Weights & Biases Weave
Tracing and evaluation for AI applications
Weave is a toolkit from Weights & Biases for logging, tracing and evaluating LLM applications. It records inputs and outputs of Python or TypeScript functions and compares runs side by side.
More in Observability
Arize Phoenix
Observability
AI observability and evaluation you can self-host
Braintrust
Observability
Evals, logging and prompt tooling for AI products
Datadog LLM Observability
Observability
LLM traces inside Datadog
Helicone
Observability
Open-source LLM observability through a proxy or SDK
Langfuse
Observability
Open-source LLM observability, evals and prompt management
LangSmith
Observability
Tracing, evals and deployment from the LangChain team