Claude Code compaction

Agent Memory Products Remember Your Conversation. Nobody Is Remembering Your Codebase

Every memory tool shipped this year stores what you said. Measured sessions of Claude Code auto compaction reduced 132,000 tokens of accumulated state to roughly 2,300, a 98% reduction, and what survives is the transcript rather than the understanding. Multiply that by 40 engineers separately paying a model to work out what the same billing service does, and the cost of not writing the answer down becomes visible.

Context Rot Is Not a Session Hygiene Problem. It Is an Architecture Problem

Compliance with an agent's own explicit constraints falls from 73% at turn 5 to 33% at turn 16 across 4,416 measured trials, and Claude Code auto compaction reduces 132,000 tokens of session state to roughly 2,300. Shorter sessions and cleaner instruction files treat the symptom. The window fills with low value tokens because the agent rebuilds an understanding of your codebase from raw source on every task.

"Context Left Until Auto-Compact: 0%" — What This Warning Means and Why Your AI Just Forgot Everything

When Claude Code shows 'context left until auto-compact: 0%', it's about to summarize everything and throw away the details. Here's exactly what gets lost and why it matters.