safer-with-jev GitHub avatar by andrelandgraf

andrelandgraf /

Security & Guardrails

safer-with-jev

An HTTP inspection gateway that checks request content with Jev before optionally forwarding it to an HTTPS destination.

License: MITLanguage: TypeScriptLast push: 9/18/2026#security-guardrails#typed-decisions

What Jev Does in this Architecture

Jev judges prompt injection or unsafe content; local rules forward, flag or block the request.

Key Architecture Benefit

Adds an inspectable content check ahead of an existing HTTP service.

Review & Benchmark Note: Renamed to safer-with-jev. The code implements content checks, not a guarantee of safety or zero latency.
Clone Repository
git clone https://github.com/andrelandgraf/safer-with-jev.git

Inspect on GitHub

Check out the upstream repository README, issues, and commit log.

andrelandgraf/safer-with-jev

Architecture Category

Security & Guardrails

Real-time safety guardrails, prompt injection detection, and moderation gates.

View all in this category →

Related Projects in Security & Guardrails

pi-jev repository icon by y0usaf

y0usaf

pi-jev

70
Security & GuardrailsMITTypeScript

A Pi extension that flags tool risks before execution and checks output for secrets and failure types.

What Jev does here

Jev scores destructive actions, scope and output risks; configuration chooses warnings or confirmation.

Defaults to shadow mode and fails open on API errors; it is not a standalone security boundary.

#security-guardrails#coding-agents
35 evidence links
Inspect details
Security & GuardrailsMITTypeScript

Adds rule checks to Pi commands and file operations, then uses Jev to assess cases that need further judgment.

What Jev does here

Local rules handle explicit denies and allows before Jev assesses authorization and risk for bash, write, and edit.

Keeps policy and decision records available for adjusting operation gates.

#security-guardrails#coding-agents
22 evidence links
Inspect details
jev-judgment repository icon by HyunjunJeon

HyunjunJeon

jev-judgment

2
Security & GuardrailsMITPython

Adds judgment checks for authorization, operation risk, and failure causes to coding Agents.

What Jev does here

Uses conversation and command results to assess whether to ask the user, whether an action exceeds scope, and whether to retry.

Makes checkpoints that may require user confirmation explicit.

#security-guardrails#coding-agents
2 evidence links
Inspect details