Open-source distributed tracing.
Open-source distributed tracing system. Jaeger collects spans from your services and shows you the call graph + timing of every request — including which agent step took how long, which tool call hung, where retries piled up.
Yes. Jaeger is open source and free under the Apache 2.0 license. It is a graduated CNCF project; you provide your own infrastructure to run it.
Yes. Jaeger natively receives OpenTelemetry trace data via the OTLP protocol, making it a common backend for OpenTelemetry-instrumented services.
Jaeger supports multiple configurable storage backends, including options such as Elasticsearch, Cassandra, and ClickHouse, with native ClickHouse support added in v2.
LangSmith is LangChain's framework-agnostic platform for tracing, evaluating, and deploying AI agents and LLM applications in production.
ObservabilityGrafana is the open-source dashboarding layer for production systems. It connects to Prometheus, Loki, Tempo, and 60+ data sources and turns raw metrics into the dashboards your team actually looks at.
ObservabilityPromptfoo is an open-source CLI and library for testing, evaluating, and red-teaming LLM applications and agents before they reach production.
Observability
Prometheus is an open-source monitoring system that scrapes metrics from your services on an interval, stores them as time-series data, and lets you query and alert on them with PromQL.
ObservabilityUpdates from the AI world — what shipped, what we’re using in production, and what’s worth your attention. Two emails a month, no spam.
