# SaarthurR/atticus-mac > macOS menu-bar voice assistant: hold ⌃⌥Space to speak, on-device speech recognition feeds Claude Code to control windows, files, apps and the screen. Runs on your existing Claude Pro/Max plan with no API key and learns your shortcuts. - Magnitude: 2.5 out of 10 — Steady - Stars: 30 total · +10 stars measured 2026-10-12, 07:55–09:31 UTC, ≈ 17 by evening - Star trust: star growth looks organic - Category: AI agents · Language: Python · License: MIT · Created: 2026-10-10 · Last push: 2026-10-12 - GitHub: https://github.com/SaarthurR/atticus-mac · Homepage: https://saarthurr.github.io/atticus-mac/ · Page: https://gitnova.dev/en/r/SaarthurR/atticus-mac ## Useful for - Arrange windows across two displays with a single voice command - Find a file by its contents and open it on another screen - Save a repeated command as an instant shortcut that skips the AI ## Why it’s here - Star-counter measurements on 2026-10-12 (UTC), 07:55–09:31: 20 → 30 stars (+10). This is the change over that interval. - Estimated end-of-day forecast: about +17 stars, using observed gains and the previous day. - The repository is 2 days old and already has 30 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet. - Hacker News: “Show HN: Atticus – Hold-to-talk voice assistant for macOS that runs on Claude -p” — 22 points, 9 h ago. ## Star trust Star growth looks organic. Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer. ## Numbers - Forks: 2 - Issues and pull requests: 0 - Watchers: 0 - Average over the last week: 7 per day - Usual pace: too little history (under two weeks) - Stars in the last hour (measured): 6 ## Stars per day, last 3 days (oldest → newest, today is partial) 2026-10-10 … 2026-10-12: 2, 2, 10 ## Hacker News - Show HN: Atticus – Hold-to-talk voice assistant for macOS that runs on Claude -p — 22 points, 1 comments: https://news.ycombinator.com/item?id=50049588 ## Spotted in now - Spotted on Hacker News ## More in this category 1. **morluto/rea** — 8.9 · Breakout · AI agents · TypeScript · +22,829 stars measured 2026-10-12, 00:13–09:25 UTC, ≈ 50,764 by evening A reverse-engineering tool that lets AI agents inspect apps and native binaries: it connects agents to Hopper or Ghidra via MCP and CLI, helping explain how a feature works and rebuild it in your own project. Full card: https://gitnova.dev/en/r/morluto/rea.md 2. **Fei2411/DeepSeek-Bot** — 7.7 · Early signal · AI agents · JavaScript · +336 stars measured 2026-10-12, 00:13–09:25 UTC, ≈ 757 by evening A DeepSeek Harness (DSH) plugin that turns DSH Web and Desktop into a multi-agent collaboration workspace, letting multiple agents communicate, coordinate and run in parallel. Full card: https://gitnova.dev/en/r/Fei2411/DeepSeek-Bot.md 3. **hugohe3/ppt-master** — 7.5 · Breakout · AI agents · Python · +360 stars measured 2026-10-12, 00:13–09:25 UTC, ≈ 877 by evening A tool that turns documents or topics into native PowerPoint decks with shapes, charts, tables, animations and narration, running inside an AI agent on your machine. Full card: https://gitnova.dev/en/r/hugohe3/ppt-master.md 4. **rociiu/talorys** — 7.1 · Early signal · AI agents · TypeScript · +60 stars measured 2026-10-12, 00:13–09:25 UTC, ≈ 201 by evening A single-user personal AI assistant deployed into your own Cloudflare account, combining chat, memory, tasks, notes and scheduled reminders with no server or database run by the developers. Full card: https://gitnova.dev/en/r/rociiu/talorys.md 5. **Ebony-Vinyl/dsh-our-free-model** — 6.6 · Breakout · AI agents · JavaScript · +1,597 stars measured 2026-10-12, 00:13–09:25 UTC, ≈ 3,474 by evening · unusual star pattern (heuristic) A dsh plugin that adds free access to Muse Spark 1.3, MiMo V2.6 and other models without sign-up or API key, plus a local OpenAI-compatible proxy and usage dashboard. Full card: https://gitnova.dev/en/r/Ebony-Vinyl/dsh-our-free-model.md --- Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score. Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast. Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself. Data as of 2026-10-12 09:41 UTC, updated every 30 minutes.