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.
More from coding & agent
- Salesforce launches Trusted Enterprise AI Harness to unify agent context, governance and security — emmanuelvivier · 2026-09-18
- Running Codex, Claude and Pi Agents Safely: gVisor Sandboxes Plus tart macOS VMs — craigbalding · 2026-09-18
- EvalSeal: open-source tool shows LLM judges flip verdicts on 5 of 20 borderline eval cases — Fit_Fortune953 · 2026-09-18
- Armin Ronacher floats replacing MCP with codemode + OpenAPI + RAG over API docs — mitsuhiko · 2026-09-18
- Obsidian Starter Kit v4 ships with MCP server, osk-cli and ~375 specialized AI skills — dSebastien · 2026-09-18
- Retrying LLM Requests Isn't Always Safe: Gateway Policies for Partial Streams and Side Effects — Rama_Surasani_ · 2026-09-18