vectory is an open-source AI evaluation toolkit designed for trace-aware assessment of LLMs, agents, and RAG systems. It includes a local Vectory Benchmark runner and a Streamlit-based interface. Available as a Python package under the MIT license, it helps machine learning engineers and developers rigorously test and observe their AI applications.
vectory sits in PulseGate's LLM eval & observability category. It focuses on evaluating and benchmarking LLM and agent performance with traceable, local tools instead of opaque cloud evaluators. vectory is an open-source project aimed at developers. vectory is open source under the MIT license. vectory is available on the web and the command line, and it can be self-hosted.
Behind vectory is tacticaledge, and it first shipped in 2026. Development happens publicly on GitHub with 23 commits in the last 90 days. Key capabilities include AI Evaluation, Benchmark Runner, and Trace Awareness.
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