Lyzr's AIMS portal provides enterprises with a robust management tool for their AI agents. Running locally on a company's cloud, the portal offers comprehensive functionalities to track performance metrics, log queries, and monitor errors. This solution ensures data privacy and allows companies to scale their AI operations efficiently while maintaining full control over their data environment. The portal is designed to improve operations and enhance productivity through seamless integration and low-code SDKs.

Chat-With-CUHKSZ provides a streamlined pipeline for building a domain-specific chatbot over the CUHKSZ knowledge base. After cloning the repository, users configure their OpenAI API credentials and specify document sources, such as campus PDFs, website pages, and research papers. The tool uses LlamaIndex to preprocess and index documents, creating an efficient vectorized store. LangChain orchestrates the retrieval and prompts, delivering relevant answers in a conversational interface. The architecture supports adding custom documents, fine-tuning prompt strategies, and deploying via Streamlit or a Python server. It also integrates optional semantic search enhancements, supports logging queries for auditing, and can be extended to other universities with minimal configuration.

DB-conv is a lightweight Python library designed to enable conversational AI over SQL databases. After installation, developers configure it with database connection details and LLM provider credentials. DB-conv handles schema introspection, constructs optimized SQL from user prompts, executes queries, and returns results in tables or charts. It supports multiple database engines, caching, query logging, and custom prompt templates. By abstracting prompt engineering and SQL generation, DB-conv simplifies building chatbots, voice assistants, or web interfaces for self-service data exploration.

MCP Agent Proxy acts as a middleware service between your applications and the OpenAI API. It transparently forwards ChatCompletion and Embedding calls, handles streaming responses to clients, caches results to improve performance and reduce costs, logs request and response metadata for debugging, and allows on-the-fly customization of API parameters. Developers can integrate it into existing agent frameworks to simplify multi-channel processing and maintain a single managed endpoint for all AI interactions.