The RecallMEM Series
How a local chatbot turned into a deterministic memory framework, then a memory-backed voice agent with stricter boundaries.
01
02
03
04
The LLM Was The Easy Part
Building RecallMEM showed me the model call was easy. The real work was memory, files, tokens, setup, persistence, and product glue.
AI memory is broken because we let the model own the truth.
Building Speak2Me taught me why AI memory needs deterministic facts, transcript chunks, vector search, and app-owned truth.
Voice Agents Need Receipts
RecallMEM now has a Deepgram voice agent with app-controlled memory. Voice made the memory layer stricter: no quote, no memory.
Your AI Agent Is Logged In. That Doesn't Mean It Should Have Access.
What building RecallMEM taught me about agent authorization, vector search, delegated access, and why relevance is not permission.