Blog

Notes on agents, memory and handoffs

What we're learning about running AI agents on real projects: shared memory, decisions, handoffs and the market around them.

All agencies agent-memory agent-teams agents-md basic-memory claude-code claude-md clients codex comparison contractors conventions cursor decisions entire guardrails handoff instinct mem0 multi-agent muse switching-tools

28 Oct 2026·7 min readclaude-mdagents-mdcursorconventions
CLAUDE.md, AGENTS.md and .cursor/rules: why they rot, and what belongs somewhere else
Keep stable conventions in repository instructions. Move changing state into reviewable handoffs, and distinguish human decisions from observed work and proposed notes.
27 Oct 2026·8 min readcursorclaude-codecodexswitching-tools
How to switch from Cursor to Claude Code (or Codex) mid-project without losing your decisions
Switch from Cursor to Claude Code or Codex with a reviewed handoff that separates human decisions, observed work, and proposed next steps, then verify it before editing.