flâneur — a map of the web's best reading

Memory for agents

blog.langchain.dev · 1,262 words · saved by 1 readers

At Sequoia’s AI Ascent conference in March, I talked about three limitations for agents: planning, UX, and memory. Check out that talk here. In this post I will dive more into memory. See the previous post on planning here, and the previous posts on UX here, here, and here.

Memory for agents Learn Docs Company Pricing Try LangSmith Get a demo Try LangSmith Get a demo Harrison's In the Loop Memory for agents Harrison Chase October 19, 2024 5 min Go back to blog Create agents Share At Sequoia’s AI Ascent conference in March, I talked about three limitations for agents: planning, UX, and memory. Check out that talk here . In this post I will dive more into memory. See the previous post on planning here , and the previous posts on UX here , here , and here . If agents are the biggest buzzword of LLM application development in 2024, memory might be the second biggest.

Explore this link on the map →

related reading