Ideas, tutorials, and technical deep-dives on AI memory.
I used to tell EIDARA what to remember. Now it listens, reads what I type, and notices what’s on my screen — and decides for itself. What changed in practice.
Read more → ReflectionTwo weeks after the senses went live, the real work began — replacing every rough edge with a structural fix that won’t break the same way twice. An update on where EIDARA is.
Read more → ReflectionI gave my AI memory three senses — voice, typing, and screen text. The most important feature isn’t any of them. It’s the off switch.
Read more → TechnicalI built an AI memory that reads my screen without looking at it. Why I rejected computer vision for the accessibility tree.
Read more → TechnicalTwo AIs disagreed about a fact in my memory. I built four ways for that conflict to resolve — and only one of them involves me.
Read more → ReflectionAn outside agent audited my memory system and found five debts the dashboard wasn’t showing. The dashboard was lying.
Read more → ReflectionThe auditor reported the same issues daily that the curator was already fixing. The principle: every failure becomes a prevention rule, not a patch.
Read more → TechnicalOne memory neuron silently accumulated 156 facts that didn’t belong. A cascade misrouting bug, and how a single guard fixed it overnight.
Read more → TechnicalReal data from two weeks of autonomous AI memory. What worked, what broke, what we changed. No theory — just numbers and decisions.
Read more → TechnicalMultiple AIs contribute atomic facts via MCP. One local curator decides what gets integrated. The folder is dead — DARA is a service now.
Read more → ReflectionI activated an autonomous curator. Five hours later, five false positives. Two weeks later, zero errors. Here's what happened.
Read more → Reflection140 cycles, zero errors. A sleep-time compute agent curating local-first AI memory — what happened, what broke, and what's next.
Read more → ReflectionWe activated the autonomous side of DARA. Five hours later, five false positives. Here's what we did about it.
Read more → Reflectionv2.0 makes the system self-correcting. Plus: atomic memory and desktop context.
Read more → ReflectionWhy I abandoned hierarchical folders for a compiled, flat approach to AI memory.
Read more → ReflectionOne AI with full context outperforms six agents without it.
Read more → ReflectionMECE is a thinking tool, not a memory tool. Here's why I had to unlearn it.
Read more → ReflectionWhy access permissions create bottlenecks — and what works instead.
Read more → TechnicalThe trick isn't better summarization — it's compilation.
Read more → TechnicalNo manual cleanup. No curator. The system maintains itself through consensus.
Read more → Technical52 tests each, no human intervention. Here's what happened.
Read more → TutorialNo technical skills required. Download, hand it to any AI, done.
Read more → TutorialAn agent is a .md file. Share it like any document.
Read more →