fx: A Tiny, Open, Embeddable Unix-like Coding Agent in Zig
This repository profile is provided by osrepos.com, an open source repository discovery platform.
Summary
fx is an experimental, open-source coding agent CLI written in Zig, designed to be small, native, and embeddable. It offers a Unix shell-like interface for interacting with various AI models, providing a flexible tool for developers. This agent supports multiple AI gateways and custom model connections, making it highly adaptable to different workflows.
Repository Information
Topics
Click on any tag to explore related repositories
Use at your own risk
OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.
Introduction
fx is a powerful, Unix-like coding agent CLI developed by Vercel Labs. Written in Zig, it's a small, native binary that is open source under the Apache-2.0 license, model-agnostic, and designed to be embeddable in larger systems. Its interface prioritizes a shell-like experience over a traditional IDE in the terminal, offering a streamlined approach to AI-assisted coding.
Why Use fx & Key Features
fx stands out for its flexibility and integration capabilities, making it a valuable tool for developers looking to leverage AI in their workflows. Here are its core highlights:
- Any Model: Connect to various AI models, including Vercel AI Gateway, ChatGPT, Grok subscriptions, or your own OpenAI-compatible endpoints like Ollama or OpenRouter.
- Any Interface: Utilize an interactive shell, perform one-shot requests with
fx askfor scripts, or embed the agent throughlibfxand ACP. - Shell-like Output: Enjoy inline rendering that preserves your terminal scrollback, maintaining a familiar command-line experience.
- Extensible: Expand its capabilities with skills, MCP servers, and subagents, allowing for deep customization and integration.
Installation
To get started with fx, simply run the following command in your terminal:
curl -fsSL https://fx.sh/setup.sh | bash
Examples
After installation, you'll need to sign in. You can choose from several options:
fx login: For Vercel AI Gateway.fx login codex: For ChatGPT subscription (OpenAI Codex OAuth).fx login grok: For Grok subscription (xAI OAuth).fx setup: Using an AI Gateway API key.
Once logged in, you can start the interactive shell from your project directory:
cd your_project
fx
Alternatively, make a one-shot request directly from your terminal:
fx ask "explain the changes in this repository"
Inside the interactive shell, type /help to explore available commands.
Links
- GitHub Repository: https://github.com/vercel-labs/fx
- Official Documentation: https://fx.sh/docs
- Installation Script: https://fx.sh/setup.sh
Related repositories
Similar repositories that may be relevant next.
Source repository
Open the original repository on GitHub.