Skip to content
| Marketplace
Sign in
Visual Studio Code>Programming Languages>KAVIA AI for VS CodeNew to Visual Studio Code? Get it now.
KAVIA AI for VS Code

KAVIA AI for VS Code

KAVIA AI

|
648 installs
| (6) | Free
KAVIA AI - From codebase understanding to reviewable delivery, inside Visual Studio Code
Installation
Launch VS Code Quick Open (Ctrl+P), paste the following command, and press enter.
Copied to clipboard
More Info

KAVIA AI for VS Code

Understand any codebase. Ship reviewed, trustworthy changes, without leaving your editor. KAVIA AI reads and reasons over your actual repository, not just the files you have open, so it can trace real dependencies, investigate real bugs, and generate code and documentation that fit how your codebase actually works. It supports quick conversations and structured workflows for larger engineering tasks, with Approval Mode for reviewing proposed changes before they are applied.

Why KAVIA AI

Unlike assistants that only suggest snippets in the current file, KAVIA AI uses context across your repositories, supports living documentation through CodeWiki, and provides approval controls for proposed changes and commands, so you get repo-aware answers and reviewable work.

Build and evolve enterprise software with reliability and speed

Open a repository, describe the outcome you need, and add the files, folders, selections, logs, or documents that matter. KAVIA uses workspace context and shared project knowledge to help you move from a question or requirement to reviewable engineering work.

The VS Code extension extends KAVIA AI from the cloud into your local development environment. See the cloud version at chat.kavia.ai.

KAVIA AI workflow

A new approach to code with workflows

KAVIA helps you ask system-level architecture questions, trace business logic across services and repositories, and get answers that account for component interactions instead of only a single function.

KAVIA is designed for teams working on:

  • Brownfield modernization and large-scale refactoring
  • RDK, OpenWrt, and Yocto projects
  • Multi-repository enterprise applications
  • Embedded and platform software
  • Android and AOSP-based systems
  • Cross-team feature development
  • Root-cause and impact analysis
  • Architecture documentation and knowledge transfer
  • Reviewable, approval-driven delivery

Explore more use cases at KAVIA AI use cases.

Highlights

Go beyond code suggestions. KAVIA can:

  • Explain unfamiliar code and architecture
  • Trace dependencies and assess change impact
  • Investigate defects and failing tests
  • Plan and implement features
  • Refactor and maintain existing code
  • Generate tests and technical documentation
  • Review and synchronize changes with your Git workspace

KAVIA analyzes your repository to map architecture, trace dependencies, and investigate issues across files—not just the code open in your editor.

KAVIA VSCE

Approval Mode

Stay in control. With Approval Mode enabled, review proposed file changes as diffs and inspect commands before approving them. Approve, reject, or request revisions before supported actions proceed.

Interactive Change Review

Workflows

Use structured workflows for multi-step engineering work. Workflows coordinate agents through stages such as planning, implementation, testing, documentation, and review. Choose a workflow for a defined outcome, or use chat for quick, iterative work.

KAVIA AI workflow

Multi-chat and specialist agents

Keep separate threads of work in separate tabs, each with its own conversation history. Use + to open a new chat or specialist-agent tab.

Tab or agent Use it for
Task Follow the main engineering task or workflow and its progress.
Chat Explore ideas, discuss documents, and turn conversations into decisions, specifications, and next steps.
Ask Get focused answers grounded in the context you provide.
RCA Agent Investigate incidents and unexpected behavior to identify root causes, contributing factors, and next steps.
Documentation Agent Create architecture, API, onboarding, or CodeWiki documentation.
Code Review Agent Review code, diffs, or pull requests for correctness, maintainability, and risks.
Fix Agent Investigate a bug report, failing test, or error trace, then fix and verify the result.

Direct Chat and Attachments

CodeWiki

Turn your codebase into structured, navigable documentation covering architecture, features, dependencies, and quality practices. Generate and maintain CodeWiki alongside repository changes to keep onboarding and architecture references useful.

Codewiki

Documentation generation

Generate task-specific architecture overviews, feature write-ups, technical investigations, implementation plans, and test plans grounded in your codebase.

Documentation

Change impact analysis

Trace dependencies across your codebase to understand which components a proposed change may affect.

Change Impact Analysis

MCP integrations

Connect supported local or remote Model Context Protocol servers to bring external tools and data into KAVIA. Review and approve tool use through the supported approval controls.

MCP integration

Skills

Define coding standards, review checklists, and repository-specific conventions once, then reuse them across tasks instead of repeating instructions in every prompt.

Report issues

Use KAVIA AI: Report Issue from the Command Palette or the chat toolbar to describe a problem and submit an issue report with available session context and diagnostics.

Report Issues

Codebase-grounded chat

KAVIA AI workflow

Ask questions, investigate issues, and perform engineering work using:

  • The active editor
  • Selected code
  • Open files
  • Workspace files and folders
  • Project structure
  • Shared project knowledge

Add the right context

Type @ to add a file, folder, or editor selection to your request. The selected context remains visible before the request is sent, so you stay in control of what KAVIA uses.

  • Files and folders
  • Selected code
  • Logs and test output
  • Images and technical documents
  • Pasted text

Getting started

  1. Install KAVIA AI for VS Code.
  2. Open your repository or workspace.
  3. Open KAVIA AI from the secondary sidebar.
  4. Sign in with your KAVIA account.
  5. Start a chat or choose an engineering workflow.
  6. Add relevant context and describe the outcome you need.
  7. Review and approve proposed actions or changes.

You can also run KAVIA AI: Open KAVIA AI from the Command Palette.

Keyboard shortcut

  • macOS: Cmd+Alt+K
  • Windows and Linux: Ctrl+Alt+K

Requirements

  • Visual Studio Code 1.96 or later
  • A KAVIA account
  • An open workspace for codebase-aware features
  • Network access to KAVIA services
  • Git for supported synchronization workflows

Get started today

Install KAVIA AI and turn your next investigation, refactor, or feature request into a reviewed, approved change, right from VS Code.

For support, visit kavia.ai/contact.

Developer testing

See the desktop E2E harness guide for reusable Playwright fixtures, isolated VS Code launches, scenario authoring, and failure diagnostics.

Summary

Topic Summary
Product KAVIA AI brings repository-aware conversations and engineering workflows into VS Code.
Getting started Install the extension, open a workspace, and sign in to a KAVIA account.
Developer testing The desktop E2E guide covers reusable tests against the actual VS Code Electron workbench.
  • Contact us
  • Jobs
  • Privacy
  • Manage cookies
  • Terms of use
  • Trademarks
  • Your Privacy Choices
  • Consumer Health Privacy
© 2026 Microsoft