LLM Wikis: How AI Agents Build a Second Brain That Never Forgets

Most AI agents forget everything the moment a session ends — forcing teams to rebuild context from zero on every run. LLM Wikis take a different approach to agent memory: instead of just storing information, the agent reads, reconciles, and rewrites its own knowledge over time, much like a person maintaining a living wiki. Join Izma Aziz for a live, hands-on build using LangGraph and Deep Agents — watching an LLM Wiki come together step by step, with the reasoning behind each design decision explained as it happens. You'll learn: → What an LLM Wiki is and why persistent, growing memory matters for agents → How it's different from RAG, file search, and standard chat history → The full lifecycle: ingesting, organizing, querying, and updating knowledge → How to watch a working LLM Wiki get built live, not just described in slides → The design tradeoffs and limitations to expect in production → Why the cost of "forgetting" compounds as agents take on longer, more autonomous tasks