Skip to content

AI Agent

From your task to a verified change.

Describe what you want to build. Lurus Code works inside your project: read context, plan changes, edit code and check the result – instead of just handing you the next snippet.

For Pro, Pro+ and Ultra. Paid subscription after the trial unless you cancel beforehand. Usage and features depend on your plan and credit.

Capture of a real agent session with a project task, tool steps and a checked change.
From task to change

Fewer handoffs

Your task does not end in a chat window.

Lurus Code connects context search, planning, implementation and testing. Describe the goal and the agent works through the connected task in your project.

From intent to change

How your task becomes a verified change.

  1. 01 / Understand

    Understand your project.

    The agent reads relevant files, dependencies and project rules. Existing patterns establish the foundation for the change.

    Relevant files and dependencies in project context.
    Understand the codebase
  2. 02 / Plan

    Plan the changes together.

    For larger tasks, ask for a plan first. Review the affected code and verification steps, then approve implementation.

    Capture of an implementation plan with affected files and verification steps.
    Plan before implementation
  3. 03 / Implement

    Implement in your project.

    The agent edits related files and runs suitable tools and terminal commands. Progress and changes remain visible.

    Tool use and concrete code changes.
    Implementation in the project
  4. 04 / Verify

    Verify the result.

    Tests, code review, security scanning and browser checks help verify changes. See which checks ran and which questions remain open.

    Capture of related diffs and the project checks that were run.
    Change and verification

The right level of autonomy

You decide how far the agent goes.

Ask

Answer a code question without changing files.

Plan

Prepare a larger change in read-only mode first.

Agent

Implement the confirmed task with the available tools.

Debug

Reproduce an issue, narrow down the cause and check a fix.

Tool access and approvals depend on your mode and permission settings. Review changes before accepting them.

Read the documentation

Your code stays yours.

Source code and request context are processed with Zero Data Retention. No use for model training. Providers and processing regions are disclosed transparently.

See privacy and processing details

A few things to know before you start.

Can I ask the agent to analyse first?
Yes. Ask and Plan are read-only modes. You can clarify project context or prepare an implementation before changes are executed.
Does the agent replace tests and code review?
No. The agent can run tests, linters and browser checks. You should still review changes and keep your project quality controls in place.
Where can I use the agent?
In the Lurus Code CLI and through the VS Code extension. Both work with your project and your Lurus Code account.

AI Agent

Move your next task forward.

Start with a real task from your project. Use Plan mode if you want to review the approach first.

For Pro, Pro+ and Ultra. Paid subscription after the trial unless you cancel beforehand. Usage and features depend on your plan and credit.

Want to start with your team? Talk to us.

A deliberate choice

Before your first prompt.

Interactive demo
Lurus Codeprivacy-demo · illustrative workspace

Demo session ready. Your model choice and data route are separate decisions.

Illustrative scenario. No real sign-in, security test or code transmission takes place.

Image preview