Jev directory
CommunityJev Integrations & Adapters
@mlola/decision-jev
npm package providing the TypeSafe Jev fast path for the MLola Browser Runtime: one request per decision cycle carrying the operation head plus speculative target heads, with responses validated before anything executes. Also ships planner and text adapters for OpenAI-compatible endpoints.
- Reading time
- 1 min
- Published by
- Community
- Added
- Nov 2026
Highlights
- Fast-path decision provider for the MLola Browser Runtime.
- Sends one request per decision cycle with the operation head plus speculative target heads.
- Validates responses before anything can execute.
- Ships planner and text adapters for any OpenAI-compatible endpoint.
- Includes deterministic offline baselines under /testing, such as ScriptedDecisionProvider.
Questions about this entry
Short answers drawn from the linked project or page.
It is the TypeSafe Jev fast path for the MLola Browser Runtime, plus planner and text adapters for OpenAI-compatible endpoints and deterministic offline baselines used by tests and demos.
It sends one request per decision cycle that carries the operation head together with speculative target heads, rather than issuing separate calls for each candidate target.
Responses are validated before anything can execute, so an invalid or malformed decision does not reach the runtime as an action.
The planner and text adapters target any OpenAI-compatible endpoint, so they are not tied to a single provider.
The package exposes deterministic offline baselines under the /testing entry point, including ScriptedDecisionProvider, which can stand in for live decisions in tests and demos.
It exports JevDecisionProvider, buildQuestions, and renderDecisionState from the main entry, and ScriptedDecisionProvider from @mlola/decision-jev/testing.
It reads a TYPESAFE_API_KEY environment variable, with keys obtained from typesafe.ai, and it is published on npm as @mlola/decision-jev.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
YouTube: CJ from Syntax demos browser use, classification, code review, a model router, and a chat bot with no LLM.
X: Text-to-screenshot (Malay Vasa)
Facebook: Intake Router keeps diagnosis out of the answer space at the front desk.
FacebookClinicnotes
X: Google's MediaPipe Decision Maker, tested in the browser
More Jev resources like this
First-party TypeSafe AI decision provider for Standard Agents. It implements DecisionProviderInterface with kind 'decision' and decide(), sending explicit context and multiple independent questions to Jev in one request.
Jev Integrations & Adapters#typescript#sdk#agents
Community
LangChain.js integration for TypeSafe System One models. It wraps the jev classifier as a Runnable that returns typed choice, score, and noul answers with calibrated probabilities, plus agent middleware for model routing and tool gating.
Jev Integrations & Adapters#typescript#sdk#routing
Community
Optional TypeSafe AI Jev decision provider for the Zhin chat framework. Evaluates named Choice, Score and Noul questions through a plugin-managed client, returning labels, distributions and confidence without generating chat replies or granting tool permissions.
Jev Integrations & Adapters#typescript#sdk#routing
Community
npm adapter that adds optional TypeSafe Jev system one decisions to AgentRun DSL workflows. createJevRunner turns judge, pick, sift and route steps into typed Choice, Noul and Score answers, with retries, timeouts and OpenRouter support.
Jev Integrations & Adapters#typescript#sdk#agents
Community
NestJS module that adds TypeSafe AI decisions to Loopstack workflows. It asks yes/no, choice, and score questions about workflow or agent state and returns probabilities, confidence values, and a legend per answer.
Jev Integrations & Adapters#typescript#sdk#classification
Community
npm package that decides what happens to each new fact in an agent memory store: add, update, supersede, or skip. It calls TypeSafe Jev for typed answers with probabilities and ships as part of Oort, open-source memory for AI agents. Apache-2.0.
Jev Integrations & Adapters#typescript#agents#sdk
Community
From the Jev guides
Original write-ups on what this entry is for.
From the Jev AI model community
Posts from builders shipping with Jev right now.