2. Ask HN: We built a solution for 100B-node P2P. Does anyone care about this?

We have developed an architecture and algorithms that enable search in a peer-to-peer network of over 100 billion nodes in under one second, and under half a second in low-orbit satellite networks. The routing requires less than 80 KB of memory per device, allowing the network to run entirely on consumer devices like smartphones.

We are two researchers. We spent years trying to build a mathematically protected secret voting system. In the process, we were forced to solve many networking problems that typically prevent a pure P2P network from reaching global scale:

— Search: Deterministic, under 1 second, 100B+ nodes, under 80 KB routing memory per device.

— Identity: Anonymous authentication without CAs. One person, many devices, no passwords. — Recovery: Session restoration without passwords or seed phrases.

— Subnets: Fully autonomous, isolated networks of any scale.

— Anonymization: Traffic analysis resistance built into the protocol.

— Integrity: Consensus-based recovery of routing data without trusted nodes

and the like.

We have a detailed architecture. The core solutions are patent-protected (patents pending). We do not have production code. We are keeping the core closed until we find one engineering co-founder to implement it with us.

Our question is not «is this possible?» We already know it is. Our question is: does anyone in the P2P community still care about solving these problems?

We haven't seen much discussion of global-scale sovereign infrastructure lately. Maybe the industry has moved on to other priorities. If you're still interested in this class of problem, we'd like to hear from you. If not, we'd like to understand why.

Overview & Contact: github.com/ikhrabry-spec/a-p2p-network-architecture-for-100b-nodes akhabry@balloting.net / ikhabry@balloting.net

Thank you for pointing to Freenet. We deeply respect Ian Clarke’s work and the foundational routing principles they’ve explored over the decades.

However, there is a fundamental difference in scale. While excellent projects like Freenet operate effectively at the scale of millions of nodes, our solution is architected to provide a 100,000x greater reach, seamlessly handling 100+ billion nodes. This massive leap is precisely why it requires the completely different set of architectural assumptions we outlined in our post.

Regarding patents: We completely understand the P2P community's skepticism toward intellectual property. As researchers, our goal isn't to lock this technology behind corporate paywalls or restrict open-source deployment.

The patent is strictly a defensive measure to secure our authorship and prevent large-scale centralized entities from capturing the core math and monopolizing it. Once a working PoC is built with our engineering co-founder, we are fully open to establishing an open/defensive patent license (like a FRAND or Open Patent Pledge) to ensure the protocol can be used freely for sovereign, public-good P2P infrastructure.