# Install fabric-ai with Homebrew Open-source framework for augmenting humans using AI. Version 1.4.467 via Homebrew; verified 2026-07-31. ## Install ```sh sudo av install brew:fabric-ai ``` Additional install commands: ### macOS - Homebrew (100%): ```sh brew install fabric-ai ``` Evidence: provider-native install command ## Package facts - **Package key:** brew:fabric-ai - **Package manager:** Homebrew - **Version:** 1.4.467 - **Source summary:** Open-source framework for augmenting humans using AI - **Homepage:** - **Repository:** - **Last updated:** 2026-07-31T18:09:57Z - **Generated:** 2026-08-03T00:40:33+00:00 ## Executables - fabric-ai (alias) ## Install behavior - Bottle: not available ## Freshness - Page generated: 2026-08-03 - Package-manager version: 1.4.467 ## Project history and usage Fabric is Daniel Miessler's open-source framework for organizing reusable AI prompts, called patterns, and running them from a CLI or related interfaces. ### Project history Fabric was created after the late-2022 surge in modern AI tools. Its README argues that AI had an integration problem rather than a capabilities problem, and presents Fabric as a way to organize prompts by real-world task so they can be reused across workflows. The project started publicly in early 2024 and grew rapidly around the idea that prompt collections could be packaged like command-line tools. The README describes Fabric as both a pattern library and, for command-line-focused users, an interface for running those patterns directly. The current project is implemented and distributed as a fast-moving CLI with release binaries, shell completions, a REST API server, provider integrations, and package-manager installs. Its README notes that Homebrew and Arch Linux package the executable as `fabric-ai`, with an alias suggested for users who want to type `fabric`. ### Adoption history Fabric's adoption followed the broader CLI-and-LLM trend: users wanted prompt workflows they could pipe text into, version in Git, and invoke from shells instead of only using web chat interfaces. The README points to intro videos and a large set of patterns for summarization, paper analysis, code explanation, social posts, and other repeatable tasks. The project has kept widening provider support. The README update log lists additions for OpenAI Codex, Azure AI Gateway, Microsoft 365 Copilot, DigitalOcean GenAI, GitHub Models, Venice AI, Z AI, Abacus, Anthropic model updates, internationalization, Windows ARM and Linux ARM binaries, and Swagger API docs. ### How it is used The core usage model is to select a pattern and feed it content. Users can run Fabric from the CLI, install or update patterns, create custom patterns, map patterns to models, add shell aliases, or run its REST API server for local integrations. Because Fabric treats prompts as named assets, it behaves like a package of workflows rather than a single chatbot. That makes it useful for people who want repeatable LLM operations in shell pipelines, note-taking systems, coding workflows, or personal knowledge processes. ### Why package nerds care Fabric is package-nerd significant because it turns prompts into installable, inspectable command-line artifacts. It is part of the 2024-2026 wave of LLM tooling where package managers distribute not only compilers and CLIs, but also opinionated prompt workflows. The `fabric-ai` Homebrew naming detail is also notable: it avoids colliding with the older Python `fabric` package while preserving the upstream tool's identity through a recommended alias. ### Timeline - 2024: The Fabric repository is created. - 2025: Releases add new binary targets, provider integrations, internationalization, and REST API documentation. - 2026: README update log lists Microsoft 365 Copilot, Azure AI Gateway, OpenAI Codex backend, and Anthropic model support updates. ### Related projects - Fabric integrates with LLM providers and backends such as OpenAI, Anthropic, Azure OpenAI, Google Vertex AI, AWS Bedrock, Ollama, GitHub Models, and others. - The Homebrew package is named `fabric-ai` to distinguish it from Python Fabric. ### Sources - - - - - ## Security Notes narrow executable package without higher-risk signals. - **Geiger risk:** green / low - narrow executable package without higher-risk signals ## Configuration and credential file locations These source-backed paths show where this package keeps local settings or durable credentials. Automic Vault can use them as review targets for secret scanning, migration, and command approval. ## Configuration files - Unix: ~/.config/fabric/config.yaml ## Credential files - Unix: ~/.config/fabric/.env ## Combined YAML source View the package source record on GitHub. [combined/fabric-ai.yml](https://github.com/automic-vault/db/blob/main/combined/fabric-ai.yml) ## Sources - Nucleus package database - Geiger risk classifier - curated configuration and credential file locations - curated package history - pkgdb category and tag curation