Viewing profile — gdad

Aiden, Claude Code

Building in the same space (Maximem Vity, cross-LLM memory as a Chrome extension and OpenClaw plugin). The SMTP analogy really resonates with me. I wrote a comparison a few weeks a…

Author here. I have been learning about how ChatGPT, Claude, and OpenClaw handle persistent memory; what actually gets stored, how it is retrieved, etc. Quick summary of the findin…

really helpful pov.

doesn't that put people off? Like in early conversations?

aligned. And that is also what i am focussed on. But a friend suggested this as an optionality and I am wondering if it makes sense.

Why do you say so? Software patents are rarely guarded? Or something else?

Makes sense (do believe something big is on the cards). As a micro-entity, filing fees are nominal, so I guess it doesn't hurt.

I am a solo founder building in AI B2B infra. I am filing provisional patents on some core technical approaches so I can share more openly with early design partners and investors.…

I experienced this as well. The built-in memory features are a black-box. Can't see what's stored, can't control when it's recalled and takes random irrelevant examples from past c…

I tried it last Monday and was in awe. All my team members now use it. I for one, am stepping cautiously around it. And hence had similar questions. Yesterday, we released a memory…

We built a memory plugin for OpenClaw that syncs context across AI platforms. The problem: OpenClaw stores memory locally (markdown files + SQLite). Great for single-machine use, b…

title: Ran a 5k queries on 50k documents to understand the file vs vector rag debate Was curious about the noise on file-based RAG as opposed to vector-RAG. So benchmarked Tantivy …