Expanso Builds a Jev-Based Agent That Reads Pod Logs and Auto-Fixes Stale Kubernetes Labels
aronchick · x · 2026-09-21
Inspired by @dotpem's description of an ideal ops agent, Expanso built a Kubernetes agent on top of Jev that reads pod logs across the cluster, inventories labels in use, compares them with each pod's actual behavior, and automatically applies—or reverts—label changes. Labels drive Service selection, Kyverno policies, and Istio routing, so stale labels mean maximum chaos.
The three-step pipeline: Expanso reads logs and proposes a label change; Jev answers one question—is the evidence supported?; if yes, Kubernetes connectors execute it. Notably, routine log lines never reach the model (only anomaly signals like 5 restarts in 4 minutes or OOMKills get judged), and events are buffered if the network goes down.
Related event: Expanso Ships Jevops Agent to Auto-Fix Stale Kubernetes Pod Labels(3 posts)→
More from coding & agent
- PM builds a real SaaS in 24 hours with AI agents, sharing his full zero-cost stack — PawelHuryn · 2026-09-21
- Prompt cache restore works, but reusing KDA/Mamba states hits illegal memory access — TheZachMueller · 2026-09-21
- Why this dev hasn't shipped his agent: heavy tokens, slow, CPU-hungry — BLUECOW009 · 2026-09-21
- 128k context with compaction beats raw 256k/1M for quantized models — Informal-Trouble2183 · 2026-09-21
- If your LLM's tool-use trace shows it browsing Bluesky, shut that down immediately — venturetwins · 2026-09-21
- The real bottleneck is memory and compression, not context: dev argues compaction is a crutch — JoelMahon · 2026-09-21