Jev-powered: Tool-call checks for coding Agents that assess operation risk, user intent and prompt-injection signals.
Real data. Real impact.
Emerging
Developers
git clone https://github.com/leepokai/jev-guard.gitPer week
Excellent
One command unlocks capabilities that would take hours to build.
Tool-call checks for coding Agents that assess operation risk, user intent and prompt-injection signals.
Jev evaluates tool inputs or outputs in session context; local rules allow, warn or block.
Adds review points around Agent tools, with behavior depending on the host client.
Not a sandbox replacement. API failures allow operations by default and confirmation support varies by client; no penetration or end-to-end testing here.
Jev is TypeSafe AI's System One decision model: it returns typed scores and choices (not free text), so agents can route, filter and gate at low latency and cost.
Source: leepokai/jev-guard — 27 stars, MIT. Listed by Awesome Jev.
MIT
4,600+ AI skills, agents & workflows. Install in 60 seconds. Part of the Torly.ai family.
© 2026 Torly.ai. All rights reserved.