RDLTR

Short for Read Later. Save links from any browser or phone. Click to save, read to clear. The full tour

One topic. Every takeSeek and you shall find

Reading up on CrewAI

2 deep · digging since apr 27

  • memory.cobanov.dev favicon
    How AI Agent Memory Works

    An interactive essay explains how agent memory systems work through context windows, embeddings, and retrieval architectures to overcome LLM statelessness.

  • tanay.co.in favicon
    Today's harness is Tomorrow's Prompt

    Temporary scaffolding around AI models becomes obsolete as models improve, so developers should build these harnesses cheap enough to discard.