DSH Hub
dsh-jev-workspace cover

buberlo/dsh-jev

dsh-jev-workspace

ToolWorkflow25 GitHub stars· updated 2026-09-23

Jev-powered decision layer for DeepSeek Harness

Install

npx @deepseek-ai/dsh plugin --profile <name> add @buberlo/[email protected]

Restart `dsh web` after install. Bundle APIs can change during the developer preview.

README badge

dsh-jev-workspace DSH Hub badge
[![DSH Hub](https://dshhub.dev/badge/dsh-jev.svg)](https://dshhub.dev/plugins/dsh-jev)

Paste this into your README. The star count updates with every catalog sync.

From the README

Excerpt from buberlo/dsh-jev, cleaned of badges and images.

dsh-jev

The Jev decision layer for DeepSeek Harness (DSH).

DSH runs the agent. TypeSafe Jev makes the small, fast decisions. Your code decides what the answers mean.

Watch the 66-second Kubernetes troubleshooting demo: healthy pods, broken connections after a rollout. The agent traces Ingress → Service → pods and repairs the network path. Jev's site policy gates a broad “allow all traffic” shortcut, so the portal can recover while PostgreSQL stays isolated. The same freshly recorded model calls run through both harnesses against a real, disposable Kubernetes cluster, with live Jev assessments. Clearly labeled replay with neural narration; no live replanning in this comparison. Video · Captions · Method, all runs and limits. The replay also shows one harmless reset being blocked—a documented false positive.

   user task
       │
       ▼
 ┌───────────────────────────────────────────────────────────┐
 │  DeepSeek Harness agent loop                              │
 │  planning · tools · execution · sessions                  │
 │                                                           │
 │   pre-step ──▶ Jev: which tools are relevant?   → restrict│
 │   tool call ──▶ Jev: is this call safe to run?  → ask/hold│
 │   result ─────▶ deterministic loop guard (no model)       │
 │   request ────▶ Jev: which model route fits?    → route   │
 └───────────────────────────────────────────────────────────┘
       │
       ▼
  TypeSafe Jev (System One)  ← choice · score · noul

No Jev call is planned by the LLM, no model output becomes an explanation, and no model answer can widen a permission. Jev only ever narrows or gates.

At a glance

Packages@buberlo/jev-core (harness-independent) · @buberlo/dsh-jev (DSH plugin/bundle)
npmnpm view 2026-09-23 lists 0.1.0, 0.1.2, 0.1.3, and 0.1.4. Dist-tag latest is 0.1.4 for both packages. Workspace is 0.1.4. npm install @buberlo/[email protected] resolves @buberlo/jev-core@^0.1.4. Do not install @buberlo/[email protected] or @0.1.3 (literal workspace:^, EUNSUPPORTEDPROTOCOL). 0.1.3 was abandoned after a staged-version conflict (E409).
Verified DSH0.1.6-alpha.2 (commit ddefc45), @deepseek-ai/cordis 4.0.2
Verified TypeSafe SDK@typesafe-ai/sdk 0.6.0
Defaultsprovider: mock, mode: shadow — offline, no behavior change
Tests147 (85 core + 62 DSH integration) · 25 evaluation fixtures plus the on-prem support set
Live APIimplemented, requires an explicit key; not part of any default
LicenseMIT

What this is — and is not

Is: a plugin that binds Jev to real DSH extension points, plus a reusable decision core you can embed in any application (games, search, MCP routers).

Is not: a Jev training or hosting project, a DSH fork, a dashboard, a database, or an MCP platform. It never auto-applies a model suggestion, never caches approvals, and never sends repositories, logs, or transcripts by default.

Try it in 60 seconds

Everything below runs offline with synthetic answers. No key, no network.

git clone https://github.com/buberlo/dsh-jev
cd dsh-jev
pnpm install
pnpm build

…

Related plugins