MacPaw launches Eney, a proactive AI assistant for Mac and iPhone
MacPaw releases Eney, an AI assistant that uses local and cloud models to manage files, apps, and system tasks across Apple devices.
Key points
- MacPaw launches Eney, a proactive AI assistant for Mac and iPhone that works across apps, files, and the system.
- The product originated in 2019 and evolved with LLM and agentic AI trends to use custom models optimized for Apple hardware.
- Eney uses a "Wand" feature invoked by cursor gesture or keyboard shortcuts to interact with on-screen content without switching apps.
MacPaw has released Eney, a proactive artificial intelligence assistant designed for Mac and iPhone, according to a report by 9to5Mac. The company stated that the tool operates across applications, files, and the operating system to help users complete tasks. This launch follows a development process that began in 2019, marking a significant milestone for the software vendor.
Eney distinguishes itself by understanding the specific context of the user's machine, including active apps, disk files, and calendar events, according to 9to5Mac. The assistant identifies items requiring attention, such as upcoming calls or low disk space, and prepares subsequent steps for user approval. This design aims to reduce the need for switching between multiple applications and tools to manage routine digital tasks.
Evolution of the Assistant
The concept for Eney originated in 2019 as a method to simplify MacPaw’s CleanMyMac software through natural-language commands, according to 9to5Mac. The project evolved alongside the rise of large language models and agentic AI technologies. MacPaw founder and CEO Oleksandr Kosovan explained that the company continuously reworked the assistant as underlying AI capabilities improved over time.
Recent advancements in local AI models have enabled them to handle complex tasks that previously required larger cloud-based systems, according to 9to5Mac. MacPaw leveraged these developments to refine Eney for its current release. The final product combines both local and cloud-based AI models to function effectively on Apple devices.
Integration and Hardware Optimization
MacPaw collaborated with Liquid AI to develop custom models optimized specifically for Apple hardware, according to 9to5Mac. This partnership supports the assistant's ability to process information efficiently on Mac and iPhone devices. The integration allows Eney to maintain system-wide awareness while managing computational resources through a hybrid model approach.
A key interface element is the Eney Wand, which users can invoke by shaking their cursor over text or using the Option + W shortcut, according to 9to5Mac. Users can also double-tap the Option key to access the assistant from any location on the screen. This feature addresses the friction of copying and pasting content into chat windows by allowing direct interaction with on-screen elements.
What should you do?
Security and technology professionals should monitor the release of new AI assistants like Eney to understand how they request system permissions and access local data. Organizations should
Background: Large language models
Large language models are a specific type of neural network trained on text. Generative AI is the broader umbrella term for any system that creates new content, including images and code. Not all generative AI uses large language models, but most modern text generators do.
What to do and how to stay safe
- Sudden role changes in output signal a successful override of system instructions.
- Hidden metadata in images or documents often carries invisible injection payloads.
- Immediate isolation of the affected session prevents lateral movement within the AI workflow.
Prompt injections exploit the model’s ability to follow instructions by hiding malicious commands in input data. Isolate affected sessions immediately and implement external guardrails to filter inputs before they reach the model.
Step-by-step guide: Prompt Injection Warning Signs: How to Spot AI Manipulation
General security guidance from the Threat Times newsroom. It is not confirmed advice from the organisations named in this story.
