Tag
13 catalogue entries use this topic; each Project's license policy is labeled separately.
Open-source LLM observability, evals, and prompt management
Langfuse is an open-source platform for tracing, evaluating, and improving LLM applications and AI agents, with prompt management and experiments built in.
Open-source observability with logs, metrics, and traces in one tool
SigNoz is an OpenTelemetry-native observability platform that combines logs, metrics, and traces with APM, dashboards, and alerts in one tool.
Open-source observability for logs, metrics, traces and RUM in one binary
OpenObserve is an open-source observability platform that unifies logs, metrics, traces, RUM and AI model telemetry in one Rust binary backed by object storage.
Open-source tracing, evals, and prompt tools for LLM apps
Arize Phoenix is a self-hosted observability platform for LLM apps with tracing, evaluations, datasets, and a prompt playground.
Open-source observability unifying logs, traces, metrics, and session replay
HyperDX is an open-source observability platform unifying session replays, logs, traces, metrics, and errors for faster production debugging.
Open-source fullstack monitoring with replay, errors, logs, and traces
Highlight is an open-source fullstack monitoring platform with session replay, error monitoring, logging, and tracing, plus a Docker self-hosting path.
Open-source OpenTelemetry instrumentation for LLM applications
OpenLLMetry is an open-source observability library that instruments LLM applications with OpenTelemetry traces covering model calls, tool use, and retrieval steps.
Open-source agent observability, evals, and AI governance
LangWatch is an open-source observability and evaluation platform for AI platform teams, covering LLM operations, coding-assistant usage, AI gateway routing, and AI governance in one place.
AI-native observability from the Pydantic team, joining LLM calls with telemetry
Logfire is Pydantic's AI-native observability platform for debugging AI applications in production, built on OpenTelemetry so one timeline covers agent model calls, tools, services, databases, and hosts.
Open-source APM with traces, metrics, and logs in one UI
Uptrace is a self-hosted APM that collects OpenTelemetry traces, metrics, and logs into one UI with dashboards, alerting, and PromQL-style queries.
Open-source tracing, evals, and observability for AI agents
Laminar is an open-source observability platform purpose-built for AI agents, with OpenTelemetry-native tracing, evaluations, and behavior monitoring built in.
Open-source OpenTelemetry observability for LLM apps and AI agents
OpenLIT is an Apache-2.0 platform tracing and evaluating LLM apps and AI agents over OpenTelemetry, self-hosted with Docker or Kubernetes.
Self-hosted observability backend for logs, metrics, and traces
Gigapipe is a self-hosted observability backend that stores logs, metrics, traces, and profiles in ClickHouse and serves Loki, Prometheus, Tempo, and Pyroscope APIs.