A loop where a coding agent writes, a review comes back, and Jev decides if it is safe to merge.
@manvendersingh21AgentGate is a safety loop for a coding agent. One agent writes code from an issue. CodeRabbit reviews it. Jev decides whether it is safe to merge. If not, another agent tries a fix, and the loop repeats until Jev approves or the attempts run out.
It was built at the San Francisco Jev hackathon.
A Claude Code hook that asks Jev about every shell command and blocks the ones that would delete something that matters.
Jev
Python
Claude CodeScores each action an agent wants to take against the job it was given: allow, ask a person, or block.
JevPythonClaude Code
CodexChecks each tool call a coding agent is about to run, and only the unclear ones go further.
JevClaude CodeA demo gate for an agent that is about to act. With no Jev key, it uses a stand-in judge and still runs.
Jev
TypeScriptShows a captured page crash and asks Jev who owns it, whether a contract broke, and how far it spreads.
JevTypeScript
ReactA Python experiment where Jev picks each actor's next legal move, and the simulation applies it.
JevPython
CodeRabbit participant
