Nexora-Intelligent Goal Planner & Research Assistant

View at publisher Summarise with VIRAT
Authors: K Dharun Kumar, Mahrooz AM, A Raja Subramanian, P Swarna Gowsalya, Saranya M
Cited by: 0
References: 6

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

In today’s professional environment, knowledge workers invest a great deal of time into the manual planning, research, and writing of documents. Currently, AI tools are created to work as block systems, without separation of roles, which is important for the creation of structured, verifiable content, and generally rely on expensive, proprietary APIs. This represents a real barrier to innovation, especially in costsensitive environments. Because of this, we would like to introduce Nexora, a modular multi-agent AI system for the automation of complex knowledge workflows. Nexora has an architecture that includes specialized agents: a Planner, a Researcher, and a Writer that work together to decompose user goals by using real-time web data and creating polished, cited content in markdown format. The system is powered by an entirely free and open-source stack, combining Flask for API delivery, the phidata framework for agent orchestration, and the Groq API with the LLaMA 3 model for high-speed inference. By demonstrating a clear separation of concerns and utilizing live web data, Nexora offers up a practical and accessible blueprint for creating sophisticated, end-to-end automation solutions that return reliable and immediately usable results.

Fields of Study & Subjects

Artificial Intelligence Applications AI-based Problem Solving and Planning Information Retrieval and Search Behavior

Publication details

Journal / source
IEEE International Students' Conference on Electrical, Electronics and Computer Science (SCEECS)
Pages
1–6
Publication date
31 January 2026
Language
EN