Writing

Ideas on memory worth reading.

What actually happens when you try to give AI agents long-term memory. The wins, the unsolved problems, and the parts nobody warns you about.

Compliance

Memory for AI That Operates Under Audit

Whisper hallucinated in clinical transcripts. Memory layers are the next surface. Feature coverage across OSS layers, a compliance-control mapping (HIPAA, SOC 2, GDPR, EU AI Act), and what we still owe.

Read →11 min read
YMYL

Your AI Memory Can't Tell a River Bank from a Savings Account

Regex-based YMYL classification flags 'bank of the river' as financial and misses 'my chest hurts' entirely. How we fixed both problems with a two-stage pipeline at zero added API cost.

Read →8 min read
Integration

Why AI Coding Agents Forget Your Project Conventions

CLAUDE.md, .cursorrules, and Aider conventions files don't scale past 200 lines. Here's how to give Claude Code, Cursor, and Aider a real memory layer with widemem, plus three cross-session saves.

Read →9 min read
Cost

The Real Cost of AI Memory: Every Provider, Compared

How much does AI memory actually cost? Mem0, Zep, Letta, Cognee, LangMem, widemem. Platform fees, LLM calls, embeddings, infrastructure. Real numbers from $0 to $475/mo.

Read →12 min read
Concepts

Why Context Windows Aren't Memory (And Why It Matters)

Context windows keep getting bigger. 128K, 1M, 10M tokens. But bigger context is not memory. Three research papers, real cost math, and benchmark data explain why.

Read →14 min read
Concepts

The Complete Guide to LLM Memory

How memory works for LLMs. The core concepts, how OpenAI, Claude, Grok, DeepSeek, and Perplexity handle memory, what memory layers are, and where this is all heading.

Read →12 min read
Uncertainty

Your AI Should Know When It Doesn't Know

Why memory systems that always answer are worse than ones that sometimes say 'I'm not sure.' Confidence scoring, uncertainty modes, and the case for honest AI memory.

Read →8 min read
Decay

I Built a Memory Layer That Forgets Only What Doesn't Matter

Why forgetting is harder than remembering, what cognitive science says about selective memory, and how batch conflict resolution, importance decay, and YMYL safety work under the hood.

Read →10 min read
Safety

Your AI Forgot Someone's Medication. Now What?

YMYL safety for AI memory: why some facts should never decay, how two-tier classification works, and the edge cases that still need solving.

Read →8 min read
Conflicts

The Contradiction Problem in AI Memory

What happens when AI agents accumulate conflicting facts over months. Why vector similarity alone cannot detect contradictions, and what batch conflict resolution looks like in practice.

Read →9 min read
Directory

Every LLM Memory Solution in One Place (2026)

A directory of open-source projects, commercial platforms, and LLM provider solutions for AI memory. What each solves, how they compare, and how to choose.

Read →7 min read