Veai AI Agent

Veai AI Agent is an IDE-native AI agent that debugs, refactors, and tests through your JetBrains IDE — not through terminal commands — saving tokens by using IDE facts instead of noisy logs. Built for developers in large, complex codebases.

The agent uses IDE indexes, debugger state, and coverage data instead of dumping logs and grepping files — so it spends your tokens on answers, not on reading code the IDE already understands. Less noise, lower cost, faster results.

IDE-native debugging, refactoring, and testing

• Debug with real execution data: investigate failures with debugger state, stack traces, executed instructions, and data flow instead of adding log statements by hand.
• Refactor semantically: search symbols, find usages, rename, and update code through IDE indexes and refactorings, not grep-based edits that break cross-file references.
• Generate tests with coverage feedback: create or update unit, integration, and end-to-end tests, then use IDE coverage and branch-aware analysis to target uncovered paths.
• Find and fix security vulnerabilities: scan JVM projects for vulnerabilities with detailed findings and agent-assisted fixes.
• Fix quality issues in context: use inspections, quick fixes, library decompilation, and build/test results from the IDE.
• Keep your workflow native: run configurations, test runners, web search, webpage reading, and Allure TestOps data are available directly from the agent.

Use it for

• debugging with IDE execution data and stack traces
• generating tests with coverage feedback and detecting flaky tests
• finding and fixing security vulnerabilities (SAST)
• refactoring code with IDE-aware search and safe renames
• fixing pull request feedback, stack traces, test failures, and TMS-linked issues
• building features and microservices from specifications
• migrating code to new frameworks or library versions
• generating documentation and code comments

Open standards and team controls

• MCP and AGENTS.md support for portable AI workflows.
• Bring-your-own-key (BYOK) LLM support and edit-scope controls for teams.
• Enterprise: VPC deployment, self-hosting, and SSO.

Agent modes

General, Code, Test, Plan, Review, and Debug modes — each mode leverages IDE-specific tools (Debug mode runs the debugger, Test mode reads coverage data). Plus an Orchestrator that splits complex tasks across specialized subagents, and custom modes for team workflows.

Getting started

1. Install Veai AI Agent.
2. Open the agent from your JetBrains IDE.
3. Try Debug mode to investigate a failing test — it uses the IDE debugger, not log prints.

Start coding with your IDE's full power. Watch a quick demo, or submit an issue if you find a bug or want to share feedback.

If Veai AI Agent helps your work, please rate the plugin on JetBrains Marketplace.