Making Claude Code Actually Remember Things

Artem Zhutov ยท Intermediate ยท๐Ÿ” RAG & Vector Search ยท2mo ago
Skills: RAG Basics90%
๐Ÿ“š Obsidian x Claude Code Lab: https://lab.artemzhutov.com โ†’ Build your own AI memory system, vault architecture, and agent skills - live, with me ๐Ÿ’ฌ Discord: https://discord.gg/g5Z4Wk2fDk This is one week of my work. Every node is a conversation with Claude Code. Every link is a file it touched. Claude Code already has memory - but it doesn't search across your vault. It doesn't know what you worked on in a different project yesterday. QMD fills that gap. https://github.com/tobi/qmd ๐ŸŽ Free: Claude Code memory skills โ†’ Your sessions become searchable memory โ†’ Subscribe free, download link in welcome email ๐Ÿ‘‡ https://memory-artemzhutov.netlify.app Follow me: Substack: https://artemxtech.substack.com/ X: https://x.com/ArtemXTech GitHub: https://github.com/ArtemXTech Timestamps: 0:00 This is one week of my work 1:06 Inside the vault 1:25 "What did I decide last week?" - 0.3 seconds 2:22 Setting up the search engine 2:47 Why brute force doesn't work 4:42 The results blew my mind 5:23 The problem nobody talks about 6:24 How the search actually works 7:19 Semantic search - it understands what you mean 8:59 Finding patterns I didn't know existed 10:34 "Show me what I missed" 13:33 Loading context without copy-paste 15:17 "What did I do yesterday?" 18:28 Topic search + the graph 20:26 The graph visualization 23:49 Three ways to use this 24:13 OpenClaw - access your vault from anywhere 27:01 Claude Code x Obsidian Lab 27:36 Grep vs BM25 vs vector - which one wins? 29:06 The actual search results 30:34 BM25 vs semantic search 31:28 Hybrid search - best of both 32:16 Embedding YouTube videos into your vault 34:38 Finding ideas you never acted on 37:06 711 sessions indexed in seconds 38:09 Making sessions searchable 39:59 The full stack 41:41 How to get this
Watch on YouTube โ†— (saves to browser)
Sign in to unlock AI tutor explanation ยท โšก30

Related AI Lessons

โšก
Ever Wondered How to Make Your RAG More Effective?
Improve your RAG effectiveness by connecting instead of searching
Medium ยท RAG
 โšก
Why StarRocks Is Better Than Elasticsearch for RAG and AI-Powered Vector Search Analytics
Learn why StarRocks outperforms Elasticsearch for RAG and AI-powered vector search analytics, and how to apply this knowledge to improve your data architecture
Medium ยท LLM
 โšก
Production RAG: Shipping a RAG System Into an Enterprise Product
Learn how to ship a RAG system into an enterprise product, overcoming operational realities and challenges beyond the demo stage
Medium ยท RAG
 โšก
HyDE: Search With the Answer You Wish You Had
Learn how HyDE improves search by using the answer you wish you had as a query, and why traditional question-based searches are limited
Medium ยท RAG

Chapters (28)

This is one week of my work
1:06 Inside the vault
1:25 "What did I decide last week?" - 0.3 seconds
2:22 Setting up the search engine
2:47 Why brute force doesn't work
4:42 The results blew my mind
5:23 The problem nobody talks about
6:24 How the search actually works
7:19 Semantic search - it understands what you mean
8:59 Finding patterns I didn't know existed
10:34 "Show me what I missed"
13:33 Loading context without copy-paste
15:17 "What did I do yesterday?"
18:28 Topic search + the graph
20:26 The graph visualization
23:49 Three ways to use this
24:13 OpenClaw - access your vault from anywhere
27:01 Claude Code x Obsidian Lab
27:36 Grep vs BM25 vs vector - which one wins?
29:06 The actual search results
30:34 BM25 vs semantic search
31:28 Hybrid search - best of both
32:16 Embedding YouTube videos into your vault
34:38 Finding ideas you never acted on
37:06 711 sessions indexed in seconds
38:09 Making sessions searchable
39:59 The full stack
41:41 How to get this
Up next
Watch this before applying for jobs as a developer.
Tech With Tim
Watch โ†’