# Installer rapid-mlx avec Homebrew Consultez les chemins d'installation, exécutables, métadonnées et notes de sécurité de rapid-mlx pour les workflows d'agents IA. ## installation ```sh sudo av install brew:rapid-mlx ``` Commandes d'installation supplémentaires: ### macOS - Homebrew (100%): ```sh brew install rapid-mlx ``` Preuve: local Homebrew formula metadata ## Faits du paquet - **Clé du paquet:** brew:rapid-mlx - **Gestionnaire de paquets:** Homebrew - **Page du gestionnaire de paquets:** - **Version:** 0.10.18 - **Résumé source:** Fast local AI engine for Apple Silicon with an OpenAI-compatible API - **Page d'accueil:** - **Dépôt:** - **Docs amont:** - **Licence:** Apache-2.0 - **Archive source:** - **Dernière mise à jour:** 2026-07-25T04:02:37Z - **Généré:** 2026-07-25T07:20:51+00:00 ## exécutables - rapid-mlx (cli) - rapid-mlx-bench (cli) - rapid-mlx-chat (cli) - vllm-mlx (cli) - vllm-mlx-bench (cli) - vllm-mlx-chat (cli) - rapid-mlx (alias) - rapid-mlx-bench (alias) - rapid-mlx-chat (alias) - vllm-mlx (alias) - vllm-mlx-bench (alias) - vllm-mlx-chat (alias) ## Dépendances - certifi - libyaml - mlx - numpy - openssl@3 - pydantic - python@3.14 - rpds-py ## Dépendances de compilation - cmake - pkgconf - rust ## Comportement d'installation - hook post-installation: non défini - Bouteille: disponible sur arm64_sequoia, arm64_sonoma, arm64_tahoe ## Version et fraîcheur - page générée: 2026-07-25 - version du gestionnaire: 0.10.18 - gestionnaire mis à jour: 2026-07-25 - données locales: OK - dépôt amont: https://github.com/raullenchai/Rapid-MLX - info: No cached GitHub release or tag data was available. ## Historique du projet et usages Rapid-MLX is a local inference engine and OpenAI-compatible HTTP server built on Apple's MLX stack for Apple Silicon Macs. It packages model serving, interactive chat, benchmarking, model management, and agent/IDE integration behind the `rapid-mlx` CLI. ### Historique du projet Development began in early 2026, with the official repository created in February and tagged releases available from March. The package was formerly exposed through `vllm-mlx` command names; those entry points remain as compatibility aliases while current documentation directs new users to `rapid-mlx`. ### Historique d'adoption Rapid-MLX developed a fast release cadence and first-class integrations for coding agents and Python frameworks. By the 0.10 series it was distributed from PyPI and Homebrew core, while its documentation described dozens of model families, an alias catalog, and reproducible community hardware benchmarks. ### Modes d'utilisation A typical workflow is `rapid-mlx serve ` followed by pointing an OpenAI-compatible client at `http://localhost:8000/v1`. Companion commands provide a terminal chat REPL, downloads and cache management, diagnostics, benchmarks, and setup templates for tools such as Codex, Claude Code, Aider, and Cursor. ### Pourquoi les passionnés de paquets s'y intéressent Rapid-MLX packages the Apple-Silicon-specific MLX ecosystem into a familiar server-and-CLI interface, reducing model selection to stable aliases and preserving compatibility with the broad OpenAI client ecosystem. Its Homebrew, pip, uv, and self-contained installer paths make local LLM serving accessible without maintaining a bespoke Python environment. ### Chronologie - 2026-02-25: Official GitHub repository created. - 2026-03-20: v0.3.0 published, the oldest retained GitHub release. - 2026: Command branding moved from vllm-mlx to rapid-mlx while compatibility entry points were retained. - 2026: Version 0.10.12 entered Homebrew core according to the official README. ### Related projects - Rapid-MLX builds on Apple MLX and MLX-LM concepts, consumes Hugging Face model repositories, offers vLLM-style flags, and acts as a local backend for OpenAI-compatible clients and coding agents. ### Sources - - - - ## Notes de sécurité Aucun manifest local de gestion des secrets correspondant n'a été trouvé pour rapid-mlx. Les métadonnées de paquet Nucleus restent publiées ici afin que la couverture future dispose d'une URL stable. ## Détails de la base source - **Source Database:** Homebrew formula API - **Tap:** homebrew/core - **Full Name:** rapid-mlx - **Version Scheme:** 0 - **Revision:** 0 - **Requirements:** macos - **Bottle Stable Root URL:** - **Deprecated:** no - **Disabled:** no - **Keg Only:** no - **URL Keys:** stable ## Liens liés - [Source-control packages](https://www.automicvault.com/fr/pkg/source-control-tools/) - Belongs to a source-control command family. - [MCP tool packages](https://www.automicvault.com/fr/pkg/mcp-tools/) - Mentions MCP or Model Context Protocol. - [AI and agent packages](https://www.automicvault.com/fr/pkg/ai-agent-tools/) - Matched AI model, agent, coding-agent, orchestration, or MCP metadata. - [Terminal utility packages](https://www.automicvault.com/fr/pkg/terminal-utilities/) - Matched terminal and command-line workflow metadata. - [mlx](https://www.automicvault.com/fr/pkg/brew/mlx/) - Runtime dependency declared by Homebrew. - [numpy](https://www.automicvault.com/fr/pkg/brew/numpy/) - Runtime dependency declared by Homebrew. - [openssl@3](https://www.automicvault.com/fr/pkg/brew/openssl-3/) - Runtime dependency declared by Homebrew. - [python@3.14](https://www.automicvault.com/fr/pkg/brew/python-3-14/) - Runtime dependency declared by Homebrew. - [cmake](https://www.automicvault.com/fr/pkg/brew/cmake/) - Build dependency declared by Homebrew. - [pkgconf](https://www.automicvault.com/fr/pkg/brew/pkgconf/) - Build dependency declared by Homebrew. - [rust](https://www.automicvault.com/fr/pkg/brew/rust/) - Build dependency declared by Homebrew. - [ollama](https://www.automicvault.com/fr/pkg/brew/ollama/) - Shares av.db curated category or tags: ai, cli, llm, local-ai, model-tools. - [oterm](https://www.automicvault.com/fr/pkg/brew/oterm/) - Shares av.db curated category or tags: ai, cli, llm, model-tools, python. - [shimmy](https://www.automicvault.com/fr/pkg/brew/shimmy/) - Shares av.db curated category or tags: ai, cli, inference-server, local-ai, model-tools. - [cai](https://www.automicvault.com/fr/pkg/brew/cai/) - Shares av.db curated category or tags: ai, cli, llm, model-tools. - [gollama](https://www.automicvault.com/fr/pkg/brew/gollama/) - Shares av.db curated category or tags: ai, cli, llm, model-tools. - [kubectl-ai](https://www.automicvault.com/fr/pkg/brew/kubectl-ai/) - Shares av.db curated category or tags: ai, cli, llm, model-tools. - [llama.cpp](https://www.automicvault.com/fr/pkg/brew/llama-cpp/) - Shares av.db curated category or tags: ai, cli, local-ai, model-tools. - [llmfit](https://www.automicvault.com/fr/pkg/brew/llmfit/) - Shares av.db curated category or tags: ai, cli, llm, model-tools. - [mlx-lm](https://www.automicvault.com/fr/pkg/brew/mlx-lm/) - Both packages touch the same language runtime or ecosystem. Shared terms: ai, certifi, chat, cli, inference. ## Combined YAML source View the package source record on GitHub. [combined/rapid-mlx.yml](https://github.com/automic-vault/db/blob/main/combined/rapid-mlx.yml) ## Sources - Nucleus package database - package-page enrichment - curated package history - package version freshness - av.db category and tag curation - package relationship graph - cross-ecosystem install command graph