jarvis-assistant-vocal

Active·★ 487·MIT·Updated 2026-10-20

Jarvis is a local, open-source French voice assistant designed to run entirely on your machine, utilizing LLMs and an extensible toolkit for various automations. It offers comprehensive control over smart home devices, PC functions, web browsing, and includes advanced features like multi-agent delegation and long-term memory, with strong emphasis on privacy and local operation.

jarvis-assistant-vocal sits in the Voice / Speech category, so it is usually better judged by workflow fit, deployment style, and team needs than by isolated features alone. Based on the available metadata, it leans most clearly toward Full Voice Control: Wake word detection, local speech-to-text (Whisper), and spoken responses.. A representative use case is Control smart home devices and PC functions via voice commands, such as adjusting lights or launching applications.. The listed license is MIT. GitHub stars are currently 487. Relevant tags include Voice Assistant, Local AI.

#Voice Assistant#Local AI#LLM#Home Automation#Desktop Automation#Multi-Agent#Privacy#Speech Recognition

Features

01Full Voice Control: Wake word detection, local speech-to-text (Whisper), and spoken responses.

02Long-Term Memory: Remembers user preferences, contacts, and projects for personalized interactions.

03Delegation to Hermes: Offloads deep thinking and research tasks to a local deliberative agent.

04Browser Assistant: Summarizes/translates active browser tabs, manages tabs, and interacts with web pages.

05Home Automation: Controls Philips Hue lights (on/off, brightness, color), and manages scenes.

Why choose it

+Full Voice Control: Wake word detection, local speech-to-text (Whisper), and spoken responses.

+Long-Term Memory: Remembers user preferences, contacts, and projects for personalized interactions.

+Control smart home devices and PC functions via voice commands, such as adjusting lights or launching applications.

+Supports 7 platforms or runtime environments.

Trade-offs

!The final decision should still be made through side-by-side comparison with similar tools.

Compatibility

Python 3.13

Runtime

Verified via docs

Windows 11

Verified via docs

Docker

Environment

Verified via docs

Ollama

LLM Backend

Verified via docs

Piper

TTS Engine

Verified via docs

Claude (Anthropic API)

LLM Backend

Verified via docs

Quick start

$ uv sync

$ uv run playwright install chromium

$ copy config.example.yaml config.yaml

$ uv run python jarvis14.py

Use cases

↳Control smart home devices and PC functions via voice commands, such as adjusting lights or launching applications.

↳Automate web tasks like summarizing browser tabs, translating content, or making restaurant/appointment reservations.

↳Manage personal agenda, emails, and social media activities vocally, including creating events or getting mail summaries.

↳Delegate complex research or content generation tasks to a local multi-agent system for in-depth analysis.

↳Maintain long-term memory for personalized interactions, remembering user preferences and ongoing projects for task continuity.

Alternatives

⚡Top VS:

VSjarvis★2.1k→VSInteractive-LLM-Powered-NPCs★732→VSai-doc-gen★768→VSxiaozhi-esp32-server★11.0k→

jarvis★ 2.1k

Private local AI assistant for your desktop. Voice and text chat, personal memory, dictation and MCP tools. Runs offline with Ollama or OpenAI-compatible servers on macOS, Windows and Linux.

Features

Why choose it

Trade-offs

Compatibility

Quick start

Use cases

Alternatives

Comments

Features

Why choose it

Trade-offs

Compatibility

Quick start

Use cases

Alternatives

Comments