docs(readme): three typo fixes in the rewritten motivation paragraph

- "lessons that had be learned" → "had been learned"
- "the same thing over any over" → "over and over"
- "shared knoweldge per project" → "knowledge"

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

Author: nickroci

README.md

@@ -10,9 +10,9 @@ A personal memory system for coding agents. Built for Claude Code; lives outside
 
 ## Why this exists
 
-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.
+The memory features that exist today — `CLAUDE.md`, Cursor rules, ChatGPT memory, the various provider built-ins — are *there* but I always felt they did not surface the lessons that had been learned well enough. They seem to be rarely useful, bloat the context, get ignored and when they fire they often feel trivial: 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 over and over and I did not want to have to manually curate an ever changing set of shared knowledge per project and globally.
 
-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.
+So I wondered what could be achieved with a much more advanced system. There are obviously many alternatives but none had all the features that I wanted. Real memory is salience-gated at write time, decays without reinforcement, mutates on retrieval, resists deletion of high-importance 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 (currently 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.
 
 Ultan watches your conversations as you work, learns your preferences and conventions, and surfaces them when they matter. It's the "remember when you told me to always use uv" that you wish Claude already did natively, except organised, deduplicated, validated, and proactively consulted before the agent interrupts you to ask something you've already answered.