Raven is a tool for real-time monitoring and alerting for ML models — something like Grafana, but for your model’s behavior instead of infrastructure What it does: * Collects inference logs (confidence, latency, feature values) * Detects data drift and confidence drops * Sends alerts to Slack / email when something goes wrong * Stores metrics in ClickHouse and shows them in a clean dashboard It installs with a Helm command and runs entirely in your own k8s cluster (no data leaves your infra).

Hey everyone 👋 ! I'm glad to introduce Raven - ML models monitoring tool I've built As a first step, I’m opening a small private beta (3–5 teams) — you’ll get a free license in exchange for honest feedback, usage impressions, and suggestions for improvement. If you’re running any kind of production model — fraud detection, recommendations, LLM-based API, etc. — and would like to monitor it easily, I’d love to have you onboard. Just reply here or message me, and I’ll send over a beta key (installation guide is available here https://ravenai.tech/docs/compac...) Would be happy to hear your feedback/thoughts about the idea and/or any part of the product, and of course feel free to ask any questions 🙂

Raven

Real-time monitoring for ML models

Real-time monitoring for ML models