AI Chat: Ollama, Local AI, LLMs | Living Web

Living Web is an AI Assistant browser Chrome extension that lets you use your locally running AI models, or your own API keys, to help with the page you are viewing. Summarize articles, ask questions, chat with documents, extract data, and automate repetitive browser tasks from a lightweight sidebar, without copying content into another tool. Local AI with Ollama, LM Studio, and llama.cpp: Connect Living Web to a local runtime and run supported AI processing on your own hardware. Page content and prompts stay on your machine. Works with open-weight LLM models such as Llama 3.3, DeepSeek-R1, Gemma, Qwen, and Mistral. Ideal if you want private, offline-capable AI assistance while browsing. Bring your own API keys (BYOK): No subscription required. Use your own keys for OpenAI GPT models, Anthropic Claude, Google Gemini, or DeepSeek, or connect through OpenRouter to reach many providers with one key. Keys are stored encrypted on your device and requests go directly to the provider you choose. Key features of our AI assistant: - Summarize web pages, articles, research papers, reports, youtube videos and product pages - Ask questions about any webpage and get answers in context - Chat with PDF, CSV, TXT, and Markdown files - Fill forms, click buttons, and navigate websites in natural language - Extract tables and page data, export to CSV or JSON - Switch between local and cloud models per task: speed, reasoning, or writing - Prompt caching and backup endpoints through OpenRouter - Lightweight sidebar built on Chrome Manifest V3 How our AI Assistant browser extension works: - Open any webpage or document. - Click the Living Web icon to open the sidebar. - Choose a local model from Ollama or a cloud provider with your key. - Ask in plain language: "Summarize this page", "Extract this table", "Help me fill this form". Built for developers, researchers, students, and privacy-focused users who want AI where they already work, inside the browser, on their own terms.