Jev in production › Agent guardrails and approvals

deepseek-harness-jev (luobosibing2)

A DeepSeek Harness plugin uses Jev for agent and skill selection, supervision, corrections and approvals across 11 togglable features, tested on DSH 0.1.7-rc.2 (author).

Open on GitHub ↗

The source publishes no measured number.
Use
Agent guardrails and approvals
Industry
Developer tools
Form
Open-source tool
Stage
Beta
Plugs into
DeepSeek Harness
Listed
2026-09-29
Found via
github
Repository
luobosibing2/dsh-jev-plugin
Stars
203
Forks
18
Last push
2026-10-11
Language
JavaScript
License
MIT
deepseek-harness-jev (luobosibing2) screenshot
docs/images/jev-feature-toggles.png in the luobosibing2/dsh-jev-plugin README, MIT; shown from GitHub.

The README opens with

Native DeepSeek Harness (DSH) plugin with Jev or Luna Decisions as its judgment model.

deepseek-harness-jev connects DeepSeek Harness (DSH) to Jev by TypeSafe AI for agent skill and file selection, task supervision, shared-finding corrections, tool-output filtering, single-operation approval assistance, and historical stage navigation. Its 12 features are individually configurable from one Jev settings page and are all disabled by default.

The main model continues to plan, generate answers, and call native tools. Enabled features use the saved Jev or Luna Decisions connection at DSH extension points for skill catalogs, agent lifecycle, tool results, and approvals, then apply results according to each feature. DSH configures the main model...

Badge

For the project's own README, linking back here:

Listed in Jev in production

Also used for agent guardrails and approvals