Open Models Are Everywhere. But What Is an Open Stack?

Hello, I'm Rijul, and I'm building LiveReview — a blast-radius aware AI code review built for your business-critical systems. Star us to help devs discover the project, give it a try, and share your feedback to help improve the product.

You may have downloaded open models, or at least heard of them.

These are models whose weights are made available for others to download and run on their own machine or infrastructure.

Usually, when accessing a model, you might do something like:

Your app → API → Model

But with an open-weight model, you can download the model weights and run them yourself. So it becomes more like:

Your app → Your infrastructure → Model

Some examples of open-weight models are Llama, Mistral, Gemma, and Qwen.

Now let's talk about another thing which you may or may not have heard of.

It's called Open Stack.

The model you get doesn't just happen by itself.

There are various layers involved in creating the final model that you use.

For example, you can think about the model development pipeline like this:

Training data
     ↓
Training code / recipes
     ↓
Model
     ↓
Evaluation
     ↓
Inference
     ↓
Deployment

So 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.

You might get information about:

When you get an open-weight model, you generally won't get this much information.

But 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.

For example, a company might release:

but not release:

So while the model itself is available, much of the process behind creating it remains closed.

Some examples of projects that take a much more open approach to the model development process are OLMo by Ai2 and BLOOM by BigScience.

If you've never heard of open stacks before, take a look at some of these projects.

It's interesting to see not just the final model, but also the training, data, evaluation, and tooling that went into creating it.

Your 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.

I'm building LiveReview, a blast-radius aware AI code review built for your business-critical systems.

Instead 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.

Spend code review effort where business risk is highest — not spread evenly across every diff.

⭐ Star it on GitHub:

LiveReview 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.

LiveReview's Blast Radius & Review Priority scoring, live in the diff viewer.

Here's the goal:

Click below to try LiveReview with your codebase: