LangGraph architecture that scales (hexagonal pattern, 110 tests)
I kept hitting the same wall with LangGraph: tutorials show you how to build a graph, not how to maintain one when you have 8 nodes, 3 agents, and shared state across subgraphs. So I built a reference architecture with: - Platform layer separation (framework-independent core) - Contract validation on every state mutation - 110 tests including architecture boundary enforcement - Patterns that AI coding agents can't accidentally break Repo: https://github.com/cleverhoods/sagecompass Wrote about the patterns:…
In plain words
LangGraph architecture that scales is a reference implementation for building maintainable LangGraph applications at scale. It addresses the gap between basic tutorials and production systems by providing a hexagonal architecture pattern with platform layer separation, contract validation on state mutations, and 110 comprehensive tests including boundary enforcement. Designed for developers building multi-node graphs with multiple agents and shared state, it includes patterns specifically designed to prevent common architectural violations. The project is MIT licensed and available on GitHub.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
I kept hitting the same wall with LangGraph: tutorials show you how to build a graph, not how to maintain one when you have 8 nodes, 3 agents, and shared state across subgraphs. So I built a reference architecture with: - Platform layer separation (framework-independent core) - Contract validation on every state mutation - 110 tests including architecture boundary enforcement - Patterns that AI coding agents can't accidentally break Repo: https://github.com/cleverhoods/sagecompass Wrote about the patterns: https://dev.to/cleverhoods/from-prompt-to-platform-architect... It's MIT licensed. Would love feedback on the approach - especially from anyone who's scaled LangGraph past the tutorial stage.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
Launched alongside, January 2026
the whole month →- IN
Hey HN! I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code. Of course no-code doesn't mean no-engineering. This project took a lot more manual labor than I'd hoped! I wrote a deep dive on the workflow and some thoughts about the future of AI coding and creativity: http://cannoneyed.com/projects/isometric-nyc
AI · Jan 2026 · cannoneyed.com
Automatic AI-powered code reviews the moment you open a PR
Dev tools · Jan 2026 · kilo.ai
