COMMUNITY OBSERVEDMetric claims: AUTHOR REPORTEDSOURCE AUDITEDπŸ€– Jev Agent

Auto-Guard for Coding Agent Tool Calls

Jev scores a proposed tool call and the user's request before code allows, escalates or blocks execution.

Overview & Result

Roshan Chandna's open-source Auto-Guard sends proposed coding-agent tool calls and the user request to Jev; code maps typed risk, scope and sensitivity answers into allow, human approval or block.

How Jev fits in the loop

  1. A coding agent proposes a tool call before it runs.
  2. Jev evaluates destructive potential, task scope, sensitivity, action class and risk.
  3. Local policy lets it run, asks a human, or blocks it; native agent permissions still apply.

How to reproduce

  1. Read the project's public README and choose a supported coding-agent hook.
  2. Install agent-autoguard and configure a supported API key as documented.
  3. Run the project's sample check and inspect allow, escalate and block outputs; keep normal agent permissions enabled.

Why this build matters

A concrete example of bounded Jev decisions placed at a consequential tool boundary, with code, demo and an author-run evaluation.

Limitations

  • Author-run holdout tests are small and not independently reproduced here.
  • The repository states Auto-Guard is a filter, not a sandbox, and can miss a risky action.
  • The guard cannot control a command after its pre-execution check.

Patterns