Build production-ready AI applications inspired by YC's Fall 2026 Requests for Startups using Moss for sub-10ms semantic search. Focus on applications where fast retrieval significantly improves product performance, responsiveness, or user experience.
By hidevs
The YC Fall 2026 x Moss: The Zero Latency Builder Sprint is a hackathon that challenges participants to create innovative AI applications. The core requirement is to leverage Moss, a technology capable of sub-10ms semantic search without a traditional vector database, to achieve low-latency performance in AI agents. Participants are encouraged to draw inspiration from Y Combinator's Fall 2026 Requests for Startups, focusing on problems where speed and responsiveness are critical. The sprint aims to foster the development of next-generation AI applications by emphasizing the competitive advantage that low latency can provide. Moss, developed by YC F25, allows AI agents to access necessary context rapidly, supporting various environments including browser, edge, on-device, and cloud. This enables the creation of highly responsive AI solutions for a range of use cases. The hackathon is open to individuals who are of legal age of majority in their country of residence, with standard country/territory exceptions. A total of ₹50,000 in cash prizes will be awarded across five placements.
Build a functional AI application inspired by one of YC's Fall 2026 Requests for Startups challenge themes. The project should demonstrate how fast retrieval with Moss improves the application's performance, responsiveness, or user experience, and must meaningfully use Moss in the retrieval layer. Specific themes include: 1. Real-Time Voice & Conversational AI: Build voice agents for various sectors. 2. Multiplayer AI & Collaborative Agents: Create AI-powered workspaces for human-agent collaboration. 3. Local-First AI & The Small Cloud: Develop privacy-first browser copilots, developer utilities, or edge AI applications. 4. Agent Reliability, Security & Evaluation: Build systems for trustworthy AI agents through guardrails, evaluation, and context validation.