MemGPT: Towards LLMs as Operating Systems
AI Summary
The paper that started the modern agent memory conversation. Packer and the Berkeley Sky Lab team argue that LLMs should be treated like operating systems, with a context window as fast RAM and external storage as disk. MemGPT introduces virtual context management, function-calling interrupts, and a self-editing memory architecture that lets agents page information in and out. Everything downstream — Letta, memory blocks, sleep-time compute — is a product decision built on top of this paper's vocabulary. If you read one thing, read this first, because it defines the terms the rest of the field argues about.
Original excerpt
We gratefully acknowledge support from the Simons Foundation, member institutions, and all contributors.Donate
Authors:Charles Packer, Sarah Wooders, Kevin Lin, Vivian Fang, Shishir G. Patil, Ion Stoica, Joseph E. Gonzalez
View a PDF of the paper titled MemGPT: Towards LLMs as Operating Systems, by Charles Packer and 6 other authors
View PDF Abstract:Large language models (LLMs) have revolutionized AI, but are constrained by limited context windows, hindering their utility in tasks like extended conversations and document analysis. To enable using context beyond limited context windows, we propose virtual context management, a technique drawing inspiration from hierarchical memory systems in…
18 more articles in this vault.
Import the full Agent Memory Patterns vault to Burn 451 and build your own knowledge base.
Content attributed to the original author (Charles Packer, Sarah Wooders, Kevin Lin, Vivian Fang, Shishir G. Patil, Ion Stoica, Joseph E. Gonzalez). Burn 451 curates publicly available writing as a reading index. For removal requests, contact @hawking520.