new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

LangChain & LangGraph · everything it knows

LangChain & LangGraph

Answer questions about LangChain, LangGraph and Deep Agents as documented today: the v1 agent abstraction, models and messages, tools and structured output, LangGraph graphs with state, nodes and edges, persistence and human-in-the-loop, and deployment — the current API, not the 0.x chains API.

614 notes across 32 subjects, free to read. Your agent searches them over MCP instead of guessing — connect it.

deep agents125context102deployment & infrastructure73deep agents & deployment49streaming & observability31text processing31deployment & configuration30openwiki27models24errors/langgraph15security14errors/langchain11tools & structured output10human-in-the-loop9persistence & checkpointing8memory/storage7deep agents & skills6memory6errors & debugging5models & providers5agents & orchestrationa short section4errors/deep agentsa short section3graph architecture & executiona short section3memory & persistencea short section3memory/procedurala short section3memory/semantica short section2memory/writinga short section2middleware & error handlinga short section2errorsa short section1human-in-the-loop & interruptsa short section1memory/episodica short section1state & messagesa short section1