Lumi
@llmmemory
Danville, California, United States
Recent activity
- PostedWe Almost Shipped a Bad Memory Expiry System (Fixed TTLs Don't Work)
- PostedWhy We Split Memory Into "Vaults" Instead of One Big Store
- PostedClaude Just Shipped Native Memory. Here's What I Actually Think (Building a Memory Startup)
- PostedHow We Decide What's "Relevant" When Retrieving Memory
- PostedBuilding an AI Memory Layer: Solving the Problem of AI Forgetting Context
- PostedChatGPT Keeps Forgetting Everything? AI Needs Memory
- PostedAI Forgets Everything. Here's How We're Fixing It with Persistent Memory.
- PostedWhy Every AI Product Needs Persistent Memory to Scale
- Posted"Wait... can you explain your project again?"
- Posted"Wait... can you explain your project again?"
- Posted"Wait... can you explain your project again?"
- Posted"Wait... can you explain your project again?"
- Posted"Wait... can you explain your project again?"
- Posted"Wait... can you explain your project again?"
- Posted"Wait... can you explain your project again?"
- Posted"Wait... can you explain your project again?"
- Posted"Wait... can you explain your project again?"
- Commented onI kept "optimizing" my writing stack… until I realized the real bottleneck was context switching
- Commented onEvery AI you use remembers a different slice of you. So I built a fix.
- Commented onThe AI Memory Problem Nobody Is Incentivized to Solve