All decision model projects

Pi-based coding agent where a small judge (Jev by default) answers yes/no, choice and score questions at 38 decision points per turn.

Demo that navigates a Neo4j graph hop by hop, asking Jev which relationship to follow and whether the goal is reached.

Jev-inspired decision API with a local mock server and Python and TypeScript SDKs for prototyping; real inference is planned.

Run System One-style typed decisions on any Hugging Face instruct model, with a typesafe-sdk-compatible server and calibration tools.

Federated knowledge retrieval engine for agents that uses Jev to route queries to backends and re-rank evidence, with keyword fallback.

Penalty shootout game against Jev, run as a Render Workflows task with scores in Postgres, in TypeScript and Python versions.

C# System One client and benchmark comparing Microsoft-Decision-1, Jev and open-jev on the same labelled support tickets.

LangGraph dental-clinic agent where a local Jev-style router picks which tools to bind each turn, halving LLM token use.

Calculator with no arithmetic in its code: Jev picks each answer character from 13 options, exposing its distributions and jitter.

Python policy-as-code SDK that runs Noul, Choice and Score rules defined in YAML through Jev, with audit mode and fail-closed options.

Vercel Labs example routing form submissions to the right team with Jev via AI SDK, falling back to an LLM when uncertain.

Kotlin Android SDK where Jev or DeepSeek selects actions from on-screen controls and an accessibility service executes them.

Thin, zero-dependency Python CLI for Jev's models and evaluate endpoints, built for use with a Grok-based Jev router bot.

TypeScript SDK and coding CLI where Jev only picks options: typed routers, decision programs and grammar-constrained AST building.

Russian-language Jev toolkit with a zero-dependency Python client, key pooling and a guide to free credits via a third-party relay.

Early-alpha Haskell DSL that composes typed Jev questions over your data and decodes answers back to the original values.

MCP gateway that trims noisy tool output and offers task classification and review advice, splitting work between local Laya and Jev.

Joke npm package that asks Jev whether a number is not odd or not even via the Vercel AI SDK.

CLI that normalises messy Japanese addresses to postal codes with rules and Japan Post data, asking Jev only for ambiguous steps.

Spring Boot 4 starter that injects a JevClient for asking Noul, Choice and Score questions from Spring MVC apps.

Video demo app showing Jev use cases with the AI SDK and shadcn/ui, from intent search and model picking to chat moderation.

RuneBench fork where Jev plays RuneScape by choosing from about 50 bounded rs-sdk actions and per-tick interventions.

Playground comparing generative UI via an LLM writing json-render specs with Jev choosing and arranging prepared components.

Design-phase proposals for verbatim, Jev-guided context compaction in Kimi Code CLI via a forked mutating PreCompact hook.

Pre-alpha PostgreSQL C extension calling Jev from SQL for Choice, Noul, Score and batched judgments, with EXECUTE revoked by default.

Very early unofficial Rust client for TypeSafe System One with a fluent request builder and typed question and answer enums.

Ruby library that makes System One measurement and probability 'collapse' native primitives, with a TypeSafe Jev provider.

.NET 10 client and examples for Ollama's System One decision API, covering ticket classification and tic-tac-toe.

AI SDK middleware and OpenAI-compatible proxy that runs seven Jev checks on every LLM response, gated by confidence.

Unofficial typed Elixir client for Jev with offline test stubs, concurrent fan-out and atom-keyed answers.