OneTriangle
The cheapest, fastest lightweight inference.
YC Summer 2026Artificial IntelligenceOpen SourceInfrastructure
About OneTriangle
Inference has surpassed training as AI’s largest compute cost, accelerated by increasing demand for AI and agents. By using proprietary KV cache transfer tech, OneTriangle has cut inference costs by 20% and time by 40% compared to present standards.
Founders
Hannah Chung
Founder
MIT CS & Econ → @Virtu Financial → @World Bank → making AI you can Trust @TrustAI
Medha Venkatapathy
Founder
Hi! I studied physics + cs at mit and we're building a browser agent company. In my free time, I like to bike and get lost.