{"slug": "open-models-are-everywhere-but-what-is-an-open-stack", "title": "Open Models Are Everywhere. But What Is an Open Stack?", "summary": "Developer Rijul, creator of LiveReview, explains the concept of an 'open stack' in AI, contrasting it with open-weight models. He notes that open-weight models like Llama, Mistral, Gemma, and Qwen provide only the final weights, while an open stack includes the full pipeline—training data, code, evaluation, and tooling—citing OLMo by Ai2 and BLOOM by BigScience as examples. He argues that openness is a spectrum across the model development pipeline.", "body_md": "*Hello, I'm Rijul, and I'm building LiveReview — a blast-radius aware AI code review built for your business-critical systems. [Star us](https://github.com/HexmosTech/LiveReview/) to help devs discover the project, give it a try, and share your feedback to help improve the product.*\n\nYou may have downloaded **open models**, or at least heard of them.\n\nThese are models whose weights are made available for others to download and run on their own machine or infrastructure.\n\nUsually, when accessing a model, you might do something like:\n\n```\nYour app → API → Model\n```\n\nBut with an open-weight model, you can download the model weights and run them yourself. So it becomes more like:\n\n```\nYour app → Your infrastructure → Model\n```\n\nSome examples of **open-weight models** are **Llama, Mistral, Gemma, and Qwen**.\n\nNow let's talk about another thing which you may or may not have heard of.\n\nIt's called **Open Stack**.\n\nThe model you get doesn't just happen by itself.\n\nThere are various layers involved in creating the final model that you use.\n\nFor example, you can think about the **model development pipeline** like this:\n\n```\nTraining data\n     ↓\nTraining code / recipes\n     ↓\nModel\n     ↓\nEvaluation\n     ↓\nInference\n     ↓\nDeployment\n```\n\nSo when we talk about an **open stack**, it's more like getting the model along with information and tooling around how it was created and operated.\n\nYou might get information about:\n\nWhen you get an open-weight model, you generally won't get this much information.\n\nBut **open stack isn't a standardized technical category**. It is better to think of openness as a spectrum across different parts of the model development pipeline.\n\nFor example, a company might release:\n\nbut **not** release:\n\nSo while the model itself is available, much of the process behind creating it remains closed.\n\nSome examples of projects that take a much more open approach to the model development process are **OLMo by Ai2** and **BLOOM by BigScience**.\n\nIf you've never heard of **open stacks** before, take a look at some of these projects.\n\nIt's interesting to see not just the final model, but also the **training, data, evaluation, and tooling that went into creating it**.\n\nYour team's attention is limited, and the deluge of AI-generated code is making it harder to keep production reliable and secure without slowing you down.\n\nI'm building **LiveReview**, a blast-radius aware AI code review built for your business-critical systems.\n\nInstead of presenting every diff with equal emphasis, **LiveReview scores each change by blast radius — how far its impact reaches through your call graph — so you can focus attention where it actually matters.**\n\nSpend code review effort where business risk is highest — not spread evenly across every diff.\n\n⭐ Star it on GitHub: \n\nLiveReview is an AI code reviewer that scores every hunk of a diff by **blast radius**: how far a change reaches through your call graph, how much persistent state it touches, and how well-tested it is. A 3-line change to a shared auth check can outrank a 300-line UI tweak. Your team's attention goes to the highest-risk code first, not spread evenly across every diff.\n\n*LiveReview's Blast Radius & Review Priority scoring, live in the diff viewer.*\n\n| The exact math, not a black box | Visualize blast radius at a glance | Every factor that feeds the score | \n|---|---|---|\n\n**Here's the goal:**\n\n**Click below to try LiveReview with your codebase:**", "url": "https://wpnews.pro/news/open-models-are-everywhere-but-what-is-an-open-stack", "canonical_source": "https://dev.to/rijultp/open-models-are-everywhere-but-what-is-an-open-stack-1pd3", "published_at": "2026-09-08 21:01:55+00:00", "updated_at": "2026-09-08 21:28:46.295979+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research", "developer-tools"], "entities": ["Rijul", "LiveReview", "Llama", "Mistral", "Gemma", "Qwen", "OLMo", "Ai2"], "alternates": {"html": "https://wpnews.pro/news/open-models-are-everywhere-but-what-is-an-open-stack", "markdown": "https://wpnews.pro/news/open-models-are-everywhere-but-what-is-an-open-stack.md", "text": "https://wpnews.pro/news/open-models-are-everywhere-but-what-is-an-open-stack.txt", "jsonld": "https://wpnews.pro/news/open-models-are-everywhere-but-what-is-an-open-stack.jsonld"}}