Project NANDA
Project NANDA is architecting the foundational infrastructure for the Open Agentic Web. We are solving the core challenge of the next decade: How can billions of AI agents discover each other, verify capabilities, and coordinate tasks without creating bottlenecks or security vulnerabilities.
Launched April 2025, Project NANDA (Networked AI Agents in Decentralized Architecture) originated at MIT and aims to dismantle the four critical choke points within this ecosystem's infrastructure by focusing on consensus-driven innovation: DNS, CA, Orchestration, Attestation. Project NANDA adoption, real-world applications, and education is the pioneering Project at the Foundation for Agentic Networks.
We are pioneering the foundational infrastructure for the Internet of AI Agents - enabling autonomous systems to interact, transact, and collaborate seamlessly.
Since inception, Project NANDA has been open source and community-driven.
Discover More
A website describing NANDA, a project building infrastructure for an “Internet of AI agents” that can discover, communicate, and coordinate across systems
The organization’s GitHub page hosting code, documentation, and repositories related to building infrastructure for the open agentic web.
A web app (sandbox/testbed) associated with NANDA designed for experimenting with the Internet-of-agents ecosystem.
A platform that lets users create a personal AI “agent” with an identity that can interact, socialize, and participate in experiences across an agent-based web.
What is NANDA
Technical Foundations & How It Works
NANDA builds on standards like the Model Context Protocol (MCP) to create a federated system where AI agents can discover, communicate, and collaborate across platforms. Its key components include the NANDA Index, which functions like a DNS for agents, and AgentFacts, cryptographically signed metadata that verify identity and trust. Together, these enable secure coordination among diverse agents, while testbeds like NEST allow developers to experiment and build interoperable tools.
Mission, Phases & Impact
NANDA aims to make AI collaboration open and accessible rather than controlled by a few companies. Its roadmap focuses on three stages: creating a discovery and interoperability layer, enabling an agent-based service economy, and ultimately supporting large-scale “societies of agents” that can solve complex global problems. This vision could transform AI into a cooperative digital infrastructure rather than isolated systems.
Who’s Behind It & How to Get Involved
The project is led by a global community of researchers, developers, and nonprofits working in open standards and AI governance. It operates transparently through open documentation, hackathons, and collaborative pilots. Individuals and organizations can participate by building interoperable agents, contributing to protocols, joining research efforts, or helping shape governance — making NANDA both a technical platform and a collaborative movement.
