jevflow

Probabilistic AI decisions as composable backend primitives — typed judgments (noul/score/choice), deterministic thresholds, and explainable workflows. Powered by TypeSafe's Jev, provider-agnostic.

How it uses Jev

JevFlow lets backend developers define typed probabilistic judgments (yes/no, scoring, classification) and use them inside normal workflows — with explicit thresholds , deterministic policy , and full explainability . It defaults to TypeSafe's Jev/System One model as the AI provider, but the provider is a replaceable seam, not a hard dependency.

Getting started

Set your TypeSafe API key (or pass it to the provider directly):

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to jevflow

Browse all
ai-provider-for-jev project preview
Connect WordPress to TypeSafe's Jev System One model for structured decisions (choice, score, noul).
nlgrep project preview
Applications
TypeScript CLI that finds code, docs, logs, and text by natural-language conditions using Jev Noul judgments, with probability thresholds, source lines, and cached results.
typesafe-cli (y0usaf) project preview
Ask Jev typed questions from the shell: noul, choice, and score answers as numbers, not prose
zcode-jev project preview
Agent tooling
Typed judgment layer for coding agents — gates from PRD to ship. Jev-ready, provider-agnostic.
jev-recipes project preview
Agent tooling
80+ composable TypeScript recipes powered by Jev for AI agents, retrieval, answer verification, and conversation workflows.
typesafe-demo-mcp project preview
Agent tooling
MCP server exposing TypeSafe System One judgments (noul, choice, score) as agent tools
tenbin project preview
Benchmarks & research
MCP server and agent skill for the TypeSafe AI System One API (Jev): decompose a judgment into Choice / Score / Noul questions, lint them, measure on labelled data, and put calibrated thresholds in code
jev-resume-match project preview
Demos & playgrounds
Score how well a resume matches a job description using Jev (TypeSafe AI). Next.js app that returns typed, explainable match scores instead of generated text.
OpenJev (zhangcy122) project preview
Jev alternatives & open source
OpenJev: Open-source alternative to TypeSafe Jev. Typed probabilistic decision API (Choice, Noul, Score) powered by open LLMs & constrained logprob calibration.