Evals & observability AI tools
Evaluation, tracing and monitoring for LLM apps. LangSmith, Braintrust, Arize and peers.
Open-source LLM observability, evals and prompt management.
Phoenix (open source) and Arize AX for agent observability and evals.
DeepEval, the open-source unit-testing framework for LLM outputs.
Open-source eval and red-teaming CLI for prompts and agents.
Experiment tracking and Weave for LLM apps, part of CoreWeave.
