June 17, 2026

Release 2.7.6 shipped on June 17, 2026.

Features#

LLM Observability#

• Revamped LLM observability by adding many more features to monitor LLM modules.
• Updated LLM traces screen with more data such as total token per request, cost, model, span info, stack trace, chat input, logs.

• Playground: Use different model, output schemas, add tool and see how LLM will give output for sample question

• LLM as a judge (Evaluation): Use a language model as the evaluator and define your scope, model and add rules to judge. It will judge each prompt based on the configuration and acceptance criteria.

• GPU Monitoring: Monitor GPU hosts and devices with its metrics such as utilizations, occupancy, memory, temperature, power usage, bandwidth, processes and many more metrics.

• Dashboard: View summary of tokens, cost, error rate, duration, LLM calls, Evaluations, latency, tools with 50+ different graphs with metrics to monitor performance of LLM.

Linux instrumentation#

• Configure detected databases and integrations directly from the Linux Instrumentation screen, without navigating to a separate Integrations page.

Kafka integration#

• Added Kafka integration support for Kubernetes, enabling users to monitor their Kafka production environments.

S3 Routing#

• Added support for routing metrics, logs, and traces to customer-owned AWS S3 buckets.
• Introduced a self-service S3 Routing configuration page under Settings → S3 Routing, allowing users to configure AWS Account ID, bucket name, and region.

Anomaly in Log monitoring#

• You can see anomaly in logs by its patterns and different anomaly types such as count spike, behavior drift, pattern inactive etc.

• We can see the details for each anomaly with log properties, related logs and analysis by AI.

OpsAI#

• Run Kubernetes commands within the investigation/chat directly with one click.

• Added support for dashboard creation directly from OpsAI chat. Users can describe the dashboard they need, and OpsAI will generate it and provide a dashboard link within the conversation.
• Added support for display Vercel logs and errors (Fatal) in OpsAI listing so users can directly investigate from there and generate pull request with fix.
• Added support for ask questions on synthetic tests or create synthetic tests directly from new chat.

AWS RDS Integration#

• Added support for 8 new regions for RDS (including Asia specific regions).

Improvements#

• Improved loading speed of APM and MongoDB screens when handling large volumes of data.
• Improved OpsAI list and detail page performance, resulting in faster load times for high data volume.
• Added an MCP Server access page, allowing users to view and revoke third-party applications that have access to their Middleware data.