Qoder provides AI Chat capabilities in two modes: Ask and Agent. These capabilities help developers solve coding problems, fix errors, debug, and troubleshoot runtime issues. Qoder also offers multi-file edits, autonomous decision-making, environment awareness, and tool use to complete end-to-end coding tasks. Install Qoder to explore more. Core features of Qoder’s AI Chat:
  1. Multiple chat modes
Within a single conversation flow, developers can freely switch between Ask and Agent modes. This flexibility enhances productivity and efficiency across development workflows.
  1. Automatic environment awareness
Qoder automatically detects project frameworks, technology stacks, required code files, and error messages from task descriptions. This eliminates the need to add context manually, making task descriptions easier.
  1. Tool use
Qoder autonomously uses over 10 built-in tools to assist with file read/write, code queries, and error troubleshooting. It also supports MCP tool configuration, allowing developers to customize their toolsets as needed.
  1. Command execution
Qoder autonomously determines, generates, and executes necessary commands, significantly improving the efficiency of task execution.
  1. Project-level changes
Based on the task description, Qoder enables modification of multiple code files within a project. Through multi-turn conversations, it supports code optimization or snapshot rollbacks, completing tasks more efficiently.
  1. Memory awareness
Qoder features LLM-based autonomous memory. It learns from each chat, gradually building a rich memory base related to the individual developer, specific projects, and encountered issues.

​
Start a new chat

​
Open the AI Chat panel

To start an AI chat, log on to Qoder, and toggle the secondary side bar in the top-right corner. Alternatively, use the keyboard shortcut:
ActionmacOSWindows
Open/Close AI Chat panel⌘ LCtrl L

​
Select a mode

  • Ask: A simple Q&A mode that answers coding questions. It gives solutions and suggestions based on context, but doesn’t modify code.
  • Agent: An autonomous coding task execution mode that features self-directed decision-making, environment awareness, and tool utilization. Based on the developer’s coding requirements, it leverages project search, plan making, file editing, terminal operations, and other tools to complete coding tasks end-to-end. It also supports developer-configurable MCP tools, ensuring the coding workflow aligns closely with individual development processes.

​
Input requirements

After selecting a chat mode, enter the requirement description in the input box. Consider the following recommendations for effective requirements:
  • Structure your request: Clearly state what you want Qoder to accomplish and outline the goals and steps for the coding task.
  • Provide context: Include files, images, code changes, and other relevant information to help Qoder better understand the background and generate more accurate solutions.
  • Specify expectations: State any preferences or guidelines-such as programming language, coding standards, output format, or change objectives. Example: “When generating code changes, also include comments for each method.”
  • Engage in iterative feedback: Give feedback on code suggestions or answers to help Qoder improve. For complex coding tasks, break down requirements and iterate step by step to collaboratively accomplish the task with Qoder.

​
Make plans by To-dos

Based on the inputs, Qoder will generate a plan to complete your requirements with a list of To-dos for you to review. This breaks down complex problems into manageable, sequential steps, providing a structured interface for collaboration between you and Qoder.

​
Code modification and review

​
Multi-file edits

In Agent mode, Qoder may make modifications to multiple code files. Each file modification involves both a generation and application process. You can view the affected files and their statuses in the chat box or the workspace:
  • Generating: Code suggestions are generated based on task breakdowns.
  • Applying: Suggestions are integrated with the original files to create new change files.
  • Applied: Code change files are completed and ready for review.
Clicking a specific file shows the code modification suggestion generation process and displays a diff comparison of the changes.

​
Review, accept, or reject modifications

Click the View Changes button in the workspace or individual files to compare modifications. Then:
  • Use the up or down arrow to navigate and view the changes in the current file.
  • Reject or accept each change.
  • Use the forward and backward arrows in the file-level operation area to switch between changed files.
  • Reject or accept in the file-level operation area.
  • Partially modify change files.

​
Multi-turn iterations

​
Refine requirements in multiple turns

In Agent mode, after completing a round of conversation and generating code change files, you can continue to supplement or modify your requirements by submitting additional queries. Qoder will incorporate the previously generated code changes, analyze the updated requirements, and produce one or more new code change files accordingly. Also, multiple snapshots will be generated based on your requirements. To revoke certain operations, just click the Undo button in the chatflow.

​
Start a new chat

To start a new chat, use either of the following methods:
  • Method 1: Click the add button in the upper-right corner of the AI Chat panel.
  • Method 2: Type / and then select /newChat in the chat box.

​
View chat history

Click the history icon in the upper-right corner of the AI Chat panel to see all chat histories.

​
Context

Qoder supports rich contextual information, such as code files, directories, images, git commits, and rules. It also enables flexible composition of prompts using both context and user input, allowing developers to freely combine and articulate their requirements. For more information, see Context.

​
Memory

Qoder offers long-term memory capabilities. As developers interact with Qoder, it gradually builds a rich memory base related to the individual developer, specific projects, and encountered issues. This memory is automatically organized and updated over time. With this capability, Qoder can interact with developers more effectively and, as time goes on, gain a deeper understanding of each developer’s unique needs and context. For more information, see Memory.

​
Tools

Qoder offers various tools to help programming in different aspects, such as:
  • File searching
  • File reading
  • Directory reading
  • Semantic symbol searching
  • File editing
  • Error checking
  • Command execution
When utilizing tools, Qoder operates autonomously, making decisions and executing actions without requiring developer confirmation or intervention. For more information, see Tools.

​
MCP

Qoder’s Agent mode integrates with MCP servers. Developers can configure their own MCP servers for the agent, expanding the capabilities of the AI coding assistant and better aligning it with how the developer works. The agent also connects to a marketplace for third-party MCP servers. This allows developers to install the required MCP servers with one click. For more information, see MCP.