---
title: "Show HN: Ved AI Voice Assistant"
slug: "show-hn-ved-ai-voice-assistant"
date: 2026-07-09
category: community
tags: []
language: en
sources_count: 1
featured: false
publisher: AInauten News
url: https://news.ainauten.com/en/story/show-hn-ved-ai-voice-assistant
---

# Show HN: Ved AI Voice Assistant

**Published**: 2026-07-09 | **Category**: community | **Sources**: 1

---

## TL;DR

- Ved is a local offline AI agent for Windows, Linux, and macOS.

---

## Summary

- Ved is a local offline AI agent for Windows, Linux, and macOS. The repo lists 12 GB VRAM and 32 GB RAM for local models; with an OpenRouter cloud fallback, it claims to run on 4 GB VRAM and 16 GB RAM.
- It includes a Tkinter desktop UI, FastAPI server with SSE, LangGraph orchestration, standard, turbo, and coder modes, per-thread RAG, file uploads, script execution, and human approval for risky tool actions.
- The voice pipeline runs offline with wake word, faster-whisper, LLM, and Piper TTS, including barge-in while the assistant speaks. Next steps are server-client setup, smart-home mic endpoints, and secure remote access.

---

## Why it matters

Ved is a local offline AI agent for Windows, Linux, and macOS. The repo lists 12 GB VRAM and 32 GB RAM for local models; with an OpenRouter cloud fallback, it claims to run on 4 GB VRAM and 16 GB RAM.

---

## Key Points

- Ved is a local offline AI agent for Windows, Linux, and macOS. The repo lists 12 GB VRAM and 32 GB RAM for local models; with an OpenRouter cloud fallback, it claims to run on 4 GB VRAM and 16 GB RAM.
- It includes a Tkinter desktop UI, FastAPI server with SSE, LangGraph orchestration, standard, turbo, and coder modes, per-thread RAG, file uploads, script execution, and human approval for risky tool actions.
- The voice pipeline runs offline with wake word, faster-whisper, LLM, and Piper TTS, including barge-in while the assistant speaks. Next steps are server-client setup, smart-home mic endpoints, and secure remote access.

---

## Nauti's Take

Good direction, but still clearly a maker project rather than a finished home assistant. The README is more concrete than the HN pitch: hardware targets, model paths, API, UI, and telemetry are spelled out. That also raises the bar. If the promise is local privacy, remote access, telemetry, tool permissions, and update paths need careful design, otherwise offline just becomes self-hosted risk.

---


## FAQ

**Q:** What is Show HN about?

**A:** - Ved is a local offline AI agent for Windows, Linux, and macOS.

**Q:** Why does it matter?

**A:** Ved is a local offline AI agent for Windows, Linux, and macOS. The repo lists 12 GB VRAM and 32 GB RAM for local models; with an OpenRouter cloud fallback, it claims to run on 4 GB VRAM and 16 GB RAM.

**Q:** What are the key takeaways?

**A:** Ved is a local offline AI agent for Windows, Linux, and macOS. The repo lists 12 GB VRAM and 32 GB RAM for local models; with an OpenRouter cloud fallback, it claims to run on 4 GB VRAM and 16 GB RAM.. It includes a Tkinter desktop UI, FastAPI server with SSE, LangGraph orchestration, standard, turbo, and coder modes, per-thread RAG, file uploads, script execution, and human approval for risky tool actions.. The voice pipeline runs offline with wake word, faster-whisper, LLM, and Piper TTS, including barge-in while the assistant speaks. Next steps are server-client setup, smart-home mic endpoints, and secure remote access.

---

## Related Topics

- —

---

## Sources

- [Show HN: Ved AI Voice Assistant](https://github.com/Krish6190/Ved-Test) - Hacker News AI

---

## About This Article

This article is a synthesis of 1 sources, curated and summarized by AInauten News. We aggregate AI news from trusted sources and provide bilingual (German/English) coverage.

**Publisher**: [AInauten](https://www.ainauten.com) | **Site**: [news.ainauten.com](https://news.ainauten.com)

---

*Last Updated: 2026-07-09*