Dark | Light
[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

![TDataScience Avatar](https://lunarcrush.com/gi/w:24/cr:twitter::788898706586275840.png) Towards Data Science [@TDataScience](/creator/twitter/TDataScience) on x 242.1K followers
Created: 2025-07-22 23:14:01 UTC

Agentic AI needs more than clever prompts. It needs memory. In this thoughtful breakdown, Ida Silfverskiöld explains the architectures behind LLM memory systems, from “pocket-sized facts” to long-span summaries, and when to choose knowledge graphs over vector stores. 




XXXXX engagements

![Engagements Line Chart](https://lunarcrush.com/gi/w:600/p:tweet::1947797309095346280/c:line.svg)

**Related Topics**
[llm](/topic/llm)
[coins ai](/topic/coins-ai)
[agentic](/topic/agentic)

[Post Link](https://x.com/TDataScience/status/1947797309095346280)

[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

TDataScience Avatar Towards Data Science @TDataScience on x 242.1K followers Created: 2025-07-22 23:14:01 UTC

Agentic AI needs more than clever prompts. It needs memory. In this thoughtful breakdown, Ida Silfverskiöld explains the architectures behind LLM memory systems, from “pocket-sized facts” to long-span summaries, and when to choose knowledge graphs over vector stores.

XXXXX engagements

Engagements Line Chart

Related Topics llm coins ai agentic

Post Link

post/tweet::1947797309095346280
/post/tweet::1947797309095346280