Engineer shares how he runs infra ops with Codex agents
kuza55 · x · 2026-10-24
Engineer kuza55 responded to a question about using agents for ongoing ops with concrete practice: he used Codex for all initial performance tuning and monitoring setup, and built patched containers for many OSS projects that were slow to respond to the eMudhra security issue. His takeaway: "This is all a lot easier with agents" — not fully autonomous ops, but agents taking a stab at IaC-defined infrastructure with human correction.
More from coding & agent
- Flywheel ships local UI: your graphs on your own machine, no account needed — tensorqt · 2026-10-25
- Five settings and four built-in commands to stop Hermes Agent from burning tokens — alexcovo_eth · 2026-10-25
- Flint ranked a top-3 daily coding driver, running Recursive_SI's local model with day-zero MLX support — altryne · 2026-10-25
- Agent-assisted self-hosting now takes days, not months, dev argues on X — kuza55 · 2026-10-24
- PyMemoryEditor MCP lets your agent read and write any process's memory — SupermarketTrue7507 · 2026-10-24
- OO-Harness: Google paper boosts agent ~16 points by evolving harnesses, not models — alex_verem · 2026-10-24