🍺 BREW Explorer

← all formulae

open-mpi

brew install open-mpi v5.0.9 BSD-3-Clause

High-performance message passing library for distributed and parallel computing on clusters and supercomputers.

Why you might care

Open MPI is the de facto standard MPI implementation for HPC workloads, offering optimized collective operations, hardware support detection, and strong community backing. Use this if you're building parallel Fortran/C/C++ applications that need to run across multiple nodes; it's production-grade and widely compatible with academic and commercial HPC systems.

Categories

library scientific benchmark

Alternatives

MPICH Intel MPI Cray MPICH
2.8k
30-day installs · #817
9.0k
90-day · #851
103.3k
365-day · #409

Runtime dependencies

gcc hwloc libevent pmix

Links

Blurb generated by claude-haiku-4-5 on today.

Raw metadata 
{
  "aliases": [
    "openmpi"
  ],
  "alternatives": [
    "MPICH",
    "Intel MPI",
    "Cray MPICH"
  ],
  "build_dependencies": [],
  "categories": [
    "library",
    "scientific",
    "benchmark"
  ],
  "caveats": null,
  "conflicts_with": [
    "mpich"
  ],
  "dependencies": [
    "gcc",
    "hwloc",
    "libevent",
    "pmix"
  ],
  "deprecated": 0,
  "deprecation_reason": null,
  "desc": "High performance message passing library",
  "disable_reason": null,
  "disabled": 0,
  "enrichment_fetched_at": "2026-06-20T23:41:07+00:00",
  "first_seen": "2026-06-20T23:34:18+00:00",
  "full_name": "open-mpi",
  "github_default_branch": null,
  "github_last_commit_at": null,
  "github_readme_excerpt": null,
  "github_repo": null,
  "github_stars": null,
  "github_topics": [],
  "homepage": "https://www.open-mpi.org/",
  "homepage_og_description": null,
  "homepage_og_image": null,
  "homepage_title": "Open MPI: Open Source High Performance Computing",
  "installs_30d": 2848,
  "installs_365d": 103328,
  "installs_90d": 9001,
  "keg_only": 0,
  "keg_only_reason": null,
  "last_seen": "2026-06-20T23:34:18+00:00",
  "license": "BSD-3-Clause",
  "llm_generated_at": "2026-06-20T23:47:14+00:00",
  "llm_model": "claude-haiku-4-5",
  "name": "open-mpi",
  "oldnames": [],
  "one_liner": "High-performance message passing library for distributed and parallel computing on clusters and supercomputers.",
  "optional_dependencies": [],
  "rank_30d": 817,
  "rank_365d": 409,
  "rank_90d": 851,
  "raw_hash": "3c593411aa40d2e4",
  "recommended_dependencies": [],
  "revision": 0,
  "ruby_source_path": "Formula/o/open-mpi.rb",
  "tap": "homebrew/core",
  "test_dependencies": [],
  "uses_from_macos": [],
  "version_head": "HEAD",
  "version_stable": "5.0.9",
  "versioned_formulae": [],
  "why_use_this": "Open MPI is the de facto standard MPI implementation for HPC workloads, offering optimized collective operations, hardware support detection, and strong community backing. Use this if you\u0027re building parallel Fortran/C/C++ applications that need to run across multiple nodes; it\u0027s production-grade and widely compatible with academic and commercial HPC systems."
}