How AI Agents Search Their Memory скачать в хорошем качестве

How AI Agents Search Their Memory

In my last video, I covered how AI agents store memory. But storing it is only half the problem. In this one, we dig into how agents retrieve the right memory at the right time. I cover keyword search, semantic search, hybrid retrieval, and re-ranking, then dig into how OpenClaw implements all of it in practice using SQLite, BM25, and vector embeddings. --- What you'll learn: How keyword search (grep, BM25) and semantic search (embeddings, vector similarity) each work -- and where they break down Why hybrid search beats both approaches alone, and how weighted fusion and reciprocal rank fusion combine results What re-ranking is, when to use it, and the cost/latency tradeoff How a production agent memory system stores chunks, indexes them with FTS5 and sqlite-vec, and runs hybrid search in parallel The two-step memory pattern: search then get, and why it keeps context windows lean How incremental sync works: file watchers, content hashing, embedding caches, and full reindex triggers --- Watch the full series: Part 1: How AI Agents Remember Things (the write path) →    • How AI Agents Remember Things   Part 2: How AI Agents Search Their Memory (this video) We use OpenClaw as the real-world case study -- it's a clean open-source implementation that shows these patterns in practice. --- Resources mentioned: OpenClaw: https://github.com/openclaw/openclaw SQLite FTS5 documentation: https://www.sqlite.org/fts5.html sqlite-vec extension: https://github.com/asg017/sqlite-vec OpenAI Embeddings API: https://platform.openai.com/docs/guid... QMD by Toby Lutke: https://github.com/tobi/qmd pgvector (Postgres vector extension, mentioned as an alternative): https://github.com/pgvector/pgvector Affiliate links — I may earn a commission or credits at no cost to you: Pinecone (dedicated vector database, mentioned as an alternative): https://try.pinecone.io/vc9wh4lq5uj6 → Want to build your own AI agent? https://www.damiangalarza.com/ai-agen... → Newsletter (practical AI without the hype): https://www.damiangalarza.com/newslet... --- Timestamps: 0:00 - The retrieval problem 0:35 - Keyword search: grep and BM25 1:12 - Semantic search and how embeddings work 2:04 - Vector databases and nearest neighbor search 3:41 - Where semantic search breaks down 4:05 - Hybrid search: combining keyword and semantic 4:18 - Weighted fusion vs. reciprocal rank fusion 5:01 - Re-ranking: trading speed for accuracy 6:12 - OpenClaw's implementation walkthrough 7:10 - Embedding providers and auto-selection 8:08 - The SQLite schema: FTS5, sqlite-vec, and the embedding cache 9:33 - The search pipeline step by step 10:54 - Memory tools: search and get 11:08 - Why the two-step pattern keeps context windows lean 11:40 - The incremental sync and indexing pipeline 12:44 - Wrap-up --- Work with me: ∙ 1:1 Coaching (agent architecture, Claude Code, AI workflows): https://www.damiangalarza.com/coachin... ∙ All services: https://www.damiangalarza.com/services About me: I'm Damian Galarza, a software engineering leader and former CTO with 15+ years building SaaS products. I make practical AI engineering tutorials and share what I'm learning about agent architecture, LLM applications, and building production AI systems. Connect: Newsletter: https://www.damiangalarza.com/newslet... LinkedIn:   / dgalarza   Blog: https://www.damiangalarza.com #AIAgents #VectorSearch #RAG #SemanticSearch #OpenClaw