# Install openvino with Homebrew, dnf, Nix, zypper Open Visual Inference And Optimization toolkit for AI inference. Version 2026.2.1 via Homebrew; verified 2026-06-20. ## Install ```sh sudo av install brew:openvino ``` Additional install commands: ### macOS - Homebrew (100%): ```sh brew install openvino ``` Evidence: local Homebrew formula metadata ### Linux - dnf (92%): ```sh sudo dnf install intel-npu-compiler ``` Evidence: Fedora Rawhide package metadata: intel-npu-compiler from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/e5ca8ce900cd68f5419e1c39ae517343100b306336cbaeb70a3c153121d95094-primary.xml.zst - Nix (92%): ```sh nix profile install nixpkgs#openvino ``` Evidence: nixpkgs package indexes: pkgs/by-name/op/openvino/package.nix from https://api.github.com/repos/NixOS/nixpkgs/git/trees/master?recursive=1 - zypper (92%): ```sh sudo zypper install libopenvino2620 ``` Evidence: openSUSE Tumbleweed package metadata: libopenvino2620 from https://download.opensuse.org/tumbleweed/repo/oss/repodata/be8d3611d25469107f32075a1697e69ec57a2b850b42348a658cc671ad5ec2b50760d02c3e59524d50da9a11d5be799bdaffba2e166e8ca8858512e3c0bd665d-primary.xml.zst ## Package facts - **Package key:** brew:openvino - **Package manager:** Homebrew - **Package manager page:** - **Version:** 2026.2.1 - **Source summary:** Open Visual Inference And Optimization toolkit for AI inference - **Homepage:** - **Repository:** - **Upstream docs:** - **License:** Apache-2.0 - **Source archive:** - **Last updated:** 2026-06-20T05:07:44Z - **Generated:** 2026-07-08T07:18:31+00:00 ## Executables - benchmark_app (cli) - ovc (cli) - benchmark_app (alias) - ovc (alias) ## Dependencies - abseil - nlohmann-json - numpy - onnx - protobuf - pugixml - snappy - tbb ## Build dependencies - cmake - flatbuffers - pkgconf - pybind11 - python@3.14 - scons ## Install behavior - Post-install hook: not defined - Bottle: available on arm64_linux, arm64_sequoia, arm64_sonoma, arm64_tahoe, sonoma, x86_64_linux ## Freshness - Page generated: 2026-07-08 - Package-manager version: 2026.2.1 - Package-manager updated: 2026-06-20 - Local data: ok - Upstream repository: https://github.com/openvinotoolkit/openvino - Upstream latest detected: 2026.2.1 (current) ## Project history and usage OpenVINO, short for Open Visual Inference and Neural Network Optimization, is Intel's open source toolkit for optimizing and deploying AI inference. It grew from a computer-vision inference toolkit into a broader runtime for conventional deep learning, generative AI, model serving, and Intel CPU, GPU, and NPU deployment. ### Project history Intel introduced OpenVINO as a distribution for taking trained neural-network models and running them efficiently on Intel hardware. The project standardized a workflow around model conversion, graph optimization, a runtime API, and device plugins rather than training models from scratch. Early OpenVINO packaging centered on the Model Optimizer and Inference Engine. The 2022 release line introduced OpenVINO API 2.0, aligning inputs and outputs more closely with common framework tensor conventions while retaining older Inference Engine and nGraph APIs during the transition. The 2023 and 2024 release notes show the toolkit expanding beyond classic computer vision into speech, recommendation systems, natural language processing, Stable Diffusion, transformer models, LLM-oriented optimizations, OpenVINO GenAI, model-serving workflows, JavaScript access, and NPU support for Intel Core Ultra systems. ### Adoption history OpenVINO's adoption path follows Intel's hardware platform strategy: give developers one inference API and deployment stack across laptops, edge devices, servers, and AI PCs. The public GitHub organization includes the main runtime, NNCF compression tooling, notebooks, GenAI libraries, and OpenVINO Model Server, which indicates a package family rather than a single binary. It became a package-manager concern because AI applications increasingly need native runtimes, Python wheels, CLI tools such as ovc and benchmark_app, device plugins, and framework bridges. OpenVINO packages are used by developers who want to benchmark models, convert framework artifacts, reduce inference cost with quantization or compression, and deploy on Intel hardware without binding directly to one training framework. ### How it is used Developers use OpenVINO to load or convert models from frameworks such as PyTorch, TensorFlow, ONNX, TensorFlow Lite, PaddlePaddle, and JAX/Flax; optimize or compress them; then run inference through C++, Python, C, Node.js, server, or GenAI APIs. Operators also use benchmark_app to measure throughput and latency on target devices. The package is most visible in edge AI, AI PC, industrial vision, local LLM, and model-serving workflows where deployment constraints matter more than model training. ### Why package nerds care OpenVINO is the kind of package that turns dependency management into hardware enablement: a formula or distro package can decide whether an AI app has CPU, GPU, or NPU acceleration and whether model artifacts from several ML ecosystems can share one runtime. It is also a moving example of AI packaging churn: native C++ libraries, Python and JavaScript bindings, command-line converters, release-year documentation, and device plugins all need to stay aligned. ### Timeline - 2018: Intel releases OpenVINO as an open source toolkit for deep-learning inference deployment. - 2022: OpenVINO API 2.0 is introduced with cleaner tensor-oriented APIs and a migration path from older Inference Engine and nGraph APIs. - 2023: OpenVINO release notes add wider generative-AI model support, including Stable Diffusion and transformer-family workloads. - 2023-2024: OpenVINO GenAI, OpenVINO Model Server, JavaScript access, and NPU support broaden the toolkit beyond the original computer-vision focus. - 2026: OpenVINO documentation describes runtime support across Linux, Windows, and macOS with Python, C++, and C APIs. ### Related projects - OpenVINO is related to Intel oneAPI, OpenCV, NNCF, OpenVINO Model Server, OpenVINO GenAI, ONNX, PyTorch, TensorFlow, PaddlePaddle, JAX/Flax, and hardware plugin stacks for Intel CPU, GPU, and NPU devices. ### Sources - - - - - - - ## Security Notes narrow executable package without higher-risk signals. - **Geiger risk:** green / low - narrow executable package without higher-risk signals ## Source Database Details - **Source Database:** Homebrew formula API - **Tap:** homebrew/core - **Full Name:** openvino - **Version Scheme:** 0 - **Revision:** 1 - **Head Version:** HEAD - **Bottle Stable Root URL:** - **Deprecated:** no - **Disabled:** no - **Keg Only:** no - **URL Keys:** head, stable ## Other Package-Manager Records - Nix - openvino: normalized package name match | nixpkgs package indexes: pkgs/by-name/op/openvino/package.nix from https://api.github.com/repos/NixOS/nixpkgs/git/trees/master?recursive=1 - dnf - intel-npu-compiler - 2025.1.0-14.fc44: normalized package name match | Fedora Rawhide package metadata: intel-npu-compiler from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/e5ca8ce900cd68f5419e1c39ae517343100b306336cbaeb70a3c153121d95094-primary.xml.zst | OpenVINO NPU Compiler | https://github.com/openvinotoolkit/openvino - dnf - libopenvino-ir-frontend - 2025.1.0-14.fc44: normalized package name match | Fedora Rawhide package metadata: libopenvino-ir-frontend from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/e5ca8ce900cd68f5419e1c39ae517343100b306336cbaeb70a3c153121d95094-primary.xml.zst | OpenVINO IR Frontend | https://github.com/openvinotoolkit/openvino - dnf - libopenvino-onnx-frontend - 2025.1.0-14.fc44: normalized package name match | Fedora Rawhide package metadata: libopenvino-onnx-frontend from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/e5ca8ce900cd68f5419e1c39ae517343100b306336cbaeb70a3c153121d95094-primary.xml.zst | OpenVINO ONNX Frontend | https://github.com/openvinotoolkit/openvino - dnf - libopenvino-paddle-frontend - 2025.1.0-14.fc44: normalized package name match | Fedora Rawhide package metadata: libopenvino-paddle-frontend from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/e5ca8ce900cd68f5419e1c39ae517343100b306336cbaeb70a3c153121d95094-primary.xml.zst | OpenVINO Paddle Frontend | https://github.com/openvinotoolkit/openvino - dnf - libopenvino-pytorch-frontend - 2025.1.0-14.fc44: normalized package name match | Fedora Rawhide package metadata: libopenvino-pytorch-frontend from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/e5ca8ce900cd68f5419e1c39ae517343100b306336cbaeb70a3c153121d95094-primary.xml.zst | OpenVINO PyTorch Frontend | https://github.com/openvinotoolkit/openvino - dnf - libopenvino-tensorflow-frontend - 2025.1.0-14.fc44: normalized package name match | Fedora Rawhide package metadata: libopenvino-tensorflow-frontend from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/e5ca8ce900cd68f5419e1c39ae517343100b306336cbaeb70a3c153121d95094-primary.xml.zst | OpenVINO Tensorflow Frontend | https://github.com/openvinotoolkit/openvino - dnf - libopenvino-tensorflow-lite-frontend - 2025.1.0-14.fc44: normalized package name match | Fedora Rawhide package metadata: libopenvino-tensorflow-lite-frontend from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/e5ca8ce900cd68f5419e1c39ae517343100b306336cbaeb70a3c153121d95094-primary.xml.zst | OpenVINO Tensorflow-lite Frontend | https://github.com/openvinotoolkit/openvino - dnf - openvino - 2025.1.0-14.fc44: normalized package name match | Fedora Rawhide package metadata: openvino from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/e5ca8ce900cd68f5419e1c39ae517343100b306336cbaeb70a3c153121d95094-primary.xml.zst | Toolkit for optimizing and deploying AI inference | https://github.com/openvinotoolkit/openvino - dnf - openvino-devel - 2025.1.0-14.fc44: normalized package name match | Fedora Rawhide package metadata: openvino-devel from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/e5ca8ce900cd68f5419e1c39ae517343100b306336cbaeb70a3c153121d95094-primary.xml.zst | Development files for openvino | https://github.com/openvinotoolkit/openvino - dnf - openvino-plugins - 2025.1.0-14.fc44: normalized package name match | Fedora Rawhide package metadata: openvino-plugins from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/e5ca8ce900cd68f5419e1c39ae517343100b306336cbaeb70a3c153121d95094-primary.xml.zst | OpenVINO Plugins | https://github.com/openvinotoolkit/openvino - dnf - python3-openvino - 2025.1.0-14.fc44: normalized package name match | Fedora Rawhide package metadata: python3-openvino from https://dl.fedoraproject.org/pub/fedora/linux/development/rawhide/Everything/x86_64/os/repodata/e5ca8ce900cd68f5419e1c39ae517343100b306336cbaeb70a3c153121d95094-primary.xml.zst | OpenVINO Python API | https://github.com/openvinotoolkit/openvino - zypper - libopenvino2620 - 2026.2.0-1.1: normalized package name match | openSUSE Tumbleweed package metadata: libopenvino2620 from https://download.opensuse.org/tumbleweed/repo/oss/repodata/be8d3611d25469107f32075a1697e69ec57a2b850b42348a658cc671ad5ec2b50760d02c3e59524d50da9a11d5be799bdaffba2e166e8ca8858512e3c0bd665d-primary.xml.zst | Shared library for OpenVINO toolkit | https://github.com/openvinotoolkit/openvino - zypper - libopenvino_c2620 - 2026.2.0-1.1: normalized package name match | openSUSE Tumbleweed package metadata: libopenvino_c2620 from https://download.opensuse.org/tumbleweed/repo/oss/repodata/be8d3611d25469107f32075a1697e69ec57a2b850b42348a658cc671ad5ec2b50760d02c3e59524d50da9a11d5be799bdaffba2e166e8ca8858512e3c0bd665d-primary.xml.zst | Shared C library for OpenVINO toolkit | https://github.com/openvinotoolkit/openvino - zypper - libopenvino_ir_frontend2620 - 2026.2.0-1.1: normalized package name match | openSUSE Tumbleweed package metadata: libopenvino_ir_frontend2620 from https://download.opensuse.org/tumbleweed/repo/oss/repodata/be8d3611d25469107f32075a1697e69ec57a2b850b42348a658cc671ad5ec2b50760d02c3e59524d50da9a11d5be799bdaffba2e166e8ca8858512e3c0bd665d-primary.xml.zst | Paddle frontend for Intel OpenVINO toolkit | https://github.com/openvinotoolkit/openvino - zypper - libopenvino_onnx_frontend2620 - 2026.2.0-1.1: normalized package name match | openSUSE Tumbleweed package metadata: libopenvino_onnx_frontend2620 from https://download.opensuse.org/tumbleweed/repo/oss/repodata/be8d3611d25469107f32075a1697e69ec57a2b850b42348a658cc671ad5ec2b50760d02c3e59524d50da9a11d5be799bdaffba2e166e8ca8858512e3c0bd665d-primary.xml.zst | Onnx frontend for OpenVINO toolkit | https://github.com/openvinotoolkit/openvino ## Related links - [Terminal utility packages](https://www.automicvault.com/pkg/terminal-utilities/) - Matched terminal and command-line workflow metadata. - [Networking and protocol packages](https://www.automicvault.com/pkg/networking-protocol-tools/) - Matched network, protocol, or remote-service metadata. - [Scientific computing packages](https://www.automicvault.com/pkg/scientific-computing-tools/) - Matched scientific computing metadata. - [Documentation packages](https://www.automicvault.com/pkg/documentation-tools/) - Matched documentation, manual, or publishing metadata. - [numpy](https://www.automicvault.com/pkg/brew/numpy/) - Runtime dependency declared by Homebrew. - [protobuf](https://www.automicvault.com/pkg/brew/protobuf/) - Runtime dependency declared by Homebrew. - [cmake](https://www.automicvault.com/pkg/brew/cmake/) - Build dependency declared by Homebrew. - [flatbuffers](https://www.automicvault.com/pkg/brew/flatbuffers/) - Build dependency declared by Homebrew. - [pkgconf](https://www.automicvault.com/pkg/brew/pkgconf/) - Build dependency declared by Homebrew. - [pybind11](https://www.automicvault.com/pkg/brew/pybind11/) - Build dependency declared by Homebrew. - [opencv](https://www.automicvault.com/pkg/brew/opencv/) - Popular package that depends on this formula. - [gibbslda](https://www.automicvault.com/pkg/brew/gibbslda/) - Shares av.db curated category or tags: cli, machine-learning, science. - [grt](https://www.automicvault.com/pkg/brew/grt/) - Shares av.db curated category or tags: cli, machine-learning, science. - [liblinear](https://www.automicvault.com/pkg/brew/liblinear/) - Shares av.db curated category or tags: cli, machine-learning, science. - [mlpack](https://www.automicvault.com/pkg/brew/mlpack/) - Shares av.db curated category or tags: cli, machine-learning, science. - [tinysvm](https://www.automicvault.com/pkg/brew/tinysvm/) - Shares av.db curated category or tags: cli, machine-learning, science. - [colmap](https://www.automicvault.com/pkg/brew/colmap/) - Shares av.db curated category or tags: cli, computer-vision, science. - [flann](https://www.automicvault.com/pkg/brew/flann/) - Shares av.db curated category or tags: cli, computer-vision, machine-learning, science. - [g2o](https://www.automicvault.com/pkg/brew/g2o/) - Shares av.db curated category or tags: cli, computer-vision, science. ## Combined YAML source View the package source record on GitHub. [combined/openvino.yml](https://github.com/automic-vault/db/blob/main/combined/openvino.yml) ## Sources - Nucleus package database - Geiger risk classifier - package-page enrichment - curated package history - package version freshness - av.db category and tag curation - package relationship graph - external package-manager database matches - cross-ecosystem install command graph