Skip to content

TypeSafe Jev Bridge

Zero-dependency Node bridge that exposes Jev through OpenAI-style chat and responses endpoints with streaming, plus a CLI, a code-audit tool, and an auto-fix loop.

Stars
5
Language
JavaScript
Published by
Community
Author
RevocGG
Last verified
Oct 2026

About this project

Most AI models generate text. Jev doesn't — it answers typed questions with calibrated probabilities: a yes/no likelihood (noul), a choice among options, or a score on a rubric you define. You give it state (any text or file) plus questions; it gives your code answers it can act on. It's fast and cheap, and it says "I'm not sure" when it genuinely is — instead of making something up.

Quoted from the project's README. Read the full README.

Highlights

  • Translates chat completions and responses requests, including streaming, into decision calls.
  • CLI asks choice, score, and yes-or-no questions with confidence and distributions shown.
  • Loopback-only service with origin allow-list, optional shared token, and secret redaction.
  • Works with routers, IDE agents, or any OpenAI SDK without global installs.

Watch out

This is an unofficial community bridge, and file-sending commands transmit content to the TypeSafe API. Copy reviewed against the repository README on 2026-10-04, not from running it.

Questions about this entry

Short answers drawn from the linked project or page.

More Jev resources like this

45GitHub stars
Go SDK plus a pipeline-friendly CLI for typed decisions, covering single questions, batched question maps, retries, and line-oriented filtering over stdin.
Jev Repos & SDKs#community#jevbest#catalog-import
2GitHub stars
An MCP server packaged as both a Codex and a Claude Code plugin, exposing eight read-only tools that turn Jev probabilities into proceed/review recommendations for routing, ranking, extraction and claim checks.
Jev Agents & MCP#community#awesomejev#catalog-import
4GitHub stars
A DSH plugin, published to npm, that registers one agent tool, jev_decide, so a coding agent can ask TypeSafe's Jev a typed question and get a calibrated probability instead of guessing from intuition.
Jev Practices & Patterns#community#awesomejev#catalog-import
1GitHub stars
Community Go client for the TypeSafe API: context-aware SystemOne calls, Choice, Noul and Score constructors, scoped functional options, typed errors carrying RFC 6901 field paths, and standard-library-only runtime code. Requires Go 1.24.
Jev Repos & SDKs#community#awesomejev#catalog-import
4GitHub stars
TypeScript router that spends one Jev call deciding how an agent turn should run — model tier, effort budget, which tools are on offer and which skill applies — then your own harness runs the turn on whatever provider it already talks to.
Jev Repos & SDKs#community#awesomejev#catalog-import
1GitHub stars
C# client for Jev, TypeSafe AI's System One model. Typed Noul, Choice and Score questions go out with one state in a single round trip and come back with a value, a probability distribution and a confidence number. Choice questions can be built from an enum, so the compiler finds the switch branch you forgot.
Jev Repos & SDKs#community#awesomejev#catalog-import

From the Jev guides

Original write-ups on what this entry is for.

Closed weights have not stopped the ecosystem from rebuilding the shape in the open. API-compatible servers, retrained heads on small models, and inference-time tricks that skip generation entirely.
Jev Repos & SDKs#open-models#research#local
Read article
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai