Embeddings
6 articles about embeddings.
Long-Term Memory Without Going Bankrupt - SQLite with Local Embeddings
Cloud vector databases are expensive for AI agent memory. SQLite with local embeddings gives you persistent long-term memory at near-zero cost.
Open Source AI Memory Storage - The Deduplication Challenge
Building deduplicated memory storage for AI agents is harder than it looks. The real challenge isn't storing memories - it's knowing when two memories are
Is RAG Dead? Bigger Context Windows Shift the Use Cases
With context windows growing past 1 million tokens, many RAG use cases are better served by stuffing documents directly into context. RAG is not dead but
Self-Hosted Vector Memory for AI Agents
How to build a local-first vector memory system for AI agents using self-hosted embeddings. Keep your agent's memory private, fast, and under your control.
Tiered Memory for Desktop Agents - Plain Text First, Vector Search for Long-Term
How desktop AI agents should handle memory: plain text for recent context and vector embeddings only for long-term recall. A practical approach to agent
Embeddings vs Tokens - How AI Agent Memory Actually Works
Embeddings aren't tokens. They're dense vector representations that capture semantic meaning and power similarity search for AI agent memory retrieval.