DevoxxGenie

Devoxx Genie - Your AI-powered coding assistant for IntelliJ IDEA

📖 Full Documentation at genie.devoxx.com

Key Features

• Local & Cloud LLMs: Ollama, LMStudio, GPT4All, Llama.cpp, Exo + OpenAI, Anthropic, Gemini, Mistral, Groq, DeepInfra, DeepSeek, Kimi, GLM, OpenRouter, Azure OpenAI, Amazon Bedrock
• Agent Mode: Autonomous code tools with parallel sub-agents, multi-turn tool use, and built-in file/search/run_command tools
• Skills (new in v1.5.0): Portable SKILL.md files the LLM activates mid-conversation — the same files also work in Claude Code, Codex and Gemini
• Commands: User-defined slash commands (previously "Custom Prompts") for reusable prompt templates
• MCP Support: Model Context Protocol with integrated marketplace for installing servers (stdio and HTTP/SSE transports)
• Spec Driven Development: Backlog.md task management with Spec Browser, Kanban Board, and Agent Loop batch execution with dependency ordering
• Security Scanning: Run Gitleaks (secrets), OpenGrep (SAST) and Trivy (CVEs) as agent tools — findings auto-create prioritised backlog tasks
• Inline Code Completion: AI-powered suggestions as you type using Fill-in-the-Middle models via Ollama or LM Studio
• ACP & CLI Runners: Integrate external agents (Claude Code, Codex, Gemini CLI, Kimi, Copilot) via the Agent Communication Protocol or CLI invocation
• RAG: Retrieval-Augmented Generation for semantic code search (ChromaDB + Ollama embeddings)
• Web Search: Integrate Google and Tavily search into your prompts
• Plugin Integration API: Other IntelliJ plugins can send findings to DevoxxGenie at runtime via a reflection-based ExternalPromptService
• Chat History: Locally stored conversations (SQLite) with parallel conversation tabs
• Token Cost Calculator: Real-time cost and context-window estimation for cloud providers
• Multi-modal Support: Drag & drop images for vision models, plus Git diff and project-context attachments

Quick Start

• Install the plugin
• For local LLMs: install Ollama, LMStudio, GPT4All, Llama.cpp or Exo
• For cloud LLMs: add your API keys in Settings → DevoxxGenie → LLM Providers
• Optional: enable Agent Mode, configure MCP servers from the marketplace, or drop a SKILL.md into .devoxxgenie/skills/, .claude/skills/ or .agents/skills/
• Start prompting!

Need help? Visit our Getting Started Guide or check the Troubleshooting page.

Privacy & Anonymous Usage Analytics

To guide which LLM providers and models receive engineering investment, DevoxxGenie collects anonymous usage data when you run a prompt or change models.

What is sent:

• An anonymous install ID (UUID), generated once and stored locally
• A per-launch session ID (random 10-digit number)
• Plugin version and IDE version
• LLM provider name (e.g. anthropic, ollama)
• LLM model name (e.g. claude-3-5-sonnet)
• Which optional features are enabled (RAG, Agent mode, MCP, Web Search, streaming) and coarse counts such as the number of configured MCP servers or custom prompts — never server names, URLs, commands, or user-defined prompt names
• Which features are actually used during a prompt (RAG, Agent, MCP, Web Search, project context, custom prompts) — feature identifiers only, never prompt text or file content

What is never sent: prompt text, response text, conversation history, file content, file paths, project names, git remotes, API keys, credentials, token counts, cost data, MCP server names/URLs/commands, or user-defined custom prompt names.

A first-launch notification asks for your consent before any data is sent. You can change this any time in Settings → DevoxxGenie → Analytics.