For months, DevoxxGenie's RAG pipeline worked beautifully — as long as you stayed in chat mode. Index your project into ChromaDB, ask a question, and the most relevant code chunks would automatically appear in the prompt as a <SemanticContext> block. It was invisible, automatic, and effective.

Then we shipped Agent Mode, and RAG fell off a cliff.

Users would ask conceptual questions like "which slides discuss MCP?" or "where do we explain the indexing pipeline?" and the agent would ignore the rich semantic context we had just injected. Instead, it reached for search_files — a regex grep — and returned nonsense. The semantic context had become wallpaper: present, but unseen.

DevoxxGenie has long had a way to bottle up reusable prompts as Commands: the /test, /explain, /review style slash commands that expand a template before sending it to the model. With the latest release we are adding a second, complementary mechanism called Skills: portable SKILL.md files on disk that the LLM itself decides to activate while it is thinking.

The big difference: Commands are typed by you, Skills are picked by the model. And because Skills live in the same directories that Claude Code, Codex and Gemini's .agents-aware tools already use, the same file can teach all four assistants the same playbook.

Cloud APIs are convenient, but they come with per-token costs, rate limits, and the nagging question of where your code actually goes. What if you could run the same frontier-class models (GLM, MiniMax, Kimi, DeepSeek) at full Q6 or even Q8 quality, entirely on hardware you already own?

With DevoxxGenie's refreshed Exo integration, you can. Pool the memory of multiple Apple Silicon Macs into a single inference cluster and run models that would never fit on one machine. No subscription. No token budget. Just electricity.

Security issues rarely announce themselves. Hardcoded API keys, injection vulnerabilities and outdated dependencies sit quietly in your codebase until someone finds them — ideally you, before anyone else does.

With v0.9.17, DevoxxGenie integrates three best-in-class open-source security scanners directly as LLM agent tools. Your AI assistant can now scan your project on demand, interpret the results in context, explain each finding, suggest remediations, and automatically create prioritised backlog tasks — all from a single prompt.

DevoxxGenie is not a closed system. It exposes a small but powerful API that other IntelliJ plugins can use to interact with it at runtime — no hard compile-time dependency required. Two real-world forks demonstrate the pattern beautifully: a SonarLint fork and a SpotBugs fork that each detect a code-quality finding and send a rich, context-aware prompt to DevoxxGenie with a single click.

In the previous blog post, we introduced CLI Runners — a way to use your existing AI subscriptions (Claude Pro, Copilot, Gemini, etc.) directly inside IntelliJ by piping prompts to external CLI tools. CLI Runners solved the "double-paying" problem, but they communicate through plain text over stdin/stdout. That works, but it's a bit like having a conversation by passing notes under a door.

ACP Runners open that door. Instead of unstructured text, they use the Agent Communication Protocol — a structured, bidirectional communication layer built on JSON-RPC 2.0 — to turn your IDE into a proper agent hub.

You're paying for Claude Pro. You've got a GitHub Copilot seat. Maybe you're subscribed to Google Gemini or Kimi too. But when you want to use these tools for serious coding work, you're jumping between terminal windows, browser tabs, and your IDE — context-switching constantly.

What if you could route all of that through a single interface inside IntelliJ, using the subscriptions you already pay for?

That's exactly what CLI Runners in DevoxxGenie do.

We've all been there. You open your AI coding assistant, type a prompt, get a result, realise it missed half the requirements, rephrase, try again. Rephrase and repeat. It works (kind of) but it doesn't scale and we lose history.

What if instead of ad-hoc prompting, you could define exactly what needs to be built as a structured spec, and then let the AI agent implement it autonomously — checking off acceptance criteria as it goes?

That's the idea behind Spec-driven Development (SDD), the latest feature in DevoxxGenie v0.9.7.

DevoxxGenie has come a long way from its origins as a simple LLM chat plugin for IntelliJ IDEA. With the latest releases, the plugin has made a fundamental shift — from passive AI assistance to agentic AI capabilities. This reflects a paradigm shift in how developers interact with AI: we're moving beyond generating code snippets toward autonomous agents that can explore, reason about, and modify your codebase.

DevoxxGenie is a powerful AI-powered assistant for IntelliJ IDEA that helps developers be more productive by leveraging the capabilities of Large Language Models (LLMs). Unlike other code assistants, DevoxxGenie is built entirely in Java and offers unique flexibility by supporting both local and cloud-based LLM providers.