KAVIA AI for VS CodeUnderstand 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 AIUnlike 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 speedOpen 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.
A new approach to code with workflowsKAVIA 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:
Explore more use cases at KAVIA AI use cases. HighlightsGo beyond code suggestions. KAVIA can:
KAVIA analyzes your repository to map architecture, trace dependencies, and investigate issues across files—not just the code open in your editor. Approval ModeStay 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. WorkflowsUse 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.
Multi-chat and specialist agentsKeep separate threads of work in separate tabs, each with its own conversation history. Use + to open a new chat or specialist-agent tab.
CodeWikiTurn 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. Documentation generationGenerate task-specific architecture overviews, feature write-ups, technical investigations, implementation plans, and test plans grounded in your codebase. Change impact analysisTrace dependencies across your codebase to understand which components a proposed change may affect. MCP integrationsConnect 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. SkillsDefine coding standards, review checklists, and repository-specific conventions once, then reuse them across tasks instead of repeating instructions in every prompt. Report issuesUse 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. Codebase-grounded chat
Ask questions, investigate issues, and perform engineering work using:
Add the right contextType
Getting started
You can also run KAVIA AI: Open KAVIA AI from the Command Palette. Keyboard shortcut
Requirements
Get started todayInstall 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 testingSee the desktop E2E harness guide for reusable Playwright fixtures, isolated VS Code launches, scenario authoring, and failure diagnostics. Summary
|