Agents don't need memory, they need documentation

In one line

Why agents need project documentation instead of retrieval from old conversations.

Opening excerpt

A memory plugin analyzes your conversations. It generates 1,000 isolated snippets and inserts them into a vector database. With your every prompt, it attaches the five most similar snippets; if the agent is confused (which it is), it manually searches for more. That’s the product they call “memory.”

It’s a strange thing to use when you think about what problem you’re trying to solve. You want your agent to understand your project. To know where a feature is, why it was built, what you agreed on and what you care about. Instead, you get a lottery over RAG snippets, injected on every prompt, hoping the right ones float up.

Even when it does work, the agent still doesn’t understand your project. The entire memory plugin ecosystem is solving the wrong problem.

That’s the whole architecture. Some tools are extra fancy; they let the agent search through past transcripts word for word. Or they implement some kind of multi-tier memory system that classifies short or long-term memory. Or they add a bunch of background daemons to review, merge, or deduplicate memories.

(Excerpted from the original; full article via the source link below.)

This story hit the Hacker News front page today (330 points / 202 comments, via liao.gg). Our Tech Radar aggregates daily signals on AI engineering, backend architecture and DevOps — browse the related services and further reading below, or get in touch with our team.