Show HN: Kelet – Root Cause Analysis agent for your LLM apps
Not a pilot. Kelet automates root cause analysis for AI agents in production—turning 'why did it fail' from manual trace-scrolling into automated hypothesis clustering across hundreds of sessions.
Why it matters
As AI agents proliferate in production, observability and debugging become competitive advantages. Kelet addresses a real operational pain point: agents don't crash; they silently fail. This tool abstracts failure investigation, letting teams move faster from 'something broke' to 'here's the fix.' Relevant to any company running multi-session agent workloads.
The key facts
6 to knowCreator claims 50+ production AI agents built, some with 1M+ sessions/day
Kelet clusters hypotheses across multiple failed sessions to surface root causes
Integrates via Kelet Skill (auto-discovery for coding agents), Python SDK, TypeScript SDK
Currently free during beta, no credit card required
Show HN post (early-stage, founder-led announcement)
Published Apr 14, 2026
Go to the source
Hacker Newskelet.ai
Publisher excerpt: I've spent the past few years building 50+ AI agents in prod (some reached 1M+ sessions/day), and the hardest part was never building them — it was figuring out why they fail. AI agents don't crash. They just quietly give wrong answers. You end up scrolling through traces one by one, trying to find…