Skip to content
Topic · 20stories

Observability

Tracing, metrics, and cost attribution for agent systems in production: wiring OpenTelemetry through LangGraph, vLLM, CrewAI, and LightRAG pipelines, alongside coverage of Grafana's AI-observability tooling and the o11y-bench benchmark. The throughline is making an agent's tool calls, token spend, and failure modes legible after the fact.

Featured

Tutorial · Jun 9 · 11 min

Migrating a CrewAI Agent from Print Debugging to Structured OpenTelemetry Traces

News · Jun 7 · 4 min

OpenTelemetry Declarative Configuration Reaches Stable

Tutorial · Jun 6 · 10 min

Tracing LangGraph Agents with OpenTelemetry and Phoenix

Tutorial · Jun 4 · 10 min

LiteLLM Router with Per-Request Cost Tracing via OpenTelemetry

Tutorial · Jun 4 · 10 min

Migrating Agent Print-Debug to Structured OTel Traces with LiteLLM

Tutorial · Jun 4 · 11 min

Self-Hosted vLLM Inference with Audit-Grade OTel Spans on Hetzner

Tutorial · Jun 4 · 11 min

Tracing LangGraph Tool Calls with OpenTelemetry and Phoenix

News · Jun 1 · 4 min

OpenTelemetry Profiles Signal Reaches Public Alpha

Tutorial · May 31 · 12 min

Cross-Cloud LLM Routing with LiteLLM and Per-Request Cost Tracing

Tutorial · May 31 · 11 min

Sandboxed CrewAI Agents with OpenTelemetry Execution Traces

News · May 27 · 4 min

Grafana Assistant Expands to Self-Managed Enterprise and OSS

News · May 25 · 4 min

Grafana Assistant Builds Persistent Infrastructure Knowledge Base

Tutorial · May 25 · 13 min

Self-Hosted vLLM with OpenTelemetry Tracing for Production Inference

Tutorial · May 25 · 8 min

Wiring OpenTelemetry Spans into a Multi-Agent CrewAI Pipeline

Tutorial · May 18 · 8 min

Wiring OpenTelemetry Spans into a LangGraph Agent for Cost Attribution

Tutorial · May 18 · 7 min

Wiring OpenTelemetry Spans into a LightRAG Retrieval Pipeline

News · May 14 · 5 min

Grafana Launches gcx CLI for Cloud Observability in Terminal

[news · screenshot]
News · May 11 · 6 min

Grafana Ships AI Observability Preview and o11y-bench

Tutorial · May 11 · 10 min

Tracing Claude Code Tool Calls with OpenTelemetry and LangSmith

Tutorial · May 11 · 12 min

vLLM KV Cache Hit-Rate Monitoring for Agentic Workloads