Open-source PR Review Lab spins up sandboxes to compare GPT 5.6 Luna vs Jev reviewers

aniketmaurya · x · 2026-09-18

Developer aniketmaurya built an open-source PR review experiment using CelestoAI's Jev + Celesto sandboxes (943 stars on GitHub): paste a public PR URL, an agent spins up a test environment, runs checks, then compares GPT 5.6 Luna and Jev as reviewers on identical evidence.

The code ships as the pr-review-jev example in the Celesto repo, supporting local Celesto OSS or Celesto Cloud; requires Python 3.12+ and a sandbox backend, with API keys never sent into repository sandboxes.

Original post →

More from coding & agent

coding & agent channel →