openjev

What it is

Your opencode agent makes a lot of small decisions. OpenJev makes them faster and cheaper, and it tells you when it isn't sure.

What the README says it does

• Safety checks. Before the agent runs rm -rf or reads .env, ask whether the action is destructive or irreversible. If the answer is a confident yes, the agent stops and asks you.
• Choosing a tool or model. Decide which tool fits a request, or whether a task needs the large, expensive model or a small, fast one.
• Review verdicts. Approve, request changes, or block a PR, with a confidence bar that you set.
• Triage. Get the team, urgency, and severity for an issue in one call.
• Scoring. Rate risk, quality, or severity on a scale you define.

From the project’s README.

Getting started

From the README:

// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "plugin": ["opencode-openjev"]

Where the decision sits

openjev calls the hosted decision API rather than running its own weights. That keeps the project small and means its behaviour moves whenever the vendor ships a new model version. It also means an API key and a network round trip sit in the path of every decision.

Models it references: Jev, jev.

How active it is

Created 2026-09-24, last pushed 2026-09-25, 12 stars and 0 forks when we read it on 2026-11-02. Everything in this category is weeks old at most, so a stale push date means something different here than it would on a mature project. Check the repository before you depend on it.