Practical guides to agent memory.
These are not release notes. They are the questions people ask when an AI coding agent keeps forgetting decisions, preferences, project context, and the fixes they already paid for in time and tokens.
What is AI agent memory?
A plain-English guide to durable memory for agents: what gets stored, when recall happens, and why session history is not enough.
02Why coding agents forget context between sessions
The practical failure mode behind repeated explanations, lost decisions, and stale project assumptions.
03What is an MCP memory server?
How MCP gives Claude Code, Cursor, Cline, Windsurf, and custom agents a shared memory surface.
04How to give Claude Code persistent memory
What Claude Code memory needs beyond a tool call: hooks, recall before the model sees the prompt, and local storage.
05Local-first AI memory vs hosted memory APIs
The tradeoffs between local markdown memory, cloud memory APIs, privacy, cost, operations, and control.
06Agent memory vs RAG
Why agent memory is not just retrieval over documents, and where RAG still fits.