidence in milliseconds, labelling what it is sure about and escalating what it is not. Three guardrail layers guard every write, and a frozen eval suite gates each deploy.
Large typed decision model evaluation benchmark and novel calibration standard (`calibration.json`) for any typed decision inference system, covering 275 distinct use-cases and 27,598 individual decisions for Jev-like open typed decision models.
Engineered with a confluence-driven architecture combining ICT / Smart Money Concepts, a TradingView Chart Pattern Engine, TypeSafe Jev AI (System One) Cognitive Reasoning, Dynamic Leverage (10x–50x), and an interactive Rich Terminal Dashboard UI.
General Viral Gene Annotator, using two tiered AI-architecture
To associate your repository with the jev-api topic, visit your repo's landing page and select "manage topics."