docs(readme): rewrite the motivation opener as a question

"Each agent session resets from zero" contradicted the very next
sentence ("the memory features that exist today are *there* but
rarely used"). They can't both be true — either sessions reset or
they don't.

Replaced with a rhetorical question that puts the *user's*
frustration first ("Are you frustrated by each agent session
forgetting the valuable lessons you worked on previously?"). The
rest of the paragraph then explains why the existing memory
features don't solve that frustration — which is the real claim
the section was trying to make all along.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Author: nickroci

README.md

@@ -10,7 +10,7 @@ A personal memory system for coding agents. Built for Claude Code; lives outside
 
 ## Why this exists
 
-Each agent session resets from zero. The memory features that exist today — `CLAUDE.md`, Cursor rules, ChatGPT memory, the various provider built-ins — are *there* but rarely used, and when they do fire they often feel pointless: shallow grep against a static rules file, no judgment about what's worth remembering vs what isn't, no idea what's stale, no composition with the current turn. I was tired of teaching the same agent the same thing on day 17.
+Are you frustrated by each agent session forgetting the valuable lessons you worked on previously? The memory features that exist today — `CLAUDE.md`, Cursor rules, ChatGPT memory, the various provider built-ins — are *there* but rarely used, and when they do fire they often feel pointless: shallow grep against a static rules file, no judgment about what's worth remembering vs what isn't, no idea what's stale, no composition with the current turn. I was tired of teaching the same agent the same thing on day 17.
 
 So I wondered what could be achieved if you stopped optimising for token cost first. Real memory is salience-gated at write time, decays without reinforcement, mutates on retrieval, resists deletion of high-arousal traces, and uses different mechanisms for different latencies (ambient familiarity, deliberate recall, fast suppression). So we took the neurology seriously and built towards it — a curator pair (Sonnet + Opus) gating writes by surprise magnitude; three retrieval tiers each tuned to a different cognitive analog; surfacing-aware decay with optional arousal pinning; an opt-in mutation/reconsolidation pathway; archive-don't-delete so contradictions can resurrect old traces. Tokens cost something, but less than the friction of repeating yourself.