The agentic web is an emerging layer of the internet in which autonomous and semi-autonomous software agents discover, compose, and invoke capabilities across organizational and technological boundaries. Enterprises, platforms, and developer communities have each adopted different systems, including AI Catalogs, DNS-based service discovery, enterprise gateways, agent descriptors such as A2A Agent Cards and MCP servers, and a growing set of platform, telecom, and sector-specific registries.

Each system is authoritative within its own domain, but no common layer connects them. This fragments the ecosystem into isolated discovery islands and prevents agents from finding and using capabilities across boundaries.

NandaIndex is an AI Catalog-formatted federation layer that maps a stable resource identifier to the appropriate discovery object, whether an AI Catalog, a DNS-based service-discovery path, a gateway, a platform registry, or a hosted agent card. It functions as a global switchboard: it does not replace existing discovery systems but routes requesters to them.

For enterprises that publish AI Catalog at a well-known endpoint and own the domain, direct resolution already works. NandaIndex is not in the critical path. Small businesses can distribute runtime, agent card, and domain across separate providers and still be resolved from one resource identifier. NandaIndex enables identity-first discovery for individuals, when the underlying account identity is verifiably bound to the resolution record.

Several questions remain open, and we expect future work to address them:

• Refining resolution semantics and identity models.
• Strengthening trust, verification, and policy mechanisms.
• Standardizing the interfaces between the resolution, discovery, and infrastructure layers.
• Supporting richer query routing and multi-hop resolution across federated systems.