Engineering Blog

    Deep dives into AI coding tools, architecture patterns, and how Atlarix fits into your workflow.

    We Published Research: Blueprint and Context Management in Multi-Repo Agentic Coding

    Deep Dive

    We ran a controlled benchmark comparing Blueprint-assisted vs unassisted agentic exploration on a production multi-repository workspace. Here's what we found — including a counterintuitive result about total context usage.

    May 2026~6 min read

    How Atlarix Gives the AI Your Whole Codebase — Without RAG or Embeddings

    Deep Dive

    Everyone reaches for embeddings and a vector database. Atlarix doesn't — no embedding model, no vector index, nothing uploaded. Here's how bundled ripgrep and the model's own reasoning give it real, whole-codebase context, and why that's the better call for code.

    June 2026~7 min read

    How to Evaluate a Coding Agent — What Actually Matters

    Deep Dive

    Benchmarks, demos, and feature lists don't tell you if a tool works on your codebase. Here's the checklist we use — and that you can use — to evaluate any coding agent on what actually matters: model access, retrieval, control, and data path.

    June 2026~7 min read

    Why Local LLMs Are the Future of Private AI Coding

    Deep Dive

    Run the full coding workflow on your own hardware with Ollama or LM Studio. Here's why local models actually perform in a desktop workstation, where they often don't elsewhere.

    June 2026~6 min read

    Why Atlarix Is a Desktop App, Not an Editor Extension

    Product

    Most AI coding tools ship as editor forks or plugins. Atlarix is a standalone desktop workstation that sits beside any editor. Here's the capability case — local models, the approval queue and sandbox, and a browser/terminal around the agent.

    June 2026~5 min read