agent-gate-loop

Reusable GitHub Action: agent fix loop gated by checks, an AI reviewer, and TypeSafe Jev

How it uses Jev

1. Guards. No edits to protected paths, no deleted tests, a size limit, and at least one change. 2. Your checks. Your own typecheck, lint and test commands. 3. Reviewer. A separate, read-only Claude session that lists findings. 4. Jev (TypeSafe). Checks each finding, and asks whether the change does what the issue asked, whether it touches unrelated code, and how good the tests are.

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README.

Keep exploring

Similar to agent-gate-loop

Browse all
check-risk project preview
Agent tooling
A CLI and GitHub Action that assesses code-change risk using deterministic rules and TypeSafe Jev, recommending checks and reviewers before merge.
omp-typesafe project preview
Agent tooling
TypeSafe AI (Jev) adversarial reviewer and typesafe_ask tool for the omp coding agent
typesafe-migration-guard project preview
Automated database migration safety reviewer powered by TypeSafe AI (Jev System One model)
typesafe-ui project preview
Integrations
shadcn-style reusable components and blocks for using TypeSafe AI.
killmyidea project preview
Demos & playgrounds
Describe your startup idea. Jev decides: kill it, fix it or ship it.
unclutter project preview
Browser & computer use
WXT browser extension: Jev-powered page clutter removal with reusable template rules.
jev-acp project preview
Integrations
Use Jev's Choice, Score, and Noul decisions from ACP-compatible clients, with guided input, reusable templates, and probability displays.
siege project preview
Games & simulations
SIEGE: 200 people vs one agent. A typed action gate (TypeSafe System One) that learns from every breach, evaluated by W&B Weave, hardened by a defender loop. Built at CoreWeave Hacks: Agent Loops 2026.
agent-fastpath project preview
Browser & computer use
Jev MCP server: a decision layer for coding agents, built on TypeSafe Jev (System One model). Ship gates, risk checks, file triage that keeps files out of context, and a safe headless browser, with calibrated confidence. For Claude Code, Codex, Cursor.