The Controllable RAG Agent framework provides a modular approach to building Retrieval-Augmented Generation systems. It allows you to configure and chain retrieval components, memory modules, and generation strategies. Developers can plug in different LLMs, vector databases, and policy controllers to adjust how documents are fetched and processed before generation. Built on Python, it includes utilities for indexing, querying, conversation history tracking, and action-based control flows, making it ideal for chatbots, knowledge assistants, and research tools.

Gemini Computer Use transforms how you interact with your operating system by embedding AI-driven decision-making directly into your workflow. By integrating Google Gemini, the agent can understand context-rich English commands to perform various actions: executing terminal commands, creating, editing, or deleting files, monitoring system status, and automating multi-step routines. Users communicate directly through a CLI or API, making it easier to prototype solutions, manage servers, or develop scripts without extensive manual coding. The modular architecture allows developers to extend capabilities, integrate with custom tools, and build domain-specific agents. Whether orchestrating complex deployment processes or simplifying everyday file operations, Gemini Computer Use brings the power of conversational AI to your desktop.