Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: memory
Bedrock Agents: Memory Summarization, Versioned Guardrails and Knowledge Base
Terraform-driven Bedrock agent controls: session memory with a custom summarization prompt, versioned guardrails with detect-then-block rollout, and S3-backed RAG.
15 min readBuilding a Knowledge Assistant Agent on Databricks With LangGraph
Build a LangGraph agent on Databricks step by step: a minimal agent, Vector Search RAG, Lakebase checkpointing for short-term memory and a store for long-term memory.
7 min readGiving Claude Code a Memory: A Local MCP Plugin Called Memento
AI coding agents forget everything between sessions. Memento, a local MCP plugin for Claude Code, captures, scrubs, deduplicates and recalls project context.
7 min readBuilding Agent Memory That Survives the Conversation Without Hoarding
A three-tier memory design for agents: let session state die, keep long-term notes small and editable, and fetch live data fresh. Plus a multi-agent handoff failure.
9 min readFour Rules for Coding Agent Memory That Stays Honest
Storing more notes won't fix coding agent memory. Four rules keep it honest: visible staleness, fail-closed redaction, loud truncation and kept constraints.
9 min readAgent Memory Explained: Context Window, RAG and Persistent State
Agent memory is three different things. See how the context window, retrieval and persistent state differ, what each costs, and how to pick the right one first.
10 min readCustomer Memory for AI Agents Under a Strict Token Budget
How an agent memory layer extracts facts, scores importance, dedupes at 0.92 cosine, stores vectors in pgvector, and retrieves within a 2,048-token cap with eviction.
8 min readA Tiny Salience Gate: How a Squared Score Keeps Latency Near 119 ms
Break down a pre-model gate that scores messages with pi times psi squared, why squaring favors strong signals, and how a 0.2 ms local classifier keeps responses fast.
4 min readThe KV Cache Explained: Why Long Context Is a Memory Bill, Not Smarts
A plain-language guide to the KV cache: what it stores, how to compute its size, why long context eats memory, and four ways to cut the cost on local models.
8 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.