knighteval is an open source CLI tool for evaluating HTTP RAG endpoints using JSONL datasets. It automates faithfulness and hallucination testing, providing streamlined evaluation for AI researchers and developers.
In the LLM eval & observability space, knighteval takes a focused approach. It focuses on automating the evaluation of retrieval-augmented generation (RAG) endpoints for accuracy and faithfulness. knighteval is an open-source project aimed at AI researchers and developers. The project is open source (Apache-2.0). knighteval is available on the command line.
It is developed by GabbarX, and the product first shipped in 2026. The project is developed in the open on GitHub with 3 commits in the last 90 days. Among its 5 catalogued features are RAG evaluation, faithfulness testing, and JSONL dataset support.
Latest indexed changes and source events
Other apps tracked under the same category.
