All decision model projects

Experimental Swift 6 SDK for TypeSafe using SwiftPM, Swift concurrency and URLSession across all Apple platforms.

Unofficial dependency-free .NET port of the TypeSafe JS SDK v0.6.0, accompanying blog posts including an MCP server.

Unofficial .NET client that posts state and typed questions to /v1/systemone, inside a repo of assorted vibe-coded SDKs.

Declarative compiler that turns state, decisions and labeled examples into a measured, frozen JSON program of typed Jev questions.

Research proposal-review contract: an LLM proposes one action, Jev answers four narrow questions, code produces evidence, applies nothing.

Pi agent harness where Jev routes the model tier, picks runbook sections, gates tool calls and verifies reports on Neon Postgres.

Research preview: Python client and pinned adapters for running System One decision models on your own Modal GPUs.

Calibration experiments showing Jev's Choice probabilities on fair dice and coins stay high while accuracy stays at chance.

Rust client, CLI, terminal UI and eval harness for asking System One questions of a local model served on Xeon Phi cards.

Learning project that builds choose-an-answer decision models from scratch and from Qwen, with downloadable 0.8B and 4B releases.

Reproducible bake-off of Playwright CLI alone, CLI plus Jev, and Playwright MCP on fuzzy browser goals, with honest results.

Jev-inspired PyTorch research framework that encodes an overnight sleep recording once and answers many Choice, Noul and Score questions.

Accenture thought piece and site on stack migration with Google Cloud, placing Jev as the System 1 layer that routes, classifies and gates.

Curated directory of Jev showcase posts from X, organized into 25 categories with video previews and source links.

Public wall where Jev answers short questions yes, no or it depends in about 100 ms and picks which LLM answers signed-in users.

Unofficial Jev information hub site with access guide, pricing comparison, a BYOK playground and an auto-updated news timeline.

Interactive playground that walks step by step through real Jev requests and their probabilities using your own key.

Chinese-run aggregator of X long posts and demo videos about Jev, keeping original links and authors rather than rehosting.

Interactive teaching site where Jev races frontier LLMs in games, an arena, a sandbox and quizzes, with a keyless replay mode.

Multilingual Astro documentation site on Jev patterns and practice, whose own publishing pipeline is gated by Jev decisions.

I Ching divination site where charts and verdicts come from code and Jev only classifies the question's topic and screens unsafe ones.

Unofficial Jev operator lab: offline-first FastAPI app with primitives playground, cost lab, pattern pages and a TypeScript harness.

Daily arXiv and bioRxiv radar where Jev answers one yes/no per plain-English interest for every new paper; fork-and-go GitHub Action.

Next.js site with six live Jev demos, each compared side by side with Gemini or Claude on latency, cost and agreement.

Ollama-style single binary that pulls and runs open decision models locally, with a TypeSafe-compatible API and playground.

AstrBot group-chat plugin fork that adds a 50-70 ms System One check on whether the bot should chime in, after the original random gate.

LM Studio-style desktop app and local server for open Jev-like decision models, with a playground, templates, API and LoRA training.

Writing checker running separate named Jev checks such as hedging, filler, tone and passive voice, each with its own verdict.

Python re-style library that finds, replaces, splits and extracts text by meaning, with Jev judging each candidate span.

Web app that lints human prose like a compiler: Jev measures tone and information, code emits rustc-style diagnostics.