When I wrote the first post about openLight in March, the project was a 1.0 commit, a Raspberry Pi,...
What I Learned Building a Lightweight Local AI Agent
Related
I Cut My LLM API Bill by 38% With a Caching Layer — Here's the Complete Implementation
A practical, code-heavy tutorial on building a smart caching layer for LLM API calls. Covers exact-match hashing, semantic similarity caching with embeddings, temperature threshold...
I got tired of re-explaining myself to AI. So I built a memory graph
Every AI conversation starts from zero. You explain your architecture. The next day, you explain it...
Why production RAG fails — and the boring metrics that fix it
Diagnose retrieval failures, measure recall as its own metric, and add a cross-encoder reranker to a LangChain + FAISS RAG pipeline.