hydrag-benchmark is an open-source CLI tool for locally benchmarking retrieval-augmented generation (RAG) systems. It provides metrics such as recall, MRR, chunk overlap, latency, and BEIR IR, helping AI researchers evaluate and compare RAG pipelines.
hydrag-benchmark sits in PulseGate's LLM eval & observability category. It focuses on measuring and benchmarking retrieval-augmented generation (RAG) systems locally for developers and researchers. It is built as an open-source project for AI researchers. The project is open source (Apache-2.0). It ships for the command line.
hydrag-benchmark first shipped in 2026. Development happens publicly on GitHub with 6 commits in the last 90 days. Key capabilities include RAG benchmarking, recall measurement, and MRR calculation.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do