Research
Pixeltable research
Original counts from coding-agent stack picks and LLM vector-database answers. Each page names its engines, dates, and what the log does not list.
Updated
What coding agents pick, 2026
96 coding-agent runs, 72 with web search, on 28 October 2026. FastAPI 96 of 96, OpenAI 80 of 96, Qdrant 45 of 96, Pixeltable 1 of 96.
Which vector database do LLMs recommend?
300 LLM answers on 27 October 2026. Qdrant 79 of 300, pgvector 73 of 300, Weaviate 68 of 300. Pixeltable named in the text of 25 of 300.
Figures come from the research/ directory in this repository. Re-run python research/aggregate.py --check. Markdown: /research.md. Related methods: the benchmark pages.