{"slug": "anovax-voice-assistant-runs-locally-on-user-s-computer", "title": "AnovaX voice assistant runs locally on user's computer", "summary": "AnovaX, a new voice assistant described in a preprint on arXiv, runs entirely locally on a user's computer using a single Python process and Gemini-generated JSON plans, avoiding cloud-orchestration frameworks. The architecture uses typed executor agents with bounded thread pools, speculative execution of read-only tools to hide LLM latency, and a localized ReAct recovery loop capped at two recursive planning levels, demonstrating reliable desktop automation with local safety whitelists.", "body_md": "[arXiv](https://arxiv.org/abs/2607.15367)\n\n### AnovaX voice assistant runs locally on user's computer\n\nWhich summary reads better? Pick one — models revealed after.Both summaries are AI-generated.\n\nAnovaX demonstrates that robust desktop automation can run entirely in a single local Python process, using a bounded thread pool of typed executor agents directed by Gemini-generated JSON plans. To maintain responsiveness, the architecture hides LLM planning latency by speculatively executing read-only tools while a localized ReAct recovery loop handles single-step failures within a hard limit of two recursive planning levels. For production engineers, this proves you can bypass complex cloud-orchestration frameworks and ship reliable, self-recovering OS agents using lightweight thread locks, local safety whitelists, and structured JSON planning.\n\nThe whole architecture is a few-thousand-line single Python process: LLM (Gemini) does planning only—emitting JSON tool-call plans—while typed per-tool agent classes (each with own timeout, retry, resource locks) do the actual desktop actuation, gated by a whitelist/denylist and a ReAct recovery loop that speculatively runs read-only tools to hide LLM latency. The pattern worth stealing: keep the model out of the actuation path entirely, wrap each executor as a typed agent with bounded concurrency and its own retry/lock policy, and cap recursive self-delegation (here at two levels) so plan expansion stays predictable and legible.", "url": "https://wpnews.pro/news/anovax-voice-assistant-runs-locally-on-user-s-computer", "canonical_source": "https://www.snipvote.com/story/cmrtk39vj0004j4lqlac7iixz", "published_at": "2026-07-20 12:00:00+00:00", "updated_at": "2026-07-20 18:54:45.250746+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-products"], "entities": ["AnovaX", "Gemini", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/anovax-voice-assistant-runs-locally-on-user-s-computer", "markdown": "https://wpnews.pro/news/anovax-voice-assistant-runs-locally-on-user-s-computer.md", "text": "https://wpnews.pro/news/anovax-voice-assistant-runs-locally-on-user-s-computer.txt", "jsonld": "https://wpnews.pro/news/anovax-voice-assistant-runs-locally-on-user-s-computer.jsonld"}}