Comparisons

Comparisons

vs Claude Built-In Memory

Feature	SmartAssist	Claude memory
Learning	Active RLHF — explicit feedback	Passive observation
Tracking	Thompson Sampling — exact scores	No visibility
Priority	Focuses on weak areas (<70%)	All info equal
Search	1024-dim hybrid + cross-encoder reranking	Has embeddings, no feedback loop
Time decay	30-day half-life	Old info never fades
Portability	Works on any project via smartassist init	Tied to Claude account
Privacy	100% local	Cloud-based
Cost	Zero	$$$ per token

vs CLAUDE.md

Aspect	SmartAssist	CLAUDE.md
Update speed	Instant ("thumbs down")	10-30 min (edit, PR, merge)
Verification	Measurable scores	No way to know if Claude learned
Context usage	~200 tokens (relevant only)	~2000 tokens (entire file)
Maintenance	Self-maintaining	Manual editing
Team standards	Personal only	Shared across team
Onboarding	Starts from scratch	Immediate access

Best approach: use both. CLAUDE.md provides team-wide standards (Layer 1). SmartAssist provides personal learning and verification (Layer 2).

vs Generic RAG

Feature	SmartAssist	Generic RAG
Learning	Retrieve → Generate → Get Feedback → Improve	Retrieve → Generate (no learning)
Quality	Every lesson scored by Thompson Sampling	All documents equal weight
Search	Hybrid (vector + BM25) + cross-encoder	Pure vector search
Personalization	Adapts to YOUR workflow	Same for everyone
Portability	pip install + smartassist init	Usually hardcoded to one project

vs Claude Code Skills

Skills (like react-native-best-practices from Callstack) and SmartAssist both inject knowledge into Claude — but they work in fundamentally different ways.

TL;DR: Skills teach Claude generic domain knowledge. SmartAssist teaches Claude project-specific lessons. Skills are the textbook. SmartAssist is the field notes.

Dimension	SmartAssist	Claude Code Skills
What it is	Portable pip-installed package: MCP server + vector DB + feedback loop + 5 hooks + CLI	Markdown instruction files with YAML metadata
Knowledge type	Project-specific — from real PRs and commits	Generic domain — applicable to any project
Search method	Hybrid vector (1024-dim) + BM25 + cross-encoder	String matching on description
Learning	Active — Thompson Sampling + feedback loop	Static — only updates when author publishes
Feedback loop	Yes — thumbs up/down, corrections, rag_feedback tool	None
Relevance scoring	Continuous 0-100% with cross-encoder precision	Binary — matches or doesn't
Observability	Full — 20,070+ logged entries with decision funnels	Minimal — invisible to user
Infrastructure	pip install -e, LanceDB, BAAI/bge-m3 + cross-encoder	Zero — just markdown files

The Three-Layer Knowledge Stack

Layer	System	What it provides	Example
1. CLAUDE.md	Static file	Team-wide standards	"Coverage thresholds: branches 79%, lines 89%"
2. Skills	Markdown plugins	Generic domain expertise	"Use Hermes profiling to find JS thread bottlenecks"
3. SmartAssist	MCP + LanceDB + RLHF	Project-specific lessons	"Mock @react-native-firebase/analytics before imports"

Each layer adds specificity. CLAUDE.md says what standards to follow. Skills say how to do things generically. SmartAssist says what we learned doing it in this exact codebase.