Catalog

159 products for building with AI models, from the apps and editors you work in to the model servers and cloud services underneath. Each has a page of what its maker's own pages say: what it does, where it runs, where its models run, and how to set it up with a local model.

Start here: The products at each layer: Every product, at each layer it works at, grouped by the form it comes in, with a filter for compliance items.

See how the pieces fit

• Where everything fits: Every layer of the stack in one picture, from you to a model. Select a layer to see its products.
• Hybrid model setups: how the pieces fit: How a coding tool, a proxy, a model server and a cloud provider fit together, and which of them you need.

Local and cloud models together

• Hybrid on your own machine: The apps, command-line tools and editors you install on your own machine, with the model servers that come as one, and what their pages say about using a local model beside a cloud one.
• Hybrid in a container environment you run: The services you run in containers, on a server or in your own cloud account, and the inference servers you host, and what their pages say about using a local model beside a cloud one.
• Hybrid as a cloud service: The products that run on a vendor's servers, and what their pages say about reaching models from more than one provider.

Your data when you call a cloud model

• Customer data, by cloud and model: what Amazon Bedrock, Microsoft Foundry and Gemini Enterprise Agent Platform say happens to prompts and outputs, by model, routing tier and region.

Rendered 2026-10-29

The catalog is an opinion offered to help with a decision, and the vendor's page is the authority. Each line links the page it summarizes and the date we read it; if you restate a line, carry its link and read date with it. How the catalog is made, and the terms.