OpenObserve Releases v1.0 with AI Observability at Its Core

OpenObserve, the open-source unified observability platform, announced the general availability of v1.0 on September 22, 2026, covering both self-hosted deployments and OpenObserve Cloud. The release centers on AI Observability, bringing agent tracing, LLM monitoring, evaluation, and session annotation into the same platform that already handles logs, metrics, traces, and real user monitoring.

The new capabilities let teams track a single request from the browser through the agent loop, model call, tool call, and database without stitching separate tools together. OpenObserve also supports token cost and usage tracking across more than 80 providers, full-session tracing, Agent Graph, and agent behavior analysis.

Founder and CEO Prabhat Sharma said AI observability was never going to work as a separate tool, as agents interact with databases, backends, and users. theCUBE Research Practice Lead Paul Nashawaty noted that 93% of enterprises are building custom AI agents, but only about one in five have mature governance in place, pointing to a need for unified observability connecting agent behavior, model output, application telemetry, and operational context.

AI Observability previously appeared on Product Hunt on September 10 and was ranked #2 Product of the Day. v1.0 also adds an alert library of more than 1,200 curated alerts, composite and SLO burn-rate alerts with Terraform and OpenTofu export, database monitoring, open-source synthetic monitoring, and faster PromQL support. Decklar CTO Shailesh Mangal said the unified view has cut his team's time to diagnose agent issues from hours to minutes.