֎🇦🇮 A private, local AI assistant for your documents—without sending data to the cloud.
[repo]: https://github.com/mscbuild/local-docs-ai-agent/ [demo]: https://mscbuild.github.io/local-docs-ai-agent/ # 🌟 LocalDocsAI assistant **A private, local AI assistant for your documents—without sending data to the cloud** <a href="https://github.com/mscbuild"><img src="https://img.shields.io/badge/AI-Code%20Assist-EB9FDA"></a>  [](http://mscbuild.github.io/)        <img width="1200" height="494" alt="ai agent" src="https://github.com/user-attachments/assets/36affcb3-175a-4f1e-b98d-a5533181ed08" /> ##### [ View Live Preview][demo] # 💡 The gist of the idea Users upload their PDF, DOCX, TXT, or notes (e.g., from Obsidian, Notion, or personal files) and receive a local AI assistant that: - Answers questions about document content. - Finds citations, summarizes sections, and compares files. - Works completely offline on their computer (Mac, Windows, or Linux). - No data is transmitted online—maximum privacy. # ✨ Opportunities - 📄 Document upload: **PDF, TXT, Markdown** - 💬 AI-powered chat based on your documents (RAG) - 🕵️♂️ Complete privacy – everything runs on your computer - 🧠 Uses local LLM via **Ollama** (phi3, Mistral, Llama 3, etc.) - 📜 Chat history is saved - 🌐 Simple web interface (or desktop app) # 🔧 Technologies - **Language:** Python (base) + Electron or Tauri (for GUI) - **LLM:** Ollama (phi3, Mistral, Llama 3) - **Embeddings + RAG:** ChromaDB or FAISS - **Frontend:** React +
Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.