All decision model projects

Swift library and CLI for Jev with enum-typed Choice, Noul and Score questions, plus an agent skill for coding agents.

Web playground for Jev: preset scenarios, editable state and typed questions, via OpenRouter, Vercel AI Gateway or TypeSafe.

Unofficial, zero-dependency Go client (v1.0.0) porting the official SDK concepts so Go services can call Jev without a sidecar.

Curated directory of active Jev integrations, compatible models, SDKs, agent tools and research, filtered by activity and stars.

.NET library that turns C# enums into Jev Choice questions and returns real enum values with probabilities and confidence.

Chinese curated list of the Jev ecosystem with official resources, SDKs, apps, agent tools, reproductions, evaluations and Chinese guides.

Code search CLI and agent skill (jg) where Jev judges relevance across folders, files and declarations to return excerpts.

Local social research agent: Jev picks each bounded Instagram, TikTok or LinkedIn step and socai CLI runs it in your Chrome.

Graph-database-agnostic GraphRAG framework where swappable Laya or Jev decisions score edges, route intents and gate hallucinations.

Community Java 17 SDK for Jev with typed Ask declarations, enum-backed choices and a Spring Boot starter.

PowerShell module that builds Jev Noul, Choice and Score questions and returns answers as pipeline-friendly properties.

MCP server exposing a judge tool for typed noul, choice and score questions over JSON state, backed by Jev.

Rust agent-facing CLI built on the unofficial jev-sdk crate: predict, choose and score with strict stdout and meaningful exit codes.

Zero-dependency Python SDK for deterministic gates over calibrated model answers, with LangChain, OpenAI and Claude agent hooks.

Rust library and CLI for compound decisions: ask Jev small questions, combine answers with rules in a YAML/JSON decision graph.

OpenAI-compatible LLM router across 80+ providers with an optional jev-auto mode that picks the model using calibrated probabilities.

Small TypeScript client with tagged-template helpers to ask Jev yes/no, choice and score questions about your data in one request.

Orchvia: local engine with TS and Python SDKs that runs Claude Code and Codex agents as a team, routing tasks by code and typed decisions.

Vercel's AI SDK for Python, in public beta, listed for carrying Jev through its evaluation operation and AI Gateway examples.

Swift package for typed decisions (probability, choice, score) over local MLX or Core AI models, Clef decision heads, or the Jev API.

Browser extension and MCP server where Aside observes the page and Jev picks the next action from defined candidates.

Zero-dependency Python CLI that hands small semantic judgments and verbatim passage selection to Jev; the calling agent keeps authority.

Self-hosted Rust LLM gateway that puts OpenAI, Anthropic and Jev-style /v1/systemone backends behind one endpoint with load balancing.

Claude Code plugin and Python CLI that hands judgments repeated over many items to Jev, with redaction, rate limits and a pilot run.

Stop hook for Claude Code and Codex that refuses 'done' until a check passes after the last edit; Jev advises but never causes a block.

Unofficial portable Clojure SDK for the TypeSafe System One API, with question constructors, validation, retries and JVM or Jolt backends.

Standard-library MCP server giving Codex advisory Jev tools for role and resource selection, with local validation and 85 offline tests.

Precision-first RAG service where Jev routes queries, triages each retrieved chunk and verifies every claim before an answer is released.

Composable Python toolkit for Jev: question builders, confidence gates, batch evaluator, calibration, CLI, MCP server and agent skill.

Local MCP server that lets an agent delegate a decision to Jev and get a recommended choice with percentages.