MemGPT, every mention

11 scenes · ← back to MemGPT

tap a year for its mentions
0010220420242025episodesmentions
02420242025episodes it came up in
002.525420242025episodesmentions per episode

every year anyone Charles Packer 10Shawn Wang 5Harrison Chase 2Alessio Fanelli 2Andy Konwinski 1

Verbatim, from the transcripts: the passages where MemGPT comes up

loading…

Terminal-Bench 2.0: the most impt coding agent benchmark of 2025 gets a v2! Launch + Q&A w/ founders Nov 8, 2025 · 1 mention

  • ▶ 23:29 Andy Konwinski Was really into sweep inch and mem GPT and we, and then Devon happened and I thought, wow, that's an interesting demo.

Sleep-Time Compute — Letta AI (Charles Packer, Charlie Snell, Kevin Lin) Apr 21, 2025 · 14 mentions

  • ▶ 0:16 Shawn Wang I actually don't know the name of the new paper yet, but anyway, Charles, actually you, you are presented a workshop, but you're, you're most famously known as one of the co-authors of MemGPT and two of your co-authors, Charlie and Kevin,… 3 times in the scene
  • ▶ 5:04 Charles Packer And I think, um, GPT established kind of like
  • ▶ 9:37 Charles Packer I think, you know, to go back to the analogy thing, I think, you know, with like MemGPT, we also thought a lot about like, you know, is the systems analogy better or is like cognitive analogy better? 4 times in the scene
  • ▶ 14:18 Shawn Wang Uh, I actually did even look back to the original memgpt implementation and I don't think there was, there was heartbeats, but there wasn't like a very heavy sleep cycle.
  • ▶ 29:29 Charles Packer So it's basically like memgptv two. 2 times in the scene
  • ▶ 31:23 Charles Packer And yeah, I mean, I think, you know, MemGPT was like one cool idea we had. 3 times in the scene

The Agent Network — Dharmesh Shah, Agent.ai + CTO of HubSpot Mar 28, 2025 · 1 mention

2024 Year in Review: The Big Scaling Debate, the Four Wars of AI, Top Themes and the Rise of Agents Jan 1, 2025 · 2 mentions

  • ▶ 1:00:39 Alessio Fanelli Do these memory products like the MAMGPTs of the world create a better way to implicitly extract preference? 2 times in the scene

[Paper Club] Who Validates the Validators? Aligning LLM-Judges with Humans (w/ Eugene Yan) Sep 28, 2024 · 1 mention

  • ▶ 59:55 unnamed speaker Uh, yeah, just a, I guess as a hint, if you drop by either the Gorilla server or the mem GPT server, both, uh, uh, Charlie and Shashir are generally, like, usually available in there if you have questions.

Personal AI Meetup - Bee, BasedHardware, LangChain LangFriend, Deepgram EmilyAI Apr 6, 2024 · 2 mentions

  • ▶ 55:33 Harrison Chase Um, so MemGPT uses the language model to, like, actively kind of, like, construct memory. 2 times in the scene
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 200 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.