Nestor offers a modular architecture to assemble AI agents that maintain conversation state, invoke external tools, and customize processing pipelines. Key features include session-based memory stores, a registry for tool functions or plugins, flexible prompt templating, and unified LLM client interfaces. Agents can execute sequential tasks, perform decision branching, and integrate with REST APIs or local scripts. Nestor is framework-agnostic, enabling users to work with OpenAI, Azure, or self-hosted LLM providers.

Granite Retrieval Agent provides developers with a flexible platform to build retrieval-augmented generative AI agents that combine semantic search and large language models. Users can ingest documents from diverse sources, create vector embeddings, and configure Azure Cognitive Search indexes or alternative vector stores. When a query arrives, the agent retrieves the most relevant passages, constructs context windows, and calls LLM APIs for precise answers or summaries. It supports memory management, chain-of-thought orchestration, and custom plugins for pre- and post-processing. Deployable with Docker or directly via Python, Granite Retrieval Agent accelerates the creation of knowledge-driven chatbots, enterprise assistants, and Q&A systems with reduced hallucinations and enhanced factual accuracy.