AI Agents, Memory and MCP: Articles
What is changing in AI agents, context and memory, written for people who build with them, and what it means in practice.
Context Engineering Turns One: The Four Techniques, a Year Later
Anthropic’s context engineering post named four techniques in September 2025. A year on, each has become a product feature. Here is where each one stands and what is still missing.
Updated September 29, 2026
Dreaming Everywhere: How Every Major AI Vendor Started Consolidating Agent Memory in 2026
Anthropic, OpenAI, Mem0 and Letta all shipped background memory consolidation this year, and memory itself turned into versioned files. What changed and what to watch.
Updated September 29, 2026
MCP Went Stateless on July 28. Here Is Where State Lives Now.
The 2026-07-28 MCP spec removed the session handshake, deprecated Roots, Sampling and Logging, and tightened OAuth. What changed, what it means for servers, and where memory fits.
Updated September 29, 2026
Resets Beat Compaction: What 2026 Taught Us About Long-Running AI Agents
Compaction keeps a conversation going; it does not give the agent a clean slate. Across vendors, 2026’s answer to context exhaustion is durable state outside the window.
Updated September 29, 2026
Skills, AGENTS.md and Memory: Which Layer Should Hold What?
Agent Skills became an open standard, AGENTS.md moved to the Linux Foundation, and Claude Code now reads it. A practical map of what belongs in rules, skills and memory.
Updated September 29, 2026
Subagents Went Mainstream in 2026. The Hard Part Is the State Between Them.
Claude Code, Claude Managed Agents, Codex, Gemini and Letta all shipped multi-agent orchestration this year. What the pattern looks like and where coordination breaks.
Updated September 29, 2026
Why AI Agent Memory Goes Stale, and the Four Ways Tools Now Fix It
Memory that only grows ends up full of reversed decisions. Validity windows, supersession pointers, version history and audits are the four fixes that shipped in 2026.
Updated September 29, 2026