Vector RAG Is Not Enough for AI Agent Memory
We Built an Alternative to Vector RAG for AI Agent Memory
Traditional RAG splits documents into chunks and retrieves by vector similarity, but AI agents need to decide when and how to retrieve information. Agentic RAG treats retrieval as a tool the agent can invoke, evaluate, and repeat. This shift doesn't make vector databases obsolete—they remain useful for large knowledge bases—but for many document-agent workflows, developers should start with direct document operations like structured extraction, full-document processing, and multi-document comparison instead of a fixed vector pipeline.
The question is not whether these tools are valuable. The question is whether every agent should begin with a full vector retrieval stack.
- geuis
The entire site looks like it was generated with Claude.
The site hijacks scrolling.
I scanned through paragraph after paragraph of overbloated and repetitive descriptions of what and how RAG works compared to how "modern agents" need to access documents.
What I never saw at any point was whatever this "alternative to RAG" was supposed to be.
Honestly the entire body of copy feels like it was llm generated.
- cmenge
I read the first paragraph or two, but then I stopped for two reasons:
A) searching using BM25 and via vector embeddings are two different methods of search; both have their uses, many practical use cases benefit from having both. The search method is independent of who calls it when, i.e. whether you just have a static pipeline, or a dynamic one where the search tool calls them.
B) you're describing the static pipeline as if it were SOTA. We dropped that well over a year ago IIRC. There might still be cases where that is good enough, but in general, agentic search has pretty much become the default since LLMs became reasonably good at tool calling.
- ericol
yeah no thank you. There's no way in hell I am going to share with you any sort of document.