An agent decides which tool to call almost entirely from one thing: the tool's description. Not its name, not its parameters — the sentence or two that says "Read the contents of a file in the project" is what the model weighs when it picks read_file over run_command.

Until now those descriptions were string literals compiled into the plugin. You could switch a tool off, but you couldn't tell the model anything about the tools that remained. So "use ./gradlew, never a global gradle" or "prefer semantic search over grep in this repo" meant repeating yourself in every prompt, or editing the plugin.

You can now rewrite any built-in tool's description from Settings.

Agent Mode is fast. You describe a migration, walk away, and come back to a finished answer and a changed project. The answer tells you what the agent says it did. Until now, DevoxxGenie had nothing to show you what it actually did.

That gap had a name: issue #705. The old Git Diff/Merge feature was removed back in 0.4.x because MCP tooling had made it obsolete — and nothing replaced the part people actually missed. A user put it plainly on the closed issue a few days ago:

Was just desperately searching why this feature is not available. Could someone point me in the right direction how to get a diff/merge view for approving changes suggested by an agent?

Fair question. Here's the answer, shipping in v1.13.0.

We have a lot of numbers. The growth curve keeps climbing, and the analytics deep-dive told us which providers and features people actually reach for. What none of that tells us is the interesting part: what you are building with DevoxxGenie, and what it changed about your day.

So we made a page for it: genie.devoxx.com/success-stories.

The system prompt is the most powerful setting in DevoxxGenie and the one nobody touches twice. You write a good one, it works, and then it quietly becomes wrong for half of what you do. The prompt that makes a model a great pair programmer — write the code, be concrete, show me the diff — is exactly the prompt that makes it a mediocre reviewer, because a reviewer that starts rewriting your method has stopped reviewing it.

The usual workaround is to argue with the model in the prompt itself: "don't implement anything, just review". It works about as often as it doesn't.

Personas, new in DevoxxGenie 1.12.0, fix this the boring way: give each role its own system prompt, name it, and put the names in a dropdown.

The local AI story on the Mac has always been a bit of a scavenger hunt. The models live in a Hugging Face cache, the server is a Python process you babysit in a terminal, the performance numbers are whatever flew past in the logs, and the chat UI is a browser tab pointed at localhost. It all works, but nothing about it feels like it belongs on a Mac.

Nativ fixes that with one opinionated move: it puts the whole workflow — chat, model management, serving, monitoring, and even hardware telemetry — inside a single native SwiftUI app. And as of DevoxxGenie 1.10.1, it's a first-class provider in the plugin, sitting right next to Ollama and LM Studio in the LLM Providers list.

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.

Agent Mode is at its best when you stop babysitting it. Turn on "auto-approve read-only tools", let it explore, let it run your tests, and go get coffee.

The moment that stops being comfortable is run_command. Ninety-nine commands out of a hundred are ./gradlew test or git status. The hundredth is git reset --hard — and the agent runs it with the same cheerful confidence.

DevoxxGenie now lets you name that hundredth command in advance.

Running a 35B model on your laptop is impressive right up until you watch it type. Local inference on Apple Silicon is memory-rich and bandwidth-poor: every single token needs its own forward pass through the whole model, and that pass is dominated by shuffling weights from unified memory into the GPU. The math is fast. The waiting is not.

MTPLX attacks exactly that bottleneck, and it does it without the usual trade-offs. On a Mac mini it lands around 1.6x faster decode; on Qwen 3.6 27B the author measures up to 2.24x. And it does that while producing the same output your model would have produced anyway.

Every so often you glance at the dashboards and the numbers make you stop and just... smile. This is one of those weeks. DevoxxGenie has crossed 75,000 downloads on the JetBrains Marketplace, and the active-user curve has gone from a gentle slope to a proper hockey stick. Thank you, all of you. 🙏

Reasoning models don't just answer. They think first. They talk themselves through the problem, weigh options, and correct course before committing to a reply. Until now, all of that happened invisibly: you saw the polished answer, but never the reasoning that produced it.

Starting with DevoxxGenie 1.8.12, you can watch it happen. Turn on Show Thinking and the model's chain of thought appears in its own dedicated 🧠 section, streaming live, right before the final answer.