Evanson - Hackdot

Evanson

Show HN: Lumina – Open-source observability for AI systems(OpenTelemetry-native)

Posted by Evanson on Tuesday January 27, 2026 @11:00AM
from the show-hn dept.

Hey HN! I built Lumina – an open-source observability platform for AI/LLM applications. Self-host it in 5 minutes with Docker Compose, all features included.The Problem:I've been building LLM apps for the past year, and I kept running into the same issues: - LLM responses would randomly change after prompt tweaks, breaking things. - Costs would spike unexpectedly (turns out a bug was hitting...

( Read More... | no comments | on HN )

Re:Show HN: Lumina – Open-source observability for LLM applications on Monday January 26, 2026 @08:55AM (#46765660)

Thanks, and great point. Right now, Lumina is mainly SDK/trace-level (what the app thinks happened: tokens, cost, latency, outputs), so you’re right that low-level HTTP details like retries/timeouts/failovers can be partially hidden. Capturing the raw HTTP layer alongside traces is on our roadmap because production debugging often needs both views. Also, your “see what your agent is actually doing” angle is spot-on. There’s a lot of opaque magic in agent frameworks. Curious how you’re doing it in toran.sh proxy/intercept, or wrapping the SDK HTTP client?