Enola-A deterministic architecture graph for developers and AI agents
Together with a friend, we were developing a golf application. Our codebase grew rapidly and became split between multiple repositories: the iOS app, Android app, backend, front-end, and extra tooling. Both of us also work in larger scale-ups, and we saw the same problem: understanding large distributed codebases becomes progressively harder. Yay for microservices. It takes time to understand and answer questions like: - What calls this function? - What is the impact of changing this interface? - Is this code actually reachable and used? Not a secret that both of us embrace the leverage AI…
In plain words
Enola is a tool that maps and visualizes the architecture of distributed codebases across multiple repositories. It helps developers and AI agents quickly understand code relationships, trace function calls, assess the impact of changes, and identify unused code. Rather than repeatedly discovering architecture through searching, Enola provides a deterministic graph that persists across sessions, making it easier for both humans and AI coding agents to navigate complex microservice systems.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Together with a friend, we were developing a golf application. Our codebase grew rapidly and became split between multiple repositories: the iOS app, Android app, backend, front-end, and extra tooling. Both of us also work in larger scale-ups, and we saw the same problem: understanding large distributed codebases becomes progressively harder. Yay for microservices. It takes time to understand and answer questions like: - What calls this function? - What is the impact of changing this interface? - Is this code actually reachable and used? Not a secret that both of us embrace the leverage AI coding agents bring. But … AI agents spend a surprising amount of time understanding and rediscovering architecture. For them, architecture is a result of greps and, at times, assuming dependencies. With a new session, they rediscover the architecture again. Yet, architecture is deterministic. To introduce any changes, you need to understand the architecture. Over months, we optimised and built Enola to manage that hurdle. Enola is an open-source architecture engine that exposes an MCP server. Index any codebase into a persistent knowledge graph. If needed, combine multiple repositories into a graph of graphs. While constructing the graph, Enola parses the repository without using an LLM. The graph is built deterministically from source code. Outcome: A structured, deterministic architectural model of your system (a collection of multiple repositories). Why open-source? Our goal is to provide engineering tools to manage the “code inflation”. There is a lot more code being produced, and codebases grow faster and faster. But the architectural integrity is still needed. Enola exists because software engineering still begins with understanding a system before changing it. Key Features (subset): 1. Impact Analysis: Determine the "blast radius" of a change by querying the graph of relationships between symbols, modules, and API routes. Simply ask: “If I change this, what breaks?” 2. Dead Code Discovery: Identify unused code paths and orphaned components that aren't reachable through your defined entry points. 3. Dependency Analysis (We called it traverse, because why not): Trace the dependencies, both downstream and upstream. You can simply ask Enola: “What depends on X?” 4. Multi-Repo Context: Enola supports a "graph of graphs," allowing you to index and query relationships across as many repositories as your architecture requires. So stack them up! 5. Performance: Enola runs fast, given its architecture, naturally depending on your codebase. Give it a try! Curious. We are open-source, building in public. You can find the documentation and source in the link above. If you have a complex codebase and would be willing to test Enola, I’d appreciate the feedback. Tell us what works, what is missing.
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, July 2026
the whole month →- IR
I might be the only SRE on Earth with his own bowling center. It's a more in-depth gig than you'd think. My family and I bought an abandoned 8-lane bowling center in the rural mid-west. In our small town there weren't many recreation options for families. You've heard of a food desert? This is an R&R desert. It had been abandoned for a good reason. The roof leaks, the electrical system was constantly surging, and my 70-year-old bowling equipment (still) doesn't work perfectly. The system that keeps your score is particularly interesting to me. It's the thing you watch during your game, but…
Life & fun · Jul 2026
- EElevators▲1,680
Life & fun · Jul 2026 · john.fun
- 1W18 Words▲1,160
Life & fun · Jul 2026 · 18words.com
- BA
Over the past few months, our team has been building more and more slidedecks using web frontend technologies with coding harnesses like Claude Code, but a common complaint is to make even small edits we need to edit the code either manually or via the harness. To avoid this loop, I ended up creating Bento, a single HTML file with everything you need in a slide tool including animations and shared editing. There's no install or cloud login, everything works offline. The default deck is around 560 KB and it doesn't need to fetch anything once you got it. Open it in a browser and then you can…
Dev tools · Jul 2026 · bento.page
- GG
A few days ago I found myself trying out GLM 5.2 and was really positively impressed. The capabilities and security I was getting from this LLM are similar to those I've gotten from models like Claude or GPT, and this really surprised me. But then I thought, "I wonder how it would work on a normal computer like mine," and above all, "I wonder if it would work without going into OOM on a computer like mine." So I started working with the help of agents to test this possibility. I started converting the model to int4, understanding MTP usage, and if possible implementing DSA for long context.…
AI · Jul 2026 · github.com
