Skip to content

Dsh Jev — noetion

DeepSeek Harness bundle that registers a jev_ask tool plus a jev skill so a DSH agent can send mixed Noul, Choice, and Score questions to Jev.

Stars
3
Language
TypeScript
License
MIT
Published by
Community
Author
noetion
Last verified
Oct 2026

This is one of several Jev listings for the same project. The canonical entry is Dsh Jev — buberlo.

About this project

dsh-jev is a DeepSeek Harness bundle that registers the jevask tool. A DSH agent on a profile that loads it can send typed noul, choice, and score questions to TypeSafe Jev. Jev is TypeSafe's System One model. It returns structured answers and does not generate chat or code. This package is version 0.1.0. It targets DSH 0.1.5-rc.2 from the npm next dist-tag, Node 22.19 or later on the 22.x line or Node 24 and later, and a TypeSafe API key. Pin a commit so a later push cannot change what you run.

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

Highlights

  • Session LLM decides when to call; the plugin never forces Jev into the loop.
  • One call mixes question types over the same state and returns TypeSafe JSON with probabilities and confidence.
  • Optional cordis.yml model, endpoint, and apiKeyEnv settings default to jev-latest and TYPESAFE_API_KEY.
  • Typecheck, test, build, and adopt-check run on mock transport without a key; live and boot proofs cover real use.

Watch out

Version 0.1.0 targets DSH 0.1.5-rc.2 from the npm next tag with Node 22.19 or later on 22.x or Node 24 and later. Pin a commit SHA, allow the prepare build in pnpm-workspace.yaml, and never put secrets in state since every call posts state to the API. Jev returns typed answers and cannot stream, so it cannot be an LLM adapter. 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

36GitHub stars
Pi extension that strips the full Agent Skills catalog from every request and loads only the skills a Jev ranking call judges relevant.
Jev Agents & MCP#community#jevbest#catalog-import
102GitHub stars
Behavioral code search that asks Jev to score repository fragments for a plain-language question and returns exact excerpts with paths and lines.
Jev Agents & MCP#community#jevbest#catalog-import
35GitHub stars
Diff-aware test selector that sends the git diff to Jev with one question per test, then prints the native filter flags and hands them to vitest, jest, node, bun, Playwright, cargo, or go test.
Jev Agents & MCP#community#jevbest#catalog-import
7GitHub stars
MCP server exposing Jev Choice, Score, Noul, batched ask, file-reading triage, and model listing as typed tools with full probability distributions.
Jev Agents & MCP#community#jevbest#catalog-import
5GitHub stars
A Claude Code function hook that sends AskUserQuestion dialogs to Jev and draws a probability per option above the dialog, so you still choose while seeing how confident the model is.
Jev Agents & MCP#community#jevbest#catalog-import
3GitHub stars
An MCP server built around measuring questions rather than asking them: jev_ask prototypes wording, jev_eval sweeps thresholds against labeled data, jev_map applies the winner over a workload.
Jev Agents & MCP#community#jevbest#catalog-import
Back to all resources

From the Jev community

Posts from builders shipping with Jev right now.

Follow @typesafeai