Rigging is a developer-focused framework that streamlines the creation and orchestration of AI agents. It provides tool and function registration, context and memory management, workflow chaining, callback events, and logging. Developers can integrate multiple LLM providers, define custom plugins, and assemble multi-step pipelines. Rigging’s type-safe TypeScript SDK ensures modularity and reusability, accelerating AI agent development for chatbots, data processing, and content generation tasks.

Agentic Kernel offers a decoupled architecture for constructing AI agents by composing reusable components. Developers can define planning pipelines to break down goals, configure short-term and long-term memory stores using embeddings or file-based backends, and register external tools or APIs for action execution. The framework supports dynamic tool selection, agent reflection cycles, and built-in scheduling to manage agent workflows. Its pluggable design accommodates any LLM provider and custom components, enabling use cases such as conversational assistants, automated research agents, and data-processing bots. With transparent logging, state management, and easy integration, Agentic Kernel accelerates development while ensuring maintainability and scalability in AI-driven applications.

VideoSDK AI Agent Demo combines the power of VideoSDK’s real-time video infrastructure with AI services to create an intelligent virtual assistant for group video calls. The demo features live speech-to-text transcription, enabling participants to read captions in multiple languages through on-the-fly translation. After each session, the agent generates concise meeting summaries highlighting key discussion points and action items. Users can pose natural language questions during calls, and the AI chatbot responds contextually using conversation history. Built using React for UI and Node.js for backend integration with OpenAI APIs, this demo provides a modular architecture for developers to extend or adapt features such as sentiment analysis, custom prompts, and multi-language support, accelerating the creation of AI-driven video collaboration tools.