All articles
54 articles on AI memory, agent engineering and production AI, newest first.
How to Reduce LLM Token Costs in Long Conversations: What Caching Saves, and Where It Stops
A long conversation costs far more than its number of turns suggests, because every request carries the system prompt and the entire history again, so total input grows with the square of the number of turns.
Claude API Pricing in 2026: Every Model per Million Tokens, and What Pro and Max Cost
The Claude API costs between $1 and $10 per million input tokens and between $5 and $50 per million output tokens on Anthropic's current models.
9 Essential Claude Skills for AI Engineers Building Production Agents + 1 Bonus Skill
Nine Claude Skills we run in production, plus one bonus, with the install command for each and what it saves you. Updated September 2026.
What is WebMCP? When and How to Use WebMCP in a Browser Agent?
The decision is per step, not per site: a page can expose a clean search tool and leave its account settings as ordinary DOM controls, so an agent that picks one mode per domain gets the worst of both.
Best Chatbot Memory Layer Plugins for Persistent User Data Retention and Memory
The best chatbot memory layer plugin captures durable user information, stores it with the right scope, retrieves only the relevant part of it, and updates or deletes it reliably.
The Best AI Agent Memory Layers in 2026, Ranked on Axes You Can Verify
No single AI agent memory layer is best in 2026. The right one depends on tenant isolation, contradiction handling, where you can run it, and what a retrieval costs, all of which you can check in an afternoon.
How To Use Jev In Your AI Agent: A Map Of Decision Seams
Jev cannot write a single word, which is the reason to care about it, so the question worth asking is never whether it should be your agent but which decisions inside your agent it should own.
AI Agent Evals: The Judge Is The Part Nobody Measures
An LLM judge scoring the same agent output three times will often hand back three different answers, and almost no guide to agent evaluation asks whether the judge agrees with itself or what it costs to run on everything rather than a sample.
Agent Memory Is a Real Problem. Most Builders Just Have Not Hit It Yet.
Every LLM call is stateless; agent frameworks solve that within a single run, which is why the memory problem only shows up once the run ends.
Best Claude Code Skills in 2026: 12 New Skills and What Changed
Important Claude Code skills shipped since February 2026, what each replaces, install commands, and the security problem that came with the marketplace.
MCP 2026-07-28: 20 Breaking Changes and the Errors They Cause
MCP 2026-07-28 removed sessions, the initialize handshake, and the ability for servers to initiate requests at all. It is wire-incompatible in both directions, so nothing breaks until a client upgrades underneath you. This is the full diff, every error you will hit with the fix for each, the HTTP+SSE deadline that two official sources disagree about, and a scorecard of what the release left alone.
Agentic Context Management: Agent Memory Is Not Merely a Storage & Retrieval Problem, It Is an Architecture Problem
We argue in our latest paper, that agent memory and cost is a lifecycle and architecture problem
Why OpenAI shipped an Official Plugin for Claude Code
OpenAI ships Codex plugin for ClaudeCode harness
An Anthropic Leader Told a Room of Founders to Stop Worrying About Context Windows. Here's the catch
An Anthropic researcher told a room of founders to stop worrying about context windows. Here is the question I did not get to ask, and why a bigger window solves short-term memory with bad tradeoffs and does nothing for long-term memory.
Maximem Synap's Agent Memory Now Available for Pipecat
Maximem Synap's persistent agent memory now integrates with Pipecat. Per-caller persistence, entity resolution, and 92% LongMemEval, 93.2% on LoCoMo accuracy for production voice and multimodal pipelines.
Maximem Synap & LiveKit Agents Integration
Maximem Synap's persistent agent memory now integrates with LiveKit Agents. Per-caller persistence, entity resolution, and 92% LongMemEval, 93.2% on LoCoMo accuracy for production voice agents.
Maximem Synap's Agent Memory Connected To Semantic Kernel
Maximem Synap's persistent agent memory now integrates with Microsoft Semantic Kernel. Per-user persistence, entity resolution, and 92% LongMemEval, 93.2% on LoCoMo accuracy for .NET and Python production agents.
Maximem Synap's Agent Memory Now Available for AutoGen
Maximem Synap's persistent agent memory now integrates with AutoGen. Per-user persistence, entity resolution, and 92% LongMemEval, 93.2% on LoCoMo accuracy for Microsoft multi-agent production systems.
Maximem Synap's Agent Memory Now Available for CrewAI
Maximem Synap's persistent agent memory now integrates with CrewAI. Per-user persistence, entity resolution, and 92% LongMemEval, 93.2% on LoCoMo accuracy for multi-agent production workflows.
Maximem Synap's Agent Memory Now Available for Google ADK
Maximem Synap's persistent agent memory now integrates with Google ADK. Per-user persistence, entity resolution, and 92% LongMemEval, 93.2% on LoCoMo accuracy for GCP production agents.
Maximem Synap Updates: Higher Scores, 17 Integrations, and a Live Playground
Synap updates: 92% LongMemEval (up from 90.2%), 93.2% LOCOMO, 17 framework integrations, a browser playground, public pricing, and a free accuracy eval on your own agent.
Memory Is Now Table Stakes for AEO Tools. Profound's Launch Just Proved It.
Profound shipped conversation memory. Stateless AEO tools are now behind. Here is the category signal, the three layers they need, and why building in-house is the wrong bet.
The state of AI memory in 2026: claimed vs observed
Independent reproduction of AI memory benchmark claims in 2026. LongMemEval and LoCoMo results from an open harness, with published vs. observed numbers for Mem0, Zep, SuperMemory and Synap.
Vity vs Obsidian for AI Agent Memory
Technical comparison of Vity and Obsidian for AI agent memory. Covers context rot, entity resolution, cross-AI coverage, setup complexity, and security.