Pi Web Agent is a lightweight, extensible framework for building AI chat agents on the web. It leverages Python FastAPI on the backend and a React frontend to deliver interactive conversations powered by OpenAI, Cohere, or local LLMs. Users can upload documents or connect external databases for semantic search via vector stores. A plugin architecture allows custom tools, function calls, and third-party API integrations locally, it offers full source code access, role-based prompt templates, and configurable memory storage to create customized AI assistants.

SparkChat SDK is designed to streamline the creation of AI-powered chat interfaces within existing software ecosystems. It offers a modular architecture with ready-to-use frontend widgets, SDK clients for JavaScript, iOS, and Android, and flexible backend connectors to popular LLM providers. Developers can define conversation flows and intents using JSON schemas or a visual flow editor, apply custom NLU models, and integrate user data stores for personalized responses. Real-time message streaming via WebSocket ensures low-latency interactions, while configurable moderation filters and role-based access control maintain compliance and security. Built-in analytics track user engagement metrics, session durations, and fallback rates, empowering optimization of dialog strategies. The SDK scales horizontally to support millions of concurrent conversations, facilitating deployment in customer support, e-commerce, education technology, and virtual assistant applications.