DREAMWEAVE: Layered Memory Intelligence Framework

DREAMWEAVE is a cognitive memory framework and layered retrieval middleware designed to transform how AI systems store, organize, retrieve, and reason over knowledge. Unlike traditional RAG systems that rely on flat vector similarity search, DREAMWEAVE introduces a multi-layered memory architecture inspired by neuroscience, structural reasoning, and the layered reality model from Inception. The framework operates through multiple cognitive layers. L1 handles high-resolution semantic retrieval using vector embeddings and depth-scored memory. L2 builds associative intelligence through dynamic knowledge graphs and entity relationships. L3 introduces DREAMWEAVE’s core innovation: Pattern Geometry Matching, allowing the system to retrieve information based on structural similarity instead of keywords alone. The architecture also includes the Kick Mechanism, an epistemic consistency system that detects contradictions between surface retrieval and structural reasoning, triggering automatic re-retrieval and self-correction before generation occurs. DREAMWEAVE is fully LLM-agnostic and integrates with GPT, Claude, Llama, Qwen, and other OpenAI-compatible models. The entire system runs on AMD Instinct MI300X infrastructure using ROCm and vLLM with zero external API dependency, enabling complete data sovereignty and high-performance local inference. By combining vector search, knowledge graphs, structural pattern matching, asynchronous orchestration, and contradiction-aware retrieval, DREAMWEAVE represents a new architecture for intelligent memory systems and next-generation AI reasoning infrastructure.

CrowdSense AI

CrowdSense AI is an intelligent real-time crowd monitoring and threat analysis system designed to improve public safety during large-scale events such as concerts, stadium gatherings, festivals, transportation hubs, and emergency situations. Traditional surveillance systems only record footage, but CrowdSense AI transforms passive CCTV monitoring into an active AI-powered command center capable of analyzing crowd behavior, identifying congestion zones, detecting distress signals, and generating actionable emergency responses in real time. The system combines computer vision, AI reasoning, and multi-layer decision analysis to understand crowd density, movement patterns, panic indicators, and potential safety threats. Using a modular pipeline architecture, video feeds are processed through a vision analysis layer, followed by a reasoning engine and critic layer that validate threat levels before generating officer deployment recommendations and emergency commands. CrowdSense AI also features a modern tactical dashboard interface that provides live monitoring, venue topology mapping, AI-generated insights, threat escalation alerts, and operational decision support for security personnel. The platform is designed to support scalable AI infrastructure and future multimodal integrations, making it suitable for smart city safety systems and next-generation crowd intelligence applications.

Agronomist

ArcSplit

ArcSplit is building ownership rails for community-made AI and creative workflows. Today, the best workflows are rarely made by one company alone. They are built from grassroots contributions: community-trained LoRAs, reusable prompts, automations, extensions, datasets, assets, and workflow templates. But while these building blocks create real value, the money usually flows to the biggest platforms instead of the people who made the pieces. ArcSplit changes that. It turns every workflow into a payment graph, so when a workflow is used, the value can flow directly back to the contributors behind it. That means the author of a LoRA, the creator of a workflow, the builder of a tool, or the maker of an asset can all receive their share automatically, peer to peer, without relying on a centralized marketplace or third-party payout gate. The goal is simple: reward the small creators who make the ecosystem better. When contributors are paid every time their work is used, they have a reason to keep improving it, maintaining it, and sharing it with the community. That creates better workflows, better tools, and a healthier open ecosystem built on direct support instead of centralized extraction. ArcSplit is inspired by the creative ecosystems around extensions, plugins, and community assets, but reimagined for the age of AI agents and composable workflows. Community-built should also mean community-owned and community-paid.

Python Agent Marketplace

Gemini Agent Marketplace is an AI-to-AI commerce platform where a coordinator agent decomposes a user request, hires specialist agents (research and writing), and settles each completed subtask with sub-cent USDC payments. The project combines Gemini reasoning and function-calling patterns with Circle wallet settlement flows on Arc, so value transfer is built directly into agent collaboration instead of being an afterthought. The system includes policy controls (payment caps, allowlists, approval thresholds), live wallet balances, transaction feeds, and economics metrics that compare micropayment viability versus mainnet-style transfer costs. It also supports Supabase-backed persistence for transaction history and agent registry data, plus exportable audit artifacts (CSV, PDF, JSON) for judges and operators. For demos, the dashboard streams real-time events over WebSockets, supports failure-mode simulation (low balance, quota fallback), and includes multimodal invoice analysis via Gemini when quota is available. The result is a practical prototype for autonomous, economically sustainable agent workflows where machine-to-machine payments are transparent, controllable, and production-oriented.

M-Pulse - Mumbai Health Command System

M-Pulse is an AI-driven Mumbai Health Command System designed to transform public healthcare management in one of India’s largest and most densely populated cities. It functions as a centralized command center that integrates live hospital data, civic indicators, and environmental signals into a single intelligent dashboard. Health officials can instantly view bed availability, staff deployment, equipment status, and patient flow across Mumbai’s hospital network. Key capabilities include: Outbreak Forecaster — Advanced machine-learning models predict potential disease surges using real-time and historical data. Intelligent Resource Allocator — AI recommends optimal distribution of medicines, beds, ambulances, and personnel during crises. Civic Data Integration — Pulls public health metrics from urban data streams for holistic city-wide monitoring. Advisories & Alerts — Instant, actionable notifications to enable proactive rather than reactive response. Built as a modern web application with an intuitive interface, M-Pulse turns fragmented health data into life-saving decisions. It reduces response times, optimizes scarce resources, and aims to improve health outcomes for millions of Mumbaikars. This project demonstrates how AI can power smart governance in critical public health infrastructure.