Amp vs Qwen Code

Overview

Amp is a coding agent and development environment built for frontier models. Instead of keeping one chat in one editor, Amp gives every agent its own orb — an isolated environment that keeps working after you close your laptop. You can start a task, walk away, and check on it from the web or your phone while it continues in the background.

The product is aimed at developers who run several agents at once and want to stop juggling worktrees, terminals and browser tabs. Amp describes the shift as "juggle less, ship more": you direct a team of agents, share threads with teammates, and pick work back up from any device.

What Amp provides

• Orbs — always-on environments for agents. Each orb can run commands, edit code and keep state, and agents inside them continue after your local machine disconnects.
• Remote control — run amp --no-tui on servers, CI runners or any shell, then watch and steer those agents from the web UI or your phone.
• Threads and spaces — long-running conversations grouped into spaces so multiple agents and teammates can work on the same project without stepping on each other.
• Automations — agents can schedule themselves to wake up, check production metrics, compare canary results and report back without a human prompt.
• Production access with OIDC — orbs can be granted (and revoked) access to production systems such as Google Cloud, so an agent can read logs or verify a rollout.
• Team features — service accounts for threads that belong to the team rather than one person, plus sharing so colleagues can follow or take over work.
• Git hosting integrations — connect github.com, gitlab.com or a self-hosted GitLab instance; Amp can also host a repository for a new project and clone it with amp clone.
• Portals — open what an agent built on a remote runner directly from your browser, even when the code is not on your machine.
• Boxes — always-on computers for the things you build with Amp.

How people use it

Typical workflows include handing off a bug report and letting the agent reproduce, patch and test it; running performance rollouts where an agent watches dashboards and confirms a fleet-wide win; reviewing a diff and asking follow-up questions in the same thread; and letting an agent fix its own tooling or documentation when it hits a bad error message.

Amp is model-agnostic in practice — the agent can be pointed at different frontier models — and it exposes the same threads across the desktop app, CLI, web and mobile, so a task can start on one surface and finish on another.

Getting started

1. Create an account at ampcode.com and install the CLI or desktop app.
2. Run amp in a project directory, or use amp --no-tui on a remote machine.
3. Describe the task; the agent plans, edits files, runs commands and reports back.
4. Use the web or mobile view to steer long-running orbs, or open a portal to preview what was built.
5. For team work, move persistent threads into a space and use service accounts where the work should outlive an individual.

Pricing

Amp offers a free tier with limited daily usage plus paid credit plans for heavier agent use; team and enterprise options add shared spaces, service accounts and centralized billing. Check ampcode.com for current limits.

Links

• Website: ampcode.com
• Docs: ampcode.com/docs
• CLI remote control: ampcode.com/docs/cli/remote-control
• Changelog: ampcode.com/chronicle

Why Qwen Code?

• Agentic out of the box — Auto-Memory, Auto-Skills, SubAgents, Agent Teams, and MCP. Dynamic workflows, zero setup.
• Open-source, inside and out — The framework and the Qwen models are open-source. They evolve together. No vendor lock-in.
• Multi-protocol — Supports OpenAI, Anthropic, Gemini, and Qwen APIs. Any third-party provider or local model (Ollama / vLLM). Switch at runtime.
• Beyond the terminal — IDE plugins, Desktop app, Web UI, SDKs, and chat integrations (Telegram / DingTalk / WeChat / Feishu).

[!TIP]
Qwen Code is actively iterating on itself — using its own agent and models to file issues, submit PRs, review code, and run tests. Powered by the community, driven by AI.

Installation

Looking for Qwen Code 1.0 Preview? Get started here. The instructions below are for the main version.

Linux / macOS:

curl -fsSL https://qwen-code-assets.oss-cn-hangzhou.aliyuncs.com/installation/install-qwen-standalone.sh | bash

Windows:

irm https://qwen-code-assets.oss-cn-hangzhou.aliyuncs.com/installation/install-qwen-standalone.ps1 | iex

Restart your terminal after installation to ensure environment variables take effect.

npm install -g @qwen-code/qwen-code@latest

brew install qwen-code

Quick Start

Open a terminal in your project and start Qwen Code:

cd /path/to/your-project
qwen

Inside the session, run /auth and choose Qwen Account with Subscription to sign in with your Plus or Pro subscription, or configure a provider with an API key. Then try:

Explain this repository and show me where to start.

See the Authentication Guide and Settings Reference for detailed setup.

How to Use Qwen Code

Choose the interface that fits your workflow:

For automation and custom integrations:

• Headless — Run qwen -p "..." in scripts, CI/CD, or batch jobs.
• SDKs — Build with TypeScript, Python, or Java.
• Daemon — Run qwen serve to connect clients over HTTP + SSE (ACP). (experimental) Daemon guide.
• Computer Use — Set up native MCP tools or Node REPL + SDK in Qwen Code, Claude Code, or Codex.

import asyncio

from qwen_code_sdk import is_sdk_result_message, query

async def main() -> None:
    result = query(
        "Summarize the repository layout.",
        {
            "cwd": "/path/to/project",
            "path_to_qwen_executable": "qwen",
        },
    )

    async for message in result:
        if is_sdk_result_message(message):
            print(message["result"])

asyncio.run(main())

Daemon Mode

Run Qwen Code as a long-lived service when you want browser, editor, SDK, and automation clients to share agent sessions without each starting a separate process. The daemon provides the built-in Web Shell and an HTTP + SSE API, supports multiple workspaces, and lets clients reconnect to active sessions.

Start it in the foreground and open the Web Shell:

qwen serve --open

The default address is http://127.0.0.1:4170. To run and manage it in the background instead:

qwen daemon start
qwen daemon status
qwen daemon logs -f
qwen daemon stop

By default, the daemon listens on loopback without bearer authentication; any local process that can reach it can use the full API, including code execution. On shared or untrusted hosts, set QWEN_SERVER_TOKEN and use --require-auth. See the Daemon guide for workspaces, authentication, remote access, and the API.

Capabilities

If you know Claude Code, you already know Qwen Code — and then some. We've put significant effort into bringing Qwen Code to feature parity with Claude Code, improving both breadth and reliability across the board.

Qwen Code Evaluation

On SWE-bench Verified, seven Qwen Code versions scored 76.40%–77.80% on average using the same Qwen 3.7 Max model (500 tasks, three trials per version).

Full results and evaluation configuration →

Ecosystem

• Qwen Code Desktop — Official desktop app for macOS, Windows, and Linux

• AionUi — A modern GUI for command-line AI tools including Qwen Code

• Gemini CLI Desktop — A cross-platform desktop/web/mobile UI for Qwen Code

• qwen-audio-agent — Realtime full-duplex voice frontend for Qwen Code over ACP — talk hands-free with barge-in and a local wake word

• 🦞 Qwen Code Claw — Let other agents (Claude, Codex, etc.) delegate coding tasks to Qwen Code via ACP. Paste this prompt into your agent:

Use Qwen Code as a coding agent. First, fetch and read this skill reference:
https://raw.githubusercontent.com/QwenLM/qwen-code/refs/heads/main/.qwen/skills/qwen-code-claw/SKILL.md
Then follow the instructions inside to install, authenticate, and use Qwen Code via acpx for all coding tasks.

• Aliyun Model Studio CLI — Official CLI for Aliyun's AI platform (bailian-cli). Extends Qwen Code with image/video generation, knowledge retrieval, app orchestration, and model deployment

Privacy

See the Terms of Service and Privacy Notice, including Chrome extension and Browser Use data handling.

Contributing

Contributions are welcome! See CONTRIBUTING.md for guidelines.

Acknowledgments

This project was originally based on Google Gemini CLI v0.8.2. We gratefully acknowledge the Gemini CLI team's excellent work. Starting from Qwen Code v0.1, we stopped syncing with upstream and began independent development as a multi-protocol, multi-platform agent framework with deep integrations for Qwen models and beyond.