devoxx/DevoxxGenieIDEAPlugin

DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development with CLI Runners.

What it solves

DevoxxGenie is an AI-powered code assistant for IntelliJ IDEA that bridges the gap between simple chat interfaces and autonomous agentic programming. It solves the problem of fragmented AI tools by integrating a vast array of local and cloud LLM providers, security scanners, and task management systems directly into the developer's IDE.

How it works

The plugin acts as an orchestration layer within IntelliJ IDEA, utilizing Langchain4j to connect to LLMs. It offers several operational modes:

  • Agent Mode: Allows the AI to autonomously explore and modify code using built-in tools for reading, writing, and searching files.
  • Spec Driven Development (SDD): Uses Backlog.md files to define tasks, which are then managed via a visual Kanban board and can be implemented autonomously by the agent.
  • Agent Loop: Executes batches of tasks sequentially, handling dependency ordering automatically.
  • Integration Layers: It supports the Model Context Protocol (MCP) for external tools, ACP Runners for communicating with other agents (like Claude Code or Copilot), and a Plugin Integration API for other IntelliJ plugins to send prompts.

Who it’s for

It is designed for Java developers and software engineers using IntelliJ IDEA who want to leverage both local LLMs (for privacy/cost) and frontier cloud models to automate coding, security auditing, and project management.

Highlights

  • Extensive Provider Support: Integrates with local providers (Ollama, LM Studio, Llama.cpp, Exo) and cloud providers (OpenAI, Anthropic, Gemini, Mistral, etc.).
  • Autonomous Security Scanning: Integrates Gitleaks, OpenGrep, and Trivy to find secrets and vulnerabilities, automatically converting findings into backlog tasks.
  • Agentic Workflow: Features a full SDD pipeline with Kanban boards and an Agent Loop for batch task execution.
  • Advanced Context: Supports RAG for project files, AST-based context for better code analysis, and web search via Google and Tavily.
  • Interoperability: Implements MCP and ACP for seamless communication with external AI agents and tools.

Related

  • Project
    zhukunpenglinyutong/jetbrains-cc-gui

    An IntelliJ IDEA plugin that provides a visual interface for AI coding CLIs like Claude Code and OpenAI Codex, streamlining AI-assisted programming.

  • Project
    LnYo-Cly/ai4j

    A Java AI Agentic SDK for JDK 8+ that provides unified access to multiple LLM platforms, tool calling, RAG, and agent runtime capabilities.

  • Project
    codeaholicguy/ai-devkit

    AI DevKit is a local npm‑based control plane that unifies configuration, monitoring, cross‑agent messaging, searchable SQLite memory, and composable engineering “skills” (requirements, design, testing, review, etc.) for many AI coding assistants such as Claude Code, Gemini CLI, Codex CLI, Cursor, and GitHub Copilot. It lets teams manage multiple agents from a single console, keep project conventions in a searchable store, and enforce a senior‑engineer workflow without modifying the underlying LLMs.

  • Project
    codota/tabnine-vscode

    An AI code assistant providing context-aware completions and chat to accelerate software development while ensuring data privacy and security.

  • Project
    QwenLM/qwen-code

    An open-source AI coding agent that lives in the terminal, IDE, or desktop, supporting multiple LLM providers and local models to automate software development tasks.