OctopusGarden – An autonomous software factory (specs in, code out)
I built this over the weekend after reading about StrongDM's software factory (their writeup: https://factory.strongdm.ai/, Simon Willison's deep dive: https://simonwillison.net/2026/Feb/7/software-factory/, Dan Shapiro's Five Levels: https://www.danshapiro.com/blog/2026/01/the-five-levels-from...). OctopusGarden is an open-source implementation of the pattern StrongDM described: holdout scenarios, probabilistic satisfaction scoring via LLM-as-judge, and a convergence loop that iterates until the code works; no…
What it does
In the maker’s words, at launch
I built this over the weekend after reading about StrongDM's software factory (their writeup: https://factory.strongdm.ai/, Simon Willison's deep dive: https://simonwillison.net/2026/Feb/7/software-factory/, Dan Shapiro's Five Levels: https://www.danshapiro.com/blog/2026/01/the-five-levels-from...). OctopusGarden is an open-source implementation of the pattern StrongDM described: holdout scenarios, probabilistic satisfaction scoring via LLM-as-judge, and a convergence loop that iterates until the code works; no human code review in the loop. What stood out to me was that this architecture largely rhymes with the coding workflows I and others already do with coding agents. It's basically automating the connective tissue between the workflows I was already doing in Claude Code, and then brute-forcing a result. In the dark factory model, a spec goes in, code gets generated, built in Docker, validated against scenarios the agent never saw, scored, and failures feed back until it converges. I've tried it with mostly standard CRUD/REST API apps and it works. I haven't tried anything with HTML/JS yet. You can try the sample specs in the repo. Some raw notes from the experience: 1. I don't want to maintain the code these factories generate. It works. The phenotype is (largely) correct, but the genotype is pretty wild and messy. I did not use OctopusGarden to build OctopusGarden (you can tell because it uses strict linting and tests). I know the point of these systems is zero human in the loop, but I think there's a real opportunity to get factories to generate code that humans actually want to maintain. I'm going to work on getting OctopusGarden there. 2. Compliance might be a nightmare. In my day job I think a lot about ISO 27001 and SOC 2 compliance. The idea of deploying dark-factory-generated projects into my environments and checking compliance boxes sounds painful. That might just be the current state of OctopusGarden and the code it generates, but I think we can get to a point where generated code is completely linted, statically checked, and tested inside the factory. That's not OctopusGarden today, but maybe it will be there next week? I can see this moving fast. 3. These dark factory apps will be hard to debug. There was a Claude outage today and I couldn't run my smoke tests or generate new apps. I don't want to maintain services that can't be debugged and fixed by a human in a pinch. We're already partially there with AI-assisted code, but this factory-generated code is even more convoluted. Requiring AI to create a new app version is probably worth it...but it's still yet another thing between you and quickly patching an urgent bug. 4. Security needs a better story. These things need real security hardening. Maybe that's just better spec files and scenarios, maybe it's something more. I'm going to drink a strong cola and think about this one. 5. The unit of responsibility keeps growing. Last year we said code must come in PR-sized bites — that's how we manage risk. Now we're talking about deploying meshes of services created and deployed with no humans in the loop (except at creation). AI-generated services could really push the scale of what people are willing to accept responsibility for. Most SRE teams manage 1-5 services at big companies. Will that number increase per team? How much GDP is one person willing to manage via agents? Just a shower thought. 6. I was surprised this works. I'm surprised at how easy it was to make. I'm surprised more of these aren't out there already. I only did a couple of GitHub searches and didn't find many. I'm bad at searching. Sorry if I didn't find your project.
Does the same job
all alternatives →- FFFactory Factory, open-source alternative to Codex App for ClaudeFeb 2026 · github.com · ▲6
It uses your local Claude and GitHub CLI and git worktrees, so there's nothing to configure beyond what you already have. Our AI coding workflow was a hodgepodge of scripts and ad-hoc processes, so we built this to centralize and streamline - and most importantly adapt as things change. Some cool features so far (lots more planned): 1. One click github issue to agent working on it. 2. Ratcheting mode, where it watches CI for code review comments and build failures, and automatically fixes them. Would love genuine feedback, bug reports, PRs, suggestions, etc.
- IAIsomorƒ, an experimental software development paradigm2017 · ▲23
Hi HN! We’re the founders of isomorƒ (https://isomorf.io), an experimental software development paradigm. isomorƒ is a structured cloud IDE designed around the ideas of functional programming and serverless architecture and built to reduce barriers to entry and increase developer efficiency. We wanted to see if we could reimagine the software development process in a way that would be more automated and assistive, less redundant, and more flexible. Drawing heavily on the concepts of functional purity, static typing, and statelessness, our premise was to design a simple, "low power"…
- NTNoodles – Turn any codebase into a diagram with Claude and Tree-sitterFeb 2026 · github.com · ▲6
I built a CLI tool that turns codebases and PRs into diagrams so you can quickly understand how things fit together. Originally made it because I couldn't follow my own AI-generated repos. Just shipped a big update: - Switched from D2 to Mermaid for rendering - Tree-sitter AST parsing + agentic flow instead of raw LLM calls. ~50x faster. - Works on any GitHub repo or PR, not just local - Dropped the web frontend, it's just a CLI now - Published as a pip package Still a ton to improve and I'm building fast. Feedback, issues, PRs all welcome.
- MImybf.io - platform for software reviews with social network aspect2021 · ▲10
Hi! Recently I've launched - mybfio.io - platform for software reviews with social network aspect. Prehistory Many great system are already in place that allow people to search and rate software products, including the site I am publishing this post on. However I have always felt that those systems are not specifically centered around product/software development lifecycle (releases, real users feedback over a product entire lifetime, so on) and often too broad or not designed specifically for that type of work, which is ok. Why? As an opensource author I would like to have constant…
- IMI made an open-source Replit2024 · github.com · ▲9
I spent the past few weeks making an open source cloud code editing environment with an AI copilot and multiplayer collaboration! It's fully self-hostable in 5-10 minutes. There's a lot of minor improvements to be made, and some are already listed in the Github issues. Let me know what you think and feel free to try it out.
- WMWe made our CRM/ERP platform open-source thanks to AI2025 · github.com · ▲6
We've recently made our product, ozma.io, open-source. It's a CRM/ERP platform for building enterprise systems. We believe that AI will soon handle implementing most of the boilerplate and UIs in the specialized business software. Just look at what lovable.dev does today! Soon products which make creating business software easier for developers will become obsolete, or transform into "libraries" to be used by AIs. We are losing this race, so we go the second route — publish everything and go on building other products on top of it. GitHub repo URL:…
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, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
