# NVIDIA Personal AI Router

Routes independent local inference requests across compatible computers on the same network.

> This is the Markdown version of the NVIDIA Personal AI Router page on OpenNavo, with the same facts as the web page: <https://opennavo.com/apps/nvidia-pair>

- **Latest version**: `1.0.0`
- **Developer**: NVIDIA
- **Homepage**: <https://github.com/NVIDIA/Personal-AI-Router>
- **Categories**: [AI Tools](https://opennavo.com/categories/ai)
- **Install**: `brew install --cask nvidia-pair`
- **30-day installs**: 15
- **Homebrew**: Available; updated by Homebrew
- **Download URL**: <https://github.com/NVIDIA/Personal-AI-Router/releases/download/v1.0.0/NVPAIR-Setup-1.0.0-arm64.dmg>
- **SHA-256**: `46a7545ccaeec959e3321f9d200cc9a32c50207e09f277b4d96297394f461f1b`

SHA-256 only checks that the download is complete; it is not a security certification.

## Installation and removal contents

```json
[
  {
    "declaration": {
      "uninstall": [
        {
          "quit": "com.nvidia.nvpair"
        }
      ]
    },
    "phase": "uninstall",
    "sources": [],
    "type": "uninstall"
  },
  {
    "declaration": {
      "app": [
        "NVIDIA PAIR.app"
      ],
      "target": "/Applications/NVIDIA PAIR.app"
    },
    "phase": "install",
    "sources": [
      "NVIDIA PAIR.app"
    ],
    "target": "/Applications/NVIDIA PAIR.app",
    "type": "app"
  },
  {
    "declaration": {
      "zap": [
        {
          "trash": [
            "~/Library/Application Support/com.apple.sharedfilelist/com.apple.LSSharedFileList.ApplicationRecentDocuments/com.nvidia.nvpair.sfl*",
            "~/Library/Application Support/Nvidia Corporation/Personal AI Router",
            "~/Library/Logs/Personal AI Router",
            "~/Library/Preferences/com.nvidia.nvpair.plist",
            "~/Library/Saved Application State/com.nvidia.nvpair.savedState"
          ]
        }
      ]
    },
    "phase": "cleanup",
    "sources": [],
    "type": "zap"
  }
]
```

## About

NVIDIA Personal AI Router (PAIR) is a macOS desktop application for routing local inference requests among compatible computers on the same network. It discovers participating nodes and directs each independent request to an eligible node based on engine and model availability and current workload.

- Provides local proxy endpoints for Ollama-compatible, OpenAI-compatible, and Anthropic Messages API requests.
- Supports the Ollama, LM Studio, and llama.cpp inference engines; a node must have a compatible engine running and the requested model available to serve a request.
- Lets you pair machines into a cluster and view jobs and node activity in its desktop interface.
- Routes each request to one node; it does not combine GPU memory, split a model across machines, or divide an in-progress request among nodes.

Install with `brew install --cask nvidia-pair`, then open PAIR from Applications. This cask requires macOS 13 or later and installs the `NVIDIA PAIR.app` application. It selects an arm64 disk image for Apple Silicon Macs and an x64 disk image for Intel Macs. Engine and model requirements depend on the selected engine and model. Prompts and responses are intended to stay on the local network when the configured clients, model sources, engines, and nodes are all local.

Sources: [NVIDIA PAIR project](https://github.com/NVIDIA/Personal-AI-Router) · [Homebrew cask](https://raw.githubusercontent.com/Homebrew/homebrew-cask/HEAD/Casks/n/nvidia-pair.rb)

## System requirements

- macOS 13 or later · Version: 1.0.0 · Intel · <https://github.com/homebrew/homebrew-cask/blob/HEAD/Casks/n/nvidia-pair.rb> · Checked 2026-11-22
  - <https://github.com/NVIDIA/Personal-AI-Router/releases/download/v1.0.0/NVPAIR-Setup-1.0.0-x64.dmg>
  - SHA-256: `d0366583df2b601a2f374d2d078b1048573a69c1d143c8eb828593dea67533fc`
- macOS 13 or later · Version: 1.0.0 · Apple silicon · <https://github.com/homebrew/homebrew-cask/blob/HEAD/Casks/n/nvidia-pair.rb> · Checked 2026-11-22
  - <https://github.com/NVIDIA/Personal-AI-Router/releases/download/v1.0.0/NVPAIR-Setup-1.0.0-arm64.dmg>
  - SHA-256: `46a7545ccaeec959e3321f9d200cc9a32c50207e09f277b4d96297394f461f1b`

## NVIDIA Personal AI Router security facts

Only facts that can be checked, each with its source and date. This is not a safety certification. To check the files you downloaded, scan them on your Mac with OpenNavo.

- <https://github.com/NVIDIA/Personal-AI-Router> · Open source: Yes — <https://github.com/NVIDIA/Personal-AI-Router> · Checked 2026-11-13

## Uninstall

- `brew uninstall --cask nvidia-pair`

A regular uninstall removes the app and keeps its settings and caches.

### Deep clean (optional)

- `brew uninstall --zap --cask nvidia-pair`

`--zap` also deletes the settings, caches and other files listed in the Homebrew definition. They can include data shared with other apps and cannot be restored, and it does not guarantee that nothing is left. Back up any data you need first. To keep settings and caches, leave out `--zap`.

A regular uninstall removes the app and keeps its settings and caches.

- Files and folders: `~/Library/Application Support/com.apple.sharedfilelist/com.apple.LSSharedFileList.ApplicationRecentDocuments/com.nvidia.nvpair.sfl*` — <https://github.com/homebrew/homebrew-cask/blob/HEAD/Casks/n/nvidia-pair.rb> · These entries come from the Homebrew definition, checked 2026-11-22. They say what it declares, not what is on your Mac.
- Files and folders: `~/Library/Application Support/Nvidia Corporation/Personal AI Router` — <https://github.com/homebrew/homebrew-cask/blob/HEAD/Casks/n/nvidia-pair.rb> · These entries come from the Homebrew definition, checked 2026-11-22. They say what it declares, not what is on your Mac.
- Files and folders: `~/Library/Logs/Personal AI Router` — <https://github.com/homebrew/homebrew-cask/blob/HEAD/Casks/n/nvidia-pair.rb> · These entries come from the Homebrew definition, checked 2026-11-22. They say what it declares, not what is on your Mac.
- Files and folders: `~/Library/Preferences/com.nvidia.nvpair.plist` — <https://github.com/homebrew/homebrew-cask/blob/HEAD/Casks/n/nvidia-pair.rb> · These entries come from the Homebrew definition, checked 2026-11-22. They say what it declares, not what is on your Mac.
- Files and folders: `~/Library/Saved Application State/com.nvidia.nvpair.savedState` — <https://github.com/homebrew/homebrew-cask/blob/HEAD/Casks/n/nvidia-pair.rb> · These entries come from the Homebrew definition, checked 2026-11-22. They say what it declares, not what is on your Mac.

## Latest release notes

### 1.0.0 (2026-10-13)

Adds llama.cpp, engine launch options, RTX Spark support and terminal Jobs. Browser clients now follow engine CORS. On macOS, remove the old PAIR.app after installing NVIDIA PAIR.app. Older PAIR-installed LM Studio is not automatically removed; uninstall keeps models. RTX Spark validation is Windows on ARM only. Full original notes follow.

#### Reviewed notes

Adds llama.cpp, engine launch options, RTX Spark support and terminal Jobs. Browser clients now follow engine CORS. On macOS, remove the old PAIR.app after installing NVIDIA PAIR.app. Older PAIR-installed LM Studio is not automatically removed; uninstall keeps models. RTX Spark validation is Windows on ARM only. Full original notes follow.

#### Complete official original (English)

This release brings llama.cpp and RTX Spark support to PAIR, and establishes
its public development and contribution workflow on GitHub.

##### What's New

- **llama.cpp support.** Install and manage llama.cpp directly from PAIR,
  download compatible GGUF models from Hugging Face, and route inference
  requests across paired devices. Refer to
  [Managing Engines](engine-lifecycle.mdx).
- **Engine launch options.** Customize the launch arguments and environment
  variables of PAIR-managed engines, on this device or a paired one. Tune
  settings such as context size where the engine supports them. Refer to
  [Engine Settings](engine-settings.mdx).
- **RTX Spark support.** PAIR's Windows on ARM build has been validated with
  llama.cpp and CUDA on RTX Spark N1X hardware.
- **Improved terminal experience.** The terminal interface has a redesigned
  layout organized around each device, so you can manage engines, download
  models, and pair devices from one place. A new **Jobs** tab follows inference
  work across paired devices and runs the Inference Demo, giving headless
  machines the same core tools as the desktop app. Refer to
  [Terminal Interface](terminal-interface.mdx).

##### Compatibility Notes

- **Browser clients.** PAIR's local endpoints now follow each engine's CORS
  policy instead of allowing every browser origin. A browser-based client may
  need the engine configured to allow it — for Ollama, set `OLLAMA_ORIGINS` in
  the engine's launch options.
- **The macOS app is now NVIDIA PAIR.** The new `NVIDIA PAIR.app` installs
  beside the old `PAIR.app`, so remove the old one to keep just one copy. Your
  settings, cluster membership, and downloaded models carry over.
- **LM Studio installed by an earlier PAIR.** It keeps working as before. PAIR
  now removes only engines it has a record of installing, and earlier versions
  kept no record, so uninstalling or resetting PAIR leaves that LM Studio in
  place. You can remove it from `~/.lmstudio` yourself if you no longer want it.

The [Upgrade Guide](upgrade-guide.mdx) walks through each of these.

##### Targeted Bug Fixes

- Uninstalling LM Studio from PAIR, or uninstalling PAIR with its data, no
  longer deletes the models you downloaded. They stay in `~/.lmstudio/models`,
  just as Ollama's stay in `~/.ollama` and llama.cpp's in `~/.llamacpp`.

##### Community Contributions

- Added Anthropic Messages API routing through Ollama and LM Studio, so
  compatible clients such as Claude Code can use PAIR's model-aware routing and
  failover. Thanks [@Ratherrayees](https://github.com/Ratherrayees)!
  ([#27](https://github.com/NVIDIA/Personal-AI-Router/pull/27))
- Made engine monitoring more efficient by reusing HTTP connections for health
  checks. Thanks [@Psych0h3ad](https://github.com/Psych0h3ad)!
  ([#37](https://github.com/NVIDIA/Personal-AI-Router/pull/37))
- Fixed unnecessary cluster trust refreshes: notifications are now sent only
  after new peer endorsements are saved. Thanks [@RecursiveIntell](https://github.com/RecursiveIntell)!
  ([#62](https://github.com/NVIDIA/Personal-AI-Router/pull/62))
- Fixed workload synchronization between nodes: broadcasts preserve event
  order, and a failed broker notification stays eligible for retry. Thanks
  [@mkalkere](https://github.com/mkalkere)! ([#80](https://github.com/NVIDIA/Personal-AI-Router/pull/80))
- Fixed scheduler priority updates being marked as delivered after a failed
  notification, so they are retried and the status stays accurate. Thanks
  [@sylvesterkaczmarek](https://github.com/sylvesterkaczmarek)!
  ([#122](https://github.com/NVIDIA/Personal-AI-Router/pull/122))
- Isolated the service integration and proxy failover tests from local PAIR
  settings, so tests no longer read or overwrite a developer's configuration.
  Thanks [@somtri](https://github.com/somtri)! ([#95](https://github.com/NVIDIA/Personal-AI-Router/pull/95))
- Corrected the release-intent examples to use the required services version
  key. Thanks [@somtri](https://github.com/somtri)!
  ([#120](https://github.com/NVIDIA/Personal-AI-Router/pull/120))
- Updated the contributor instructions to branch from and rebase onto
  `develop`. Thanks [@somtri](https://github.com/somtri)!
  ([#126](https://github.com/NVIDIA/Personal-AI-Router/pull/126))
- Fixed node cards showing only the first GPU on multi-GPU systems; they now
  show every GPU. Thanks [@CryptoJones](https://github.com/CryptoJones)!
  ([#34](https://github.com/NVIDIA/Personal-AI-Router/pull/34))

##### Special Thanks

Thank you to these community members for sharing ideas, submitting proposals
and fixes, investigating issues, and testing PAIR:

[@XxSilentStormIxX](https://github.com/XxSilentStormIxX), [@agenticocho](https://github.com/agenticocho), [@Mayimbe07](https://github.com/Mayimbe07), [@cruzanstx](https://github.com/cruzanstx), [@pettersandvand](https://github.com/pettersandvand),
[@cguldogan](https://github.com/cguldogan), [@mkalkere](https://github.com/mkalkere), [@CryptoJones](https://github.com/CryptoJones), [@woodsonl](https://github.com/woodsonl), [@stevbev](https://github.com/stevbev), [@habakan](https://github.com/habakan), [@arcaven](https://github.com/arcaven),
[@somtri](https://github.com/somtri), [@imluffy000](https://github.com/imluffy000), [@ndizazzo](https://github.com/ndizazzo), and [@fpvo](https://github.com/fpvo).

We are grateful for every contribution, and for the warm welcome from the local
AI community.

#### Sources

- https://formulae.brew.sh/api/cask/nvidia-pair.json
- https://github.com/NVIDIA/Personal-AI-Router/releases/tag/v1.0.0
- https://api.github.com/repos/NVIDIA/Personal-AI-Router/releases/tags/v1.0.0
- https://github.com/NVIDIA/Personal-AI-Router/releases/download/v1.0.0/NVPAIR-Setup-1.0.0-arm64.dmg

## Facts and sources

- <https://opennavo.com/apps/nvidia-pair>
- <https://opennavo.com/apps/nvidia-pair/versions>
- <https://github.com/homebrew/homebrew-cask/blob/HEAD/Casks/n/nvidia-pair.rb> · Checked 2026-11-22
- <https://formulae.brew.sh/cask/nvidia-pair>
- <https://github.com/NVIDIA/Personal-AI-Router> · Checked 2026-11-13
