{"slug": "jarvis-control-center-local-browser-agent-powered-by-gemma-4", "title": "Jarvis Control Center: Local Browser Agent Powered by Gemma 4", "summary": "A developer built Jarvis Control Center, a local-first browser agent that turns natural-language requests into automated browser actions. The agent runs Gemma 4 locally through Ollama for reasoning and tool selection, then executes actions such as opening sites, searching, and playing YouTube videos via Playwright, with optional ElevenLabs voice output enabled through environment variables. The project is open source and designed so conversations stay on the user's machine rather than a hosted API.", "body_md": "I built Jarvis Control Center, a local-first browser agent that lets users control their computer with natural language.\n\nYou can ask it to open websites, search the web, play YouTube videos, manage tasks, and use connected tools. For example:\n\n“Open YouTube and play 11K by Seedhemaut.”\n\nJarvis uses Gemma locally to understand the request, decide whether a tool is needed, and execute the browser action through Playwright.\n\nIt saves users from repeatedly opening tabs, searching manually, and performing routine browser workflows.\n\nThe launch demo is available in the repository README:\n\n[View the Jarvis Control Center repository](https://github.com/srikar-naidu/gemma-browser-agent)\n\nThe demo shows Jarvis receiving a YouTube request, opening the browser, searching for “11K — Seedhemaut,” and playing the result.\n\nJarvis is built with:\n\nThe project is designed to work locally by default. Users can run Gemma through Ollama without sending their conversations to a hosted AI API. Optional cloud services can be enabled through environment variables when voice output or external integrations are needed.\n\nOpen innovation made it possible to build an AI assistant that users can run and customize on their own machines.\n\nUsing an open-weight model through Ollama means the core assistant can work locally, with more privacy and control than a closed hosted API. Developers can inspect the system, change the agent logic, add new tools, and adapt the model to their own workflows.\n\nThe project also combines multiple open technologies instead of locking the entire experience to one provider.\n\nJarvis turns multi-step browser workflows into a single natural-language request.\n\nInstead of opening YouTube, searching for a song, checking the result, and pressing play manually, the user can give one instruction and let the browser agent handle it.\n\nThe same pattern can be extended to web research, task management, calendar actions, email workflows, and other repetitive browser tasks.\n\nGitHub Copilot helped bootstrap and accelerate the initial implementation. The project was then cloned into this repository and further developed with a local-first Gemma architecture, browser automation, Convex, and optional ElevenLabs voice output.\n\nGemma 4 is the core reasoning model used by Jarvis through Ollama, while ElevenLabs provides optional natural-sounding text-to-speech when cloud services are enabled.", "url": "https://wpnews.pro/news/jarvis-control-center-local-browser-agent-powered-by-gemma-4", "canonical_source": "https://dev.to/srikar_naidu/jarvis-control-center-local-browser-agent-powered-by-gemma-4-n2g", "published_at": "2026-10-25 17:09:03+00:00", "updated_at": "2026-10-25 17:13:22.934608+00:00", "lang": "en", "topics": ["ai-agents", "ai-tools", "large-language-models", "developer-tools"], "entities": ["Jarvis Control Center", "Gemma 4", "Ollama", "Playwright", "ElevenLabs", "Convex", "GitHub Copilot"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/jarvis-control-center-local-browser-agent-powered-by-gemma-4", "markdown": "https://wpnews.pro/news/jarvis-control-center-local-browser-agent-powered-by-gemma-4.md", "text": "https://wpnews.pro/news/jarvis-control-center-local-browser-agent-powered-by-gemma-4.txt", "jsonld": "https://wpnews.pro/news/jarvis-control-center-local-browser-agent-powered-by-gemma-4.jsonld"}}