Tag
8 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 LLM observability and AI gateway for monitoring and evaluation
Helicone is an open-source observability platform and AI gateway for LLM applications. Teams point their existing OpenAI-compatible client at the Helicone gateway and every request is logged with traces, sessions, users, cost, and latency.
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.
Open-source AI agent observability that finds failures and dispatches fixes
Latitude is an open-source, MIT-licensed observability platform for production AI agents, organized around an Observe, Understand, and Refine loop of tracing, failure signals, and guardrails.
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 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.
Open-source LLM observability with request logging, cost tracking, and agent tracing
Spanlens is an MIT-licensed observability platform for OpenAI, Anthropic, and Gemini workloads with request logging, cost tracking, and agent tracing, added with a one-line change or a drop-in proxy.
Open-source AI gateway that traces, evaluates, and protects LLM calls
Grepture is an open-source AI gateway that sits between an app and its LLM providers to trace, evaluate, and protect every call.