Qwen Agent CLI

A dependency-free OpenAI-compatible coding agent for Windows, Linux, macOS, and Termux. Node.js 20 or newer is required.

Install

From npm:

npm install -g x-qwen-agent-cli

Linux, macOS, and Termux:

chmod +x install.sh
./install.sh

Windows:

install.cmd

PowerShell can also run .\install.ps1 directly.

Configure

Interactive runs always ask for a masked API key, including qwen -p when a terminal is attached. Non-interactive runs read QWEN_API_KEY, OPENAI_COMPAT_API_KEY, or OPENAI_API_KEY. The key remains in memory for that process only and is never stored in source code, settings, or chat history.

Linux, macOS, and Termux:

export QWEN_API_KEY="your-key"

Windows PowerShell:

$env:QWEN_API_KEY = "your-key"

Use

qwen
qwen -m qwen3.7-plus
qwen -m gpt-5.5 -p "Inspect and test this project."
qwen --clarify -p "Add authentication."
qwen --yes --no-stream

The interactive composer is multiline:

• Enter: insert a new line.
• Alt+Enter: send the complete message.
• Ctrl+Enter or Alt+S: send when the terminal reserves Alt+Enter.
• Arrow keys, Home, End, Backspace, and Delete edit the message.
• Multiline clipboard paste is preserved.

Commands: /plan TASK, /clarify TASK, /image PATH PROMPT, /file PATH PROMPT, /new, /sessions, /resume SESSION, /approval ask|auto, /model, and /exit.

Use /clarify TASK or --clarify -p "TASK" when you want the agent to ask precise requirements questions first. In clarification mode the agent should not edit files or run side-effecting commands; it returns focused questions and safe assumptions before implementation.

Images and files are sent as structured OpenAI attachment parts. Their bytes are uploaded through the selected provider's file endpoint and are never inserted into the user's text message.

Streaming is enabled by default. Reasoning is shown in a separate Thinking section when the provider returns it, and is never mixed into the final answer.

Realtime WebSocket is the default transport. The CLI connects to wss://a-v-5.vercel.app/v1/realtime unless QWEN_REALTIME_URL or --realtime-url provides another full ws:// or wss:// endpoint. HTTP is used only when explicitly requested with --transport http or QWEN_TRANSPORT=http.

The agent includes bounded file reads, batch reads and writes, tree and text search, path metadata, file operations, Git status/diff, cross-platform shell execution, and background terminals for dev servers and long-running commands. Mutating actions require approval unless --yes is used. For substantial tasks the model can call update_plan; plan steps and their live status are rendered separately from chat and tool output.

Workspace tools

The Agent prompt and file tools are maintained centrally. Available workspace tools include file_info, list_files, search_files, find_in_file, read_file, read_lines, update_file, apply_patch, create_file, delete_file, move_file, copy_file, make_directory, start_background_terminal, read_background_terminal, and stop_background_terminal.

Every Agent run sends fresh lightweight runtime context in the first user message: OS/version, processor, Node.js version, workspace root, available tools, and approval mode. File contents and fixed workspace listings are not embedded in that prompt; the agent locates and reads current files on demand. The CLI and VS Code extension intentionally transport the full Agent instructions by prefixing the first user message with <agent_instructions>. Every fourth user turn is prefixed with <agent_reminder> so the model keeps the active workspace and agent role in context. This avoids gateways that drop or weaken system messages while still sending a SHA-256 prompt proof in request metadata.

The file tools enforce workspace-only paths, reject traversal and symlink escapes, deny protected secret-looking files by default, detect binary files, return SHA-256 hashes, and use hash-aware edits with structured diffs.

Install the VS Code extension

qwen install ext
qwen install ext --path ./dist/qwen-agent-1.0.0.vsix
qwen install ext --id qwen-agent.qwen-agent
qwen install ext --editor codium --force

The command detects code, code-insiders, or codium, validates local VSIX paths, and installs using argument arrays instead of shell string execution. If no --path or --id is supplied, it installs the VSIX bundled in the CLI npm package and falls back to ./dist/*.vsix in a local checkout.