We present NARS-GPT, an integrated multi-component system, which combines the power of the Generative Pre-Trained Transformer (GPT) with the reasoning capabilities of Non-Axiomatic Reasoning System (NARS). Such combination enables the system to effectively respond to questions posed in natural language while retaining the capacity to store inferred important information for future use. The GPT element readily converts natural language into formal representations enabling seamless user interaction, while NARS performs real-time reasoning on these representations and grounds them automatically by relating them to observed events. This represents a novel solution to the symbol grounding problem which does not depend on the designer to link a selected set of pre-defined symbols to the perception model, hence allowing for autonomous acquisition of grounded concepts from natural language input at runtime. NARS-GPT is capable of long-term learning through interactive Q and A sessions with users and continuously enhances the system’s knowledge base, thereby ensuring adaptability to evolving scenarios.