
QueAgent is a real-time blockchain intelligence and Agentic AI system built for the Qubic ecosystem. It continuously ingests live on-chain events and transforms them into actionable insights for traders, founders, and communities. The system tracks token movements, liquidity changes, TVL shifts, whale activity, and risk signals using a lightweight analytics engine with short-term caching—no vector database required. An integrated GPT-4–class agent explains root causes, detects patterns such as wash trading or abnormal inflows, and recommends actions. EasyConnect automates alerts to Telegram/Discord, sends periodic summaries, and supports gamified participation. A real-time dashboard visualizes TVL, liquidity, volume surges, and whale flows, while the chat interface allows users to query events conversationally (“Why did TVL drop?”). Designed for clarity, speed, and impact, QubicAgent becomes Qubic’s first unified, AI-powered monitoring and reasoning layer—offering high practical value and strong hackathon appeal, with future extensions like prediction models and compliance/AML agents.
7 Dec 2025

Our project builds an agentic coordination system that automates lead follow-up and scheduling through an integrated pipeline of modular agents. The system includes two conversational agents (Researcher and SDR) for data enrichment and outreach, plus a central Coordinator agent that ingests inbound replies, uses a watsonx LLM to classify intent, checks calendar availability, and takes action (book meetings, send templated replies, update Airtable records). The Coordinator is resilient and production-ready: it uses Redis for persistent idempotency, the Google Calendar FreeBusy API for real availability checks, and Jinja2-powered reply templates with an LLM fallback for bespoke responses. The backend runs as a FastAPI service containerized for IBM Cloud Code Engine and pulls secrets from secure environment variables; Airtable houses lead state and interaction logs. The design prioritizes accuracy, auditability, and safe operations (signature-verified webhooks, secret rotation). For the hackathon demo we provide end-to-end flows: incoming email → intent classification → booking or follow-up → Airtable update, plus logs/screenshots. This delivers faster, reliable lead conversion and a repeatable foundation for future agentic workflows.
23 Nov 2025

NARMAI is an AI powered emotional companion designed to help people understand their inner world with more clarity and calm. It offers a private space where users can check in through voice or text and receive reflections that feel personal and grounded rather than generic. NARMAI remembers past sessions, emotional themes and patterns, which helps the system deliver continuity and a deeper sense of human connection. The concept is inspired by the principles of the NARM trauma modality, which focuses on agency, pattern awareness and the integration of emotional experiences. This gives NARMAI a structured and thoughtful approach that goes beyond surface level wellness apps or simple chatbots. The long term vision is to create a multilingual, voice enabled companion that supports people across cultures. There is a growing global demand for emotional clarity tools, especially after the rise in mental health challenges and self reflection since the pandemic. Yet no current app offers a memory based, modality informed experience. With the support of developers, designers and researchers, NARMAI aims to become a new category in personal intelligence and emotional support.
19 Nov 2025