All decision model projects

Ruby gem making semantic checks ordinary methods: feels?, decide and score on model fields, with Rails validations.

npm CLI that screens large agent tool outputs with Jev, returning compact typed decisions and IDs while originals stay recoverable.

Governance proxy between Jev or local Laya and agents that turns probabilities into allow, ask, deny, keep, truncate or drop actions.

Session-aware OpenAI-compatible gateway that routes chat requests by task type, scale and rigor, optionally via Jev Choice questions.

Unofficial dependency-free Go SDK and interactive CLI for Jev via TypeSafe or Vercel AI Gateway, with an agent skill.

Unofficial Go client for Jev with YesNo, OneOf and Levels constructors and typed answer accessors.

Minimal unofficial Go SDK for Jev supporting Noul, Choice, Score, structured inputs and model listing.

Go SDK for Jev with typed question and answer structs, client options and structured API errors.

Dependency-free Go client for Jev mirroring the official Python and JavaScript SDK features, with grouped answer helpers.

TypeScript guardrail library plus DeepSeek Harness plugin screening prompts, tool calls, results, responses and claims with Jev.

Bun harness that runs Jev over datasets via OpenRouter, streams JSONL answers, and checks calibration, stability and regressions.

Per-turn router: one ~350 ms Jev call picks model tier, effort, tools and skill, with a hard deadline and regex fallback.

Idiomatic Java 17+ SDK for Jev with builders for structured instructions, rubric-bounded Choice options and Score levels.

Unofficial dependency-free Java 21 client for Jev with typed Choice, Score and Noul answers and confidence helpers.

Multi-provider Java SDK for Jev via TypeSafe, OpenRouter, Vercel or Cloudflare, plus OpenAI Decisions and Spring Boot support.

Unofficial Kotlin Multiplatform SDK for Jev on Android, iOS and JVM, built on Ktor and kotlinx.serialization.

Python MCP server wrapping Jev as classify, score, check, match and screen tools with confidence on every answer.

Local MCP server putting Jev in the coding loop: route next steps, pick prepared tool calls, review patches and verify claims.

Node MCP server with a dozen fail-closed Jev judgment tools: verify, screen, find, rerank, classify, extract, review and gate.

Go model-routing gateway for OpenAI and Anthropic clients where Jev picks a model from editable model cards, with CLI and dashboard.

Spanish compliance triage: clauses extracted deterministically, then Jev labels each obligation, risk or no action.

Python tap SDK for Android, iOS and HarmonyOS where multimodal Jev picks a numbered on-screen candidate and the SDK taps it.

Framework-agnostic PHP SDK for TypeSafe's System One API with typed Noul, Choice and Score answers, PSR-18 and Laravel support.

CLI that sends text to Jev for 13 PII-category yes/no checks and a sensitivity score, then locates spans with regex and segmentation.

Python SDK for typed Jev judgments that masks state before sending and returns 'undecided' instead of raising on any failure.

PRAXEON runtime supervisor for autonomous agents: actions are checked by policy, a LAYA or TypeSafe semantic judge, signed and sandboxed.

Grep-shaped Rust CLI for coding agents: BM25 recall plus Jev Noul window checks and a listwise Choice return path:line results with scores.

Dependency-free Go client for Jev Noul, Choice and Score questions that rejects any label or level the question never offered.

Type-safe Java 21 client for Jev's System One API using sealed interfaces and records so invalid requests fail at compile time.

LangChain and LangGraph middleware that screens tool outputs for prompt injection and gates risky tool calls with Jev.