LocalClicky brings offline macOS voice control

// 2h agoPRODUCT LAUNCH

LocalClicky brings offline macOS voice control

ANNOUNCEMENT PRODUCT GITHUB PRODUCT HUNT

LocalClicky is an open-source macOS menubar app that provides hands-free, offline computer control using local LLMs and voice recognition. Activated by a wake word, it allows users to chain voice commands to launch apps, click screen elements, and run shell commands without sending data to the cloud.

// ANALYSIS

While cloud voice assistants struggle with latency and privacy, LocalClicky offers a compelling offline alternative for hands-free Mac control, though running local LLMs and vision models will tax system resources.

–Fully offline execution ensures absolute privacy and works without API keys or subscriptions.
–Voice chaining eliminates repetitive wake-words, allowing natural back-to-back command flows.
–Leverages Ollama (Qwen/Gemma) and Whisper.cpp to enable reasoning-based tasks, UI interactions, and shell script executions.

// TAGS

macosvoice-controloffline-llmwhisperollamaopen-sourceautomation

DISCOVERED

2h ago

2026-06-05

PUBLISHED

7h ago

2026-06-05

RELEVANCE

7/ 10

AUTHOR

Dikshant Rajput

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

UPDATE52m ago

Anthropic adds 'Dreams' to Managed Agents API

Anthropic launched "Dreams", an asynchronous memory consolidation feature for the Claude Managed Agents API. The offline job prunes stale context and resolves contradictions, resulting in a cleaner and more performant long-term memory store.

MODEL1h ago

Gemma 4 12B Assistant accelerates decoding

The Gemma 4 12B IT Assistant checkpoint has caused developer confusion, as it is actually a speculative decoding drafter model rather than a standalone chatbot. When configured in tools like vLLM alongside the primary model, it accelerates inference via Multi-Token Prediction without degrading quality.

BENCHMARK1h ago

Google's Gemma 4 12B model faces criticism for slow local performance and poor multimodal generation on Apple Silicon.

A developer tested Google's Gemma 4 12B model on a MacBook Pro M5 Max with 128GB of unified memory, finding its performance disappointing for a model of its size. Achieving only 44 tokens per second, the developer noted that the model's generation quality was subpar—specifically criticizing a produced lava lamp image—and recommended developers stick with Qwen 3.6 27B or 35B instead.