Jev in production › Agent guardrails and approvals

dsh-jev-interceptor

Vendor claims Jev classifies risk, irreversibility and injection-suspicion for every DeepSeek Harness tool call at about $0.00002 per request (author).

Open on GitHub ↗

$0.00002 per requestmeasured, as published by the source
Use
Agent guardrails and approvals
Industry
Security
Form
Open-source tool
Stage
Announced
Plugs into
DeepSeek Harness
Listed
2026-09-25
Found via
github
Repository
AskTheWay/dsh-jev-interceptor
Stars
27
Forks
3
Last push
2026-10-07
Language
TypeScript
License
MIT
dsh-jev-interceptor screenshot
imgs/screenshot-01.jpeg in the AskTheWay/dsh-jev-interceptor README, MIT; shown from GitHub.

The README opens with

⚡ Millisecond judgement for every tool call and every recalled message — for about two millionths of a dollar each. Your agent's most expensive habits: asking a poetry-writing LLM yes/no questions, and amputating your context by age. This plugin wires Jev — the non-generative "System One" model that broke everyone's feed — into the decision points of DeepSeek Harness where an LLM is overkill and rules are blind.

What it does, in one breath: before a tool call runs, Jev classifies its risk, irreversibility, task-fit, and injection-suspicion in one ~$0.00002 request — confident high-risk calls get denied, medium ones escalate to a human, and clearly-granted reversible ones stop wasting your clicks on approval dialogs. And when an @session snapshot...

Badge

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

Listed in Jev in production

Also used for agent guardrails and approvals