Vera launches gyms, benchmarks and agents for cloud infrastructure operations
tianyin_xu · x · 2026-11-10
Founded by @angchen0's research group, Vera launches vera-gym (emulators of AWS/GCP/Azure for safe agent practice), CloudOpsBench (end-state-graded agent benchmarks) and vera-agents. Demo shows an agent going from 41/60 to 58/60 after gym training. Leaderboard tops claude-fable-5-1 + claude-code, followed by gpt-6-astra + codex. Team presenting at KubeCon.
More from coding & agent
- The dialectics of AI coding: LLMs can't write prod code unsupervised — neither can humans — ShenRaphael · 2026-11-10
- Mnemos memory system gives Claude cross-session mood continuity, dev claims — RileyRalmuto · 2026-11-10
- AutoVend benchmark: 4 of 5 LLM agents lose to a rule-based baseline running 20 vending machines — Qiming Shi · 2026-11-10
- LangChain on Eval-Driven Development: TDD-style methodology for building AI agents — hwchase17 · 2026-11-10
- Chrome 153 ships native tab recorder: 120fps 4K AV1 capture, no ffmpeg needed — Vjeux · 2026-11-10
- Ex-DeepMind researcher envisions mapping 2,000 corporate workflows for agent automation — gabriel1 · 2026-11-10