danielmiessler/Fabric

Fabric is an open-source framework for augmenting humans using AI. It provides a modular system for solving specific problems using a crowdsourced set of AI prompts that can be used anywhere.

What is Fabric?

Fabric is an open‑source AI‑augmentation framework written in Go. Its core idea is to treat prompts (the text you send to a language model) as reusable, shareable patterns that solve concrete real‑world tasks – summarising a video, extracting key points from a paper, generating social‑media copy, etc. Fabric lets you collect, organise, and invoke those patterns from the command line, a REST API, or a tiny web UI, and it ships with built‑in support for dozens of AI providers (OpenAI, Anthropic, Google Gemini, Azure, Bedrock, Ollama, and many OpenAI‑compatible services).

Why does it exist?

The README argues that modern AI suffers from an integration problem: there are countless models and chat‑bots, but no easy way to stitch them into daily workflows. Fabric solves this by:

  1. Cataloguing prompts as first‑class assets (called Patterns).
  2. Providing a single CLI to run any pattern against any supported model.
  3. Offering a REST API and a lightweight web app for programmatic use.
  4. Allowing per‑pattern model selection, so you can pick the best model for each task.

Key Features (as described in the README)

Feature What it does
Pattern library Hundreds of ready‑made prompts for tasks like summarisation, code explanation, video transcript extraction, AI‑art prompt generation, etc.
Multi‑provider support Native integrations for OpenAI, Anthropic Claude, Google Gemini, Azure OpenAI, Amazon Bedrock, Vertex AI, Ollama, LM Studio, Perplexity and many OpenAI‑compatible vendors (e.g., Groq, Together, Venice AI).
CLI fabric --pattern <name> runs a pattern; aliases can turn each pattern into a simple command (summarize, extract_wisdom, …).
REST API server fabric --serve starts an HTTP server with Swagger UI; includes an Ollama‑compatibility mode.
Docker images Official images on Docker Hub and GHCR for easy containerised deployment.
Internationalisation Full i18n for prompts in 10+ languages (English, Spanish, German, French, Chinese, Japanese, Portuguese, Persian, Arabic, etc.).
Extensible Users can add custom patterns, map specific models to patterns via env vars, and write helper apps (to_pdf, code2context, generate_changelog).
Installation options One‑line script, Homebrew, AUR, Winget/Scoop, manual binary download, Go go install, or Docker.
Shell completions & aliases Auto‑generated completions for Bash/Zsh/Fish and scripts to create command aliases for every pattern.

Who might use it?

  • Developers & power users who want a consistent way to call LLMs from the terminal or scripts.
  • Content creators needing quick summarisation, transcript extraction, or AI‑generated copy.
  • Teams that want a shared library of vetted prompts (the "Patterns") across members.
  • Enterprises that can integrate the REST API into internal tools while picking a compliant provider (e.g., Azure OpenAI, Microsoft 365 Copilot).

How to get started (quick steps)

  1. Install – run the one‑line installer (curl … | bash on Unix, PowerShell script on Windows) or use a package manager.
  2. Run setup – fabric --setup creates the config directory and lets you add API keys for the providers you intend to use.
  3. Run a pattern – e.g., fabric -p summarize "https://example.com/article" or simply summarize "https://example.com/article" after adding the alias.
  4. Explore – fabric --listpatterns shows all built‑in patterns; fabric --serve starts the API server with Swagger UI.

Where to learn more

  • Documentation – the docs/ folder in the repo (deep dive into internals, custom pattern creation, API details).
  • DeepWiki – an external wiki that tracks updates and usage examples.
  • YouTube – intro videos from Network Chuck, David Bombal, and the author’s own walkthroughs.
  • Changelog – frequent releases adding new models (Claude Opus 4.7, OpenAI Codex, Azure AI Gateway, etc.) and features.

TL;DR

Fabric = a Go‑based CLI / API platform that turns AI prompts into reusable, version‑controlled patterns, works with dozens of LLM providers, and aims to make AI a seamless productivity assistant for everyday tasks.

Related

  • Project
    gszhangwei/open-spdd

    A CLI tool and methodology that transforms AI coding prompts into structured design contracts using the REASONS Canvas framework to ensure synchronization between design and implementation.

  • Project
    growthxai/output

    Output is an open‑source TypeScript framework that lets you define, run, and monitor LLM‑powered workflows. It bundles prompt files, multi‑provider LLM access, automatic tracing, cost tracking, evaluators, and Temporal‑based orchestration, all under one npm package suite.

  • Project
    microsoft/skills-for-fabric

    A collection of reusable AI assistant instructions and MCP servers that help AI coding tools understand and operate Microsoft Fabric workloads, APIs, and best practices.

  • Project
    genkit-ai/genkit

    An open-source framework for building full-stack AI applications with unified APIs for multiple model providers and cross-language SDKs.

  • Project
    Fission-AI/OpenSpec

    OpenSpec is a framework that adds a lightweight specification layer to your codebase, allowing you to align with AI coding assistants on project requirements and plans before code is generated.