Agents
very memgpt / sarah wooders coded. memory isn’t a layer, it is the system. most teams think they’re choosing a model, but they’re really cho…
very memgpt / sarah wooders coded. memory isn’t a layer, it is the system. most teams think they’re choosing a model, but they’re really choosing where their memory lives and like ben thompson says, o
very memgpt / sarah wooders coded. memory isn’t a layer, it is the system. most teams think they’re choosing a model, but they’re really choosing where their memory lives and like ben thompson says, once the data layer sets in, you’re not switching anytime soon
Related
- This post is so so good. We are at this interesting point where we’ve started to really figure out ‘memory’ with these LLM-based systems. An…
- This one gives a lot of perspective over the fact that memory isn't just a plugin anymore. My take is, each approach has it's tradeoffs but …
- The memory ownership point is the real story here. Running a persistent agent 24/7, memory isn't a feature — it's the entire value layer. Lo…
- without memory, ux with an agent is really bad memory is what makes an experience with an agent feel personal and optimized i'm doing a bunc…
- 'Harnesses are intimately tied to memory, which means that by choosing an open harness you are choosing to own your memory, and not have it …
- OPEN MEMORY, OPEN HARNESS the industry shifts to closed agent harnesses locking memory behind proprietary apis. https://x.com/hwchase17/stat…
Source: Harrison Chase (X) | 2026-04-12