# LLxprt Code — Multi-Provider AI Coding CLI

> LLxprt Code is an open-source AI coding CLI that switches across providers (Anthropic, Gemini, Codex, local). Install via brew or npm.

## Install

Copy the content below into your project:

## Quick Use

```bash
brew tap vybestack/homebrew-tap
brew update && brew install llxprt-code
llxprt
# then in REPL: /provider anthropic   (or gemini/qwen/codex)
```

## Intro

LLxprt Code is an open-source AI coding CLI that switches across providers (Anthropic, Gemini, Codex, local). Install via brew or npm.

**Best for:** Terminal-first developers who want one CLI for multiple LLM providers

**Works with:** Node.js 20+ (npm path) or Homebrew, multiple provider auth flows

**Setup time:** 5-12 minutes

### Key facts (verified)

- GitHub: 673 stars · 89 forks · pushed 2026-05-13.
- License: Apache-2.0 · owner avatar + repo URL verified via GitHub API.
- README-verified entrypoint: `npm install -g @vybestack/llxprt-code`.

## Main

- Pick your provider strategy first: use free tiers (Gemini/Qwen), OAuth for subscriptions (Claude/Codex), or point to a local OpenAI-compatible base URL.

- Use non-interactive mode for automation (CI scripts) and interactive REPL for exploratory coding and refactors.

- When you need tools, connect external MCP integrations (README notes MCP support) and keep secrets in provider-specific configs.

### Source-backed notes

- README shows provider commands like `/auth` + `/provider` + `/model` for Gemini/Qwen/Anthropic/Codex.
- README includes install options via Homebrew and npm (`npm install -g @vybestack/llxprt-code`) and a no-install npx example.
- README describes both interactive REPL workflows and non-interactive single-command mode for automation.

### FAQ

- **Do I have to use one provider?**: No — README is built around switching providers and models per session.
- **Is it only interactive?**: No — README shows non-interactive mode for scripted usage and CI-style automation.
- **Can I use it with local models?**: Yes — README mentions local providers (LM Studio/llama.cpp/Ollama) and OpenAI-compatible base URLs.

## Source & Thanks

> Source: https://github.com/vybestack/llxprt-code
> License: Apache-2.0
> GitHub stars: 673 · forks: 89

---

<!-- ZH -->

## Quick Use

```bash
brew tap vybestack/homebrew-tap
brew update && brew install llxprt-code
llxprt
# then in REPL: /provider anthropic   (or gemini/qwen/codex)
```

## Intro

LLxprt Code 是开源终端编码助手，支持多 provider（Anthropic、Gemini、OpenAI/Codex、本地模型等）。README 给出 brew/npm 安装与交互式 REPL 用法，可直接在终端做开发自动化。

**Best for:** 终端优先、想用一个 CLI 统一多个模型 Provider 的开发者

**Works with:** Node.js 20+（npm 路线）或 Homebrew；多 provider 的认证流程

**Setup time:** 5-12 minutes

### Key facts (verified)

- GitHub：673 stars · 89 forks；最近更新 2026-05-13。
- 许可证：Apache-2.0；作者头像与仓库链接均已通过 GitHub API 复核。
- README 中核对过的入口命令：`npm install -g @vybestack/llxprt-code`。

## Main

- 先确定 provider 策略：可用免费层（Gemini/Qwen）、订阅 OAuth（Claude/Codex），或对接本地 OpenAI 兼容网关。

- 自动化场景走非交互模式（脚本/CI），探索与重构走交互式 REPL。

- 需要外部工具时接入 MCP（README 提到 MCP 集成），并把密钥放在各 provider 的配置里集中管理。

### Source-backed notes

- README 展示了 `/auth` + `/provider` + `/model` 的切换方式，覆盖 Gemini/Qwen/Anthropic/Codex 等。
- README 提供 Homebrew 与 npm 两种安装方式（如 `npm install -g @vybestack/llxprt-code`），并给出 npx 免安装示例。
- README 区分交互式 REPL 与非交互单命令模式，后者更适合自动化脚本。

### FAQ

- **必须固定一个 provider 吗？**：不必。README 的核心就是可在会话里切换 provider 与模型。
- **只能交互式使用吗？**：不是。README 提供非交互模式，适合脚本与 CI 自动化。
- **能接本地模型吗？**：可以。README 提到 LM Studio/llama.cpp/Ollama 等本地方案以及 OpenAI 兼容 base URL。

## Source & Thanks

> Source: https://github.com/vybestack/llxprt-code
> License: Apache-2.0
> GitHub stars: 673 · forks: 89


---
Source: https://tokrepo.com/en/workflows/llxprt-code-multi-provider-ai-coding-cli
Author: Script Depot