Kumbh Labs Research
Practical AI Research
for Mass Gatherings.
We study, develop, and evaluate practical AI architectures, multilingual interfaces, and decentralized multi-agent coordination models for the Kumbh Mela and other high-density environments.
Publications
Publication
Aug 1, 2026
KumbhDoot: A Scale-Ready, LLM-Bounded Architecture for Mass-Gathering Public-Service Assistants
A similarity-first architecture that bounds generative model usage behind semantic caching, approved information and intent routing - reducing cost and latency while keeping answers grounded.
Research
Jul 29, 2026
AI Agents for Kumbh Mela
A proposal for deploying agentic AI systems at the world's largest mass gathering, built around citizen-facing assistants, shared public infrastructure and scalable population intelligence.
Previous Work
Publication
Research Archive
Decentralized AI: A Perspective
A framing of decentralized AI systems and why coordination without central control matters for real-world deployment.
Preprint
arXiv
Agentic Systems at Population Scale
Research on architectures for large populations of interoperating agents operating under real-world constraints.
Project
Project NANDA
AI-LPM: Large Population Models
An overview of large population models - simulating and coordinating the behaviour of millions of agents.
Video Vault
Kumbh Labs - Talk 01
Kumbh Labs - Talk 02
Kumbh Labs - Talk 03
Kumbh Labs - Talk 04