Emmimal/context-graph-benchmark

A pure-Python structured memory benchmark for multi-agent LLM systems — context graph vs vector RAG vs raw history dump, five scenarios, 18 graded queries, zero API calls.

⭐ 30 ⑂ 5 Python MIT · 2026-06-27推送

https://towardsdatascience.com/vector-rag-isnt-enough-i-built-a-context-graph-layer-for-multi-agent-memory/

ai-memory benchmarking context-graph knowledge-graph llm llm-evaluation machine-learning multi-agent-systems nlp prompt-engineering rag retrieval-augmented-generation networkx ai-in-production graph-based-learning

30

Watchers

0

贡献者

0

Commits

0

Releases

0

Open Issues

2026-06-27

最近推送

原文中文

暂无 README