---
title: "Windows local AI: the stack and a coding agent"
description: "What Windows ML, Foundry Local, and Phi Silica do, what they do not give a coding agent, and the WSL2 path that works today."
canonical: https://oloop.run/guides/windows-local-coding-agent
updated: 2026-10-20
---

# Local AI on Windows: what ships, and how to run a coding agent

Windows has a native local AI stack: Windows ML, Foundry Local, and the Windows AI APIs around Phi Silica. None of them is a portable coding-agent runtime with a manifest, a lock, and evidence. oloop's supported path on Windows today is WSL2 plus a Linux setup; native oloop support and a qualified Foundry Local endpoint are not built or measured.

## What Windows ships

Microsoft ships 3 layers, and the names are easy to confuse.

The Windows local AI stack, by layer. Verified against Microsoft Learn on 2026-10-20.

| Layer | What it is | Interface | What it is not |
| --- | --- | --- | --- |
| Windows ML | The OS inference framework, built on ONNX Runtime; CPU, GPU, and NPU execution; an experimental GGUF path. | App API and execution providers. | Not an agent runtime, not a model catalog, and not an endpoint by itself. |
| Foundry Local | Microsoft's local runtime and SDK, with curated models and automatic acceleration that varies by OS and device. It can expose an OpenAI-compatible local server. | SDK, plus an optional local server. | Not a multi-user server stack, and it has no manifest, lock, or evidence layer. |
| Windows AI APIs / Phi Silica | Ready-to-use app APIs, with Phi Silica as a local language model under a Limited Access Feature, mostly on Copilot+ PCs. | App API. | Not a general OpenAI endpoint for a CLI coding agent. |

Sources: Windows ML, Foundry Local, Windows AI overview, and Phi Silica on Microsoft Learn.

- [Windows ML](https://learn.microsoft.com/en-us/windows/ai/new-windows-ml/overview)
- [Foundry Local](https://learn.microsoft.com/en-us/azure/foundry-local/what-is-foundry-local)
- [Windows AI overview](https://learn.microsoft.com/en-us/windows/ai/overview)
- [Phi Silica](https://learn.microsoft.com/en-us/windows/ai/apis/phi-silica)

## What the stack leaves out

The layers handle inference. An agent also needs a pinned configuration, a harness that behaves the same on another machine, a lock, checksums, evidence, and one root you can remove. oloop adds those, and it does not replace the runtime underneath.

What each side provides.

| Concern | Windows native stack | oloop |
| --- | --- | --- |
| Runtime | Windows ML, Foundry Local, Phi Silica | References the runtime; does not replace it |
| Model catalog | Curated in Foundry Local | Setup catalog with pins and evidence |
| Acceleration | Chosen by the runtime and device | Recorded in the qualification, not assumed |
| API shape | Local server (Foundry Local) | A manifest, not an API |
| Harness portability | Not addressed | One pinned harness under the root |
| Lock | Not addressed | oloop.lock pins host, harness, and model |
| Checksums | Not addressed | The bundle and model rows carry digests |
| Evidence | Not addressed | A qualification record per machine class |
| One root | Not addressed | Everything under one root you choose |
| Removal | App and OS managed | Remove the root; oloop remove stops its hosts |

- [Why own the runtime](/guides/why-own-the-runtime)

## The 3 paths, and which one works today

One path is supported today.

The decision table. 'Supported' means the path has a measured setup and a working command.

| Path | Status | What is missing or unqualified |
| --- | --- | --- |
| WSL2 + oloop + a Linux CPU or L4 setup | Supported. Measured Linux evidence. | GPU passthrough is expected to fit; we have not qualified it. |
| Windows + Foundry Local + oloop as a referenced endpoint | Experimental. Not qualified. | Native oloop install, harness provisioning, endpoint reachability from WSL2 or Windows, and an immutable model identity for a lock. |
| Windows AI APIs / Phi Silica | Not a fit for a CLI coding agent. | App-level APIs and a Limited Access Feature, not a general endpoint. |

## The WSL2 path

WSL2 runs a Linux distribution under Windows. Install it, install the CLI inside the distribution, then use the Linux x64 CPU setup. This assumes an x64 Windows host; Windows on ARM is a different path that we have not qualified.

The Linux setup is an explicit setup, not the no-arg bootstrap. It runs on the OS its catalog entry declares, and it passes the same RAM and disk checks as any other Linux x64 machine.

```sh
wsl --install
curl -fsSL https://oloop.run/install.sh | sh
oloop host start --setup linux-x64-cpu@1.2.2
oloop host open
```

- [The Linux CPU setup](/local/linux-cpu-8-32)
- [Install and requirements](/docs#install)
- [Setup compatibility](/docs#compatibility)

## NPU, GPU, and CPU are different measurements

NPU TOPS is not a coding benchmark. It measures an accelerator's peak arithmetic rate for the operations it supports, not how a 7B coding model behaves with a context window, a harness, and a tool loop. A model that size wants RAM and memory bandwidth before it wants a TOPS number.

Foundry Local picks an execution provider for the device it runs on. That is not the same thing as Ollama or llama.cpp using the NPU; they are different runtimes with different supported paths. We make no TOPS or tokens-per-second claim.

## Foundry Local is a client runtime

Foundry Local is optimized for single-user client devices. It can serve a model to an app on the same machine, which is useful. It is not a multi-user server stack: there is no tenant model, no shared runtime control, and no evidence layer for a team.

For a team or a server, the measured path is the self-hosted guide and the L4 page.

- [Self-hosted coding agent](/guides/self-hosted-coding-agent)
- [The NVIDIA L4 setup](/local/nvidia-l4)
- [The memory guide](/guides/local-coding-model-by-memory)

## What Windows does not have yet

There is no native oloop install for Windows, and no Windows setup in the catalog. A Foundry Local endpoint is not qualified either. oloop does not run natively on Windows today.

A native path needs a Windows build, a catalog entry, and a measured run. None of the 3 exists yet, so WSL2 is the supported route.

Facts about Windows, Foundry Local, and Phi Silica were verified 2026-10-20 against Microsoft Learn. They are re-checked quarterly; a changed source becomes an edit or a removed claim.

- [Windows ML (Microsoft Learn)](https://learn.microsoft.com/en-us/windows/ai/new-windows-ml/overview)
- [Foundry Local (Microsoft Learn)](https://learn.microsoft.com/en-us/azure/foundry-local/what-is-foundry-local)
- [Windows AI APIs (Microsoft Learn)](https://learn.microsoft.com/en-us/windows/ai/overview)
- [Phi Silica (Microsoft Learn)](https://learn.microsoft.com/en-us/windows/ai/apis/phi-silica)
- [Data and privacy](/docs#data)
- [Privacy](/privacy)
- [All machine setups](/setups)

## Install

Install the CLI, then pick the setup for your machine class.

```sh
curl -fsSL https://oloop.run/install.sh | sh
```

- [All setups](/setups)
- [Measured setups](/local)
- [Install and requirements](/docs#install)
- [The canonical install block](/learn#install)

## Questions

### Can I run oloop natively on Windows?

No. There is no native Windows install, and the catalog has no Windows entry. The supported path is WSL2 plus a Linux x64 setup.

### Can oloop use Foundry Local as its model endpoint?

Not as a qualified path. Foundry Local can expose an OpenAI-compatible local server, and a referenced endpoint still needs a native install, harness provisioning, reachability, and a lockable model identity. We have not measured those.

### Is Phi Silica a coding-agent endpoint?

No. It is an app-level API for apps on Copilot+ PCs, and it is not something a CLI coding agent can call.

### Does an NPU make a coding model faster?

TOPS does not answer that. A coding run also depends on memory capacity, memory bandwidth, the model, the quantization, and the runtime's supported execution path.

### Which Windows path should I use today?

WSL2 with the Linux x64 CPU setup. With a GPU, the L4 path is measured on Linux hardware, and GPU passthrough from Windows is not qualified.

## Related

- [Self-hosted coding agent for a team](/guides/self-hosted-coding-agent)
- [Why own the agent runtime](/guides/why-own-the-runtime)
- [Local coding on Linux with 8–32 GB, no GPU](/local/linux-cpu-8-32)

Updated 2026-10-20 · Outerloop