jevbooks

← All projects

jevlogs

reachjalil/jevlogs

Score OpenTelemetry logs before expensive LLM analysis.

What it is

Jev Logs is a local OpenTelemetry log receiver that scores each log's diagnostic value, priority, and routing decision so that costly reasoning-model analysis is only spent on records worth investigating.

How it uses Jev

For each record, Jev returns diagnostic value, priority, and actionable probability from the log body and severity. The decision drives routing: low-value events can skip a separate LLM-analysis branch, while errors, protected, ambiguous, or failed records stay eligible. Results appear as jev.* attributes and an onLog decision callback.

Primitives:choicescore

Technique worth stealing

Annotate logs with jev.* routing attributes in place, so a separate LLM-analysis branch only sees records worth spending on.

Try it

Add jevlogs.config.json at your project root, then run npx jevlogs@latest --live.

View on GitHub

judged by Jevjev-1.13.0

Evidence

Each line is one question put to Jev about the README. ≥ 0.60 reads as yes, ≤ 0.40 as no; in between Jev is not making a call.

  • Jev-centricyes0.90
  • Shows a System One patternno0.20
  • Handles uncertaintyno0.08
  • Measuredno0.06
  • Runnableyes0.94
  • Worth recommendingunclear0.40
  • Model replicano0.04
  • Problem scopescore on a 0–2 scale1.51
  • About Jevyes0.97

Signals by Jev jev-1.13.0, card written by DeepSeek V4.1 Flash from the README on 20 Sept 2026.