trelix v1.0 to v2.7: When "It Works" Meets "It Scales"
Twelve days after I shipped trelix v1.0.0, I was staring at a RetrievalConfig object with two conflicting sets of values and no idea which one was act…
Latest Architecture news from Tech News
Twelve days after I shipped trelix v1.0.0, I was staring at a RetrievalConfig object with two conflicting sets of values and no idea which one was act…
We didn't give our AI agent one big brain. We gave it skills. We built a conversational AI inside an enterprise SaaS platform, where users get work do…
After building 50+ AI systems, here is what we know about agentic coding models and the burgeoning open-source AI frontier, particularly with the grou…
Most MCP servers I see in production are stuck at Level 1 or 2. They wrap an API, expose some tools, and stop there. The result: an agent that can tec…
The first number anyone quotes when asked what generative AI costs is a per-token figure. It is a comfortable number — small, unambiguous, available o…
The Token Tax Problem: How I Built a Super Memory Layer for AI Coding Assistants We Solved the Wrong Problem First When AI coding assistants arrived, …