7 posts tagged with "llm"

Cloudflare AI Gateway sits in front of your LLM providers and gives you one place to route, cache, rate-limit, and observe every request - across OpenAI, Anthropic, Google, Workers AI, and more. Starting with DevoxxGenie v1.10.0, you can point the plugin straight at your gateway and use any model behind it, without leaving your IDE.

No per-provider setup inside the plugin. One Cloudflare token, your account ID, a gateway name - and you're talking to whatever you've configured behind the gateway.

Here's a quietly wild fact: NVIDIA is casually giving you access to a whole catalogue of frontier AI models - including five of the strongest Chinese frontier models - for free. 😳

No credit card. No subscriptions. Just one API key that unlocks everything.

Starting with DevoxxGenie 1.8.11, the plugin ships NVIDIA as a first-class cloud provider. Drop in your nvapi-... key, and the entire NVIDIA build catalogue shows up in the model dropdown - over 100 models, all reachable through a single OpenAI-compatible endpoint.

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.