#Agent

When waiting, polling, and switching between Agent sessions keep breaking our focus, task-driven work offers another way: let machines execute asynchronously while humans think one thing at a time.

From Codex's hard removal of chat/completions to the migration damage it caused in new-api, this examines the real tool-flow differences between Anthropic Messages and OpenAI protocols—why my long-chain silence is not the protocol's fault, and what truly counts as talking while working.

Does your Agent keep repeating the same mistake before it finally remembers? A look at gotcha.md: which memories must be fully available as soon as a new session begins, and which can wait to be retrieved later?

memU ADR 0007 overturns the earlier LLM mode: thoughts from a consumer-product developer and emotional-companion perspective.

A simple, ordinary story: an eighteen-year-old's dream inspired by Plastic Memories became a research topic at twenty-two—along with a technical survey of long-term memory, a plan for breaking down projects, and a look ahead at life.

Drawing on our experience building an AI companionship engine, this article compares the limitations of mainstream Agent frameworks such as LangChain, Dify, LangGraph, and Coze, and documents the core design ideas and trade-offs behind the low-level framework we built for real-time companionship.