jev-guard
leepokai
Tool-call checks for coding Agents that assess operation risk, user intent and prompt-injection signals.
- License
- MIT
- GitHub Stars
- 8
- Source reviewed
- 2026-09-19
Where Jev makes a decision
Jev evaluates tool inputs or outputs in session context; local rules allow, warn or block.
What this project offers
Adds review points around Agent tools, with behavior depending on the host client.
Review scope
Not a sandbox replacement. API failures allow operations by default and confirmation support varies by client; no penetration or end-to-end testing here.
Sources and implementation
Related projects
safer-with-jev
andrelandgraf · Security & Guardrails
An HTTP inspection gateway that checks request content with Jev before optionally forwarding it to an HTTPS destination.
pi-jev
y0usaf · Security & Guardrails
A Pi extension that flags tool risks before execution and checks output for secrets and failure types.
pi-jev-auto-mode
jomatsu · Security & Guardrails
Adds rule checks to Pi commands and file operations, then uses Jev to assess cases that need further judgment.
jev-judgment
HyunjunJeon · Security & Guardrails
Adds judgment checks for authorization, operation risk, and failure causes to coding Agents.