No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by sosoj92 · MCP Server · ★ 329
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is jarvis-assistant-vocal safe to install? View the security audit →
🤖 Jarvis — assistant vocal local English version Un assistant vocal en français qui tourne sur ta machine. Dis « Hey Jarvis », parle naturellement : il raisonne avec un LLM, utilise une boîte à outils extensible (domotique, PC, web, téléphone…) et te répond à voix haute. Deux modes au choix, en une ligne de config : cloud (Claude + ElevenLabs) ou 100 % local hors ligne (Ollama + Piper). Projet perso partagé tel quel. Cible Windows 11, nécessite un micro et (en mode cloud) une clé API Anthropic. La plupart des intégrations sont optionnelles et se désactivent proprement si non configurées. ✨ Fonctionnalités 🎙️ Tout à la voix — mot d'activation (openWakeWord), transcription locale (Whisper), réponses parlées 👁️ Vision de l'écran — « c'est quoi cette erreur ? », « lis ça », « traduis » (capture → LLM) 💡 Domotique — Philips Hue (allumer, luminosité, couleur), ambiances/scènes 🎬 Streaming — contrôle d'OBS (direct, enregistrement, scènes, replay) 🖥️ Contrôle PC — lancer des apps, média/volume, stats GPU/CPU/RAM en direct 📅 Agenda — Google Agenda sur tous tes agendas (y compris abonnés iCal), création/suppression avec confirmation
| Stars | 329 |
| Forks | 73 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 59.3204802025043/100 |
| Open Issues | 9 |
| Last Updated | 2026-09-20 |
| Created | 2026-08-07 |
| Platforms | browser, claude-code, mcp, python |
| Est. Tokens | ~15k |
These tools work well together with jarvis-assistant-vocal for enhanced workflows:
Looking for a jarvis-assistant-vocal alternative? If you're comparing jarvis-assistant-vocal with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
The self-hosted AI studio: local video, image, music, voice, LoRA training, coding swarms, RAG and screen agen
🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support
🎙️ AI Dictation App - Open Source and Local-first ⚡ Type 3x faster, no keyboard needed. 🆓 Powered by open so
The python library for research and development in NLP, multimodal LLMs, Agents, ML, Knowledge Graphs, and mor
Control and query Home Assistant from Claude and other LLMs — a Model Context Protocol (MCP) server.
Polymcp provides a simple and efficient way to interact with MCP servers using custom agents
Explore other popular mcp server tools:
jarvis-assistant-vocal is Assistant vocal local en francais : Claude ou Ollama (offline), domotique Hue, OBS, agenda, navigateur, appels Twilio, serveur MCP. Python.. It is categorized as a MCP Server with 329 GitHub stars.
jarvis-assistant-vocal is primarily written in Python. It covers topics such as anthropic-claude, browser-automation, home-automation.
You can find installation instructions and usage details in the jarvis-assistant-vocal GitHub repository at github.com/sosoj92/jarvis-assistant-vocal. The project has 329 stars and 73 forks, indicating an active community.
jarvis-assistant-vocal is released under the MIT license, making it free to use and modify according to the license terms.
The top alternatives to jarvis-assistant-vocal on Agent Skills Hub include guaardvark, web-agent-protocol, amical. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: