{"id":"openevals","name":"OpenEvals and AgentEvals","maker":"LangChain","url":"https://github.com/langchain-ai/openevals","repo":"langchain-ai/openevals","package":"pypi:openevals","summary":"Two small open-source libraries of ready-made evaluators for LLM applications and for agent trajectories.","details":"OpenEvals provides evaluator functions such as model-as-judge checks and structured-output matching, and AgentEvals provides evaluators that compare an agent's sequence of tool calls to a reference. Both are for Python and JavaScript, work alone or with LangSmith, and are MIT licensed.","open_source":true,"hosted":false,"verified":"2026-11-15","category":"observability","category_name":"Observability and evaluation","page":"https://modelmoot.com/tools/openevals","reviewed":"2026-11-15","checked":{"at":"2026-11-15T15:07:43.409Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}