#3434th of 324 in Skills, plugins and prompts
fabric
Go CLI that runs a library of task-specific prompts against many LLM providers
- Stars
- 44.5k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Go
40,045 on 10 Apr 202644,518 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Fabric is a Go command-line tool that organizes prompts as "Patterns" by real-world task (summarize, extract wisdom, explain code) and pipes text or YouTube transcripts through them to a chosen model. It supports native providers such as OpenAI, Anthropic, Gemini, Ollama and Bedrock, plus many OpenAI-compatible vendors. It also offers a REST API server with Swagger UI, custom patterns, and per-pattern model mapping.
Who it is for: Terminal users who want reusable prompts piped through any LLM provider
Strengths
- Many providers: OpenAI, Anthropic, Gemini, Ollama, Bedrock, Vertex AI, plus 30+ OpenAI-compatible vendors
- Single Go binary with one-line installers, Homebrew, Winget, Scoop and AUR packages
- Per-pattern model mapping via FABRIC_MODEL_PATTERN_NAME=vendor|model environment variables
- Built-in REST API server with Swagger UI at /swagger/index.html and an Ollama compatibility mode
Weaknesses
- Needs an external provider API key or a local model server; it does not run models itself
- Homebrew and AUR installs expose the binary as fabric-ai, requiring a shell alias
- Setup is CLI-driven via fabric --setup; the web UI is a separate app
- Docker images are published under personal Docker Hub and GHCR accounts
What it needs
- no GPU
- Needs LLM provider API key or local Ollama/LM Studio
- Models: OpenAI, Anthropic, Google Gemini, Ollama, Azure OpenAI
- port 8080
Quick answers
Is fabric open source?
Yes. Its code is on GitHub under the MIT license.
Can you run fabric with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Also in Skills, plugins and prompts
See all 324| Rank | Project | Score |
|---|---|---|
| 1 | impeccableDesign skill with 24 slash commands for AI coding agents' frontend output | 96 out of 100 |
| 2 | skillsAgent skills for planning, TDD, debugging and code review | 95 out of 100 |
| 3 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 95 out of 100 |
| #4 | gstackMarkdown slash-command skills that give Claude Code planning, review, QA and ship roles | 95 out of 100 |
| #5 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 95 out of 100 |