Packer: Stateful AI agents require an LLM OS to maintain state
Charles Packer · Sleep-Time Compute — Letta AI (Charles Packer, Charlie Snell, Kevin Lin) · Apr 21, 2025 · at 3:56
Charles Packer is discussing the architectural distinction between stateful agents and LLM OS systems developed at Letta.
0:00 / 0:06exact quote · 6.1s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“To have a stateful agent, you need like an LMOS because you need something other than the LM to kind of maintain state.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Charles Packer
Packer: Sleep-time compute during idle downtime is a major missed opportunity
“And practically speaking, you know, machines, they're not like humans, they can be run all the time. And there's a ton of downtime, both in advance of like questions being asked also like After questions have been asked too. So I think beyond just scaling at t…”
Packer: True AI agents run continuously rather than waiting for triggers
“And I think that's another aspect of like what makes something agentic, like not having to have a user send an event to trigger the machine to turn on, just allowing these machines to run all the time.”
Packer: Background sleep-time agent architectures will be standard within two years
“I think those two, yeah, I think similar to memgpt, I think they're definitely like very good reference designs for just what's coming next. I think this sort of thing is, is just gonna be like the norm in like a year or two years.”
Packer: Sleep-time compute re-represents token state into easily queryable formats
“In the test time compute setting, you know, here, the state is tokens and the kind of like sleep time, like indexing process is a re-representation of those tokens into something that is like more easily queryable and more flexible.”
Packer: Sleep-time compute offers Pareto improvements across Claude 3.7 and DeepSeek
“It's like pretty consistent across like both 3.7 deep seek, three mini, which all like the way you actually scale the x-axis here is fundamentally quite different in each case with 3.7 extended thinking mode. The parameter you provide to scale it is different …”