An AI coding assistant for terminal developers: driven by natural language, it autonomously reads files, invokes tools, runs commands, and asks for confirmation before critical operations based on your permission settings
What is Qoder CLI CN
Qoder CLI CN is the command-line AI coding assistant under the Qoder brand. It brings powerful AI coding capabilities directly into your terminal. Without leaving the command line, you can have Qoder understand your entire codebase, write and modify code, run commands, search for information, and complete the full development workflow from exploration to commit.
Qoder CLI CN is built for developers who are used to working in the terminal. It runs conversationally: you describe what you want in natural language, and Qoder autonomously decides which files to read, which tools to invoke, and which commands to run, asking for your confirmation before critical operations according to your permission settings.
Core capabilities
Qoder CLI CN's capabilities fall roughly into the following categories:
Code understanding and generation
- Query and edit large codebases, understanding project structure and dependencies across files.
- Multimodal input support (such as images and PDFs), generating code from design mockups or screenshots.
- Describe a bug in natural language and let Qoder locate and fix it.
- File reading, writing, and editing; directory browsing.
- Shell command execution.
- Code search (Grep) and file lookup (Glob).
- Web search and web page fetching for real-time information.
- Automate repetitive tasks such as Git operations, commits, and PR handling.
- Connect external services and custom tools via MCP (Model Context Protocol); see MCP.
- Headless (non-interactive) mode for running in scripts and CI/CD pipelines; see Run in Scripts.
- Extend Qoder CLI CN's behavior to fit your team's needs with Skills, Plugins, Subagents, Hooks, and Custom Commands.
- Let Qoder remember project conventions and team knowledge with Memory and Knowledge Base.
How it runs
At the core of Qoder CLI CN is an Agent: it receives your request, plans the steps, invokes tools to complete the task, and continuously adjusts its strategy based on the results along the way. The whole process revolves around four elements working together:
- Agent: understands intent, plans steps, and decides the next action.
- Tools: the Agent interacts with your project and environment through tools, such as reading and writing files, running commands, and searching code.
- Permissions: before performing operations with side effects (such as writing files or running commands), Qoder either asks for confirmation or proceeds directly, according to your permission settings.
- Context: conversation history, project instructions (
AGENTS.md), and long-term memory together form the background information Qoder relies on to complete tasks.
Multiple ways of working
The same task can be completed in different ways. Qoder CLI CN offers multiple ways of working, covering scenarios from instant conversation to long-running automation:
- Interactive mode: work as you chat — the most common default.
- Plan (plan before executing): analyze the problem and confirm the approach first, then start changing code.
- Goal (work toward a goal continuously): set a completion condition and let Qoder keep working until the goal is achieved.
- Scheduled tasks: run once at a specified time, or repeat on a calendar schedule.
- /loop (repeated execution): run the same task repeatedly at fixed intervals.
- Headless (run in scripts): run in non-interactive environments with structured output.
Typical scenarios
Qoder CLI CN is a good fit for the following typical scenarios:
- Understanding an unfamiliar codebase: quickly grasp project architecture, locate key modules, and trace call relationships.
- Implementing features and fixing bugs: start from a requirement or bug description and complete coding, testing, and verification.
- Refactoring and bulk changes: apply consistent structural changes across multiple files.
- Everyday development automation: generate commit messages, review changes, handle PRs, and write tests.
- Pipeline integration: run non-interactively in CI/CD to embed AI capabilities into automated workflows.
Next steps
- Not installed yet? Start with Installation and Upgrade.
- Already installed? Head to Sign-in and Authentication to set up your account.
- Want to dive in right away? Follow the Quick Start to complete your first task in a real project.