OneTriangle
<!-- hacklab:yc-profile -- YC company profile The cheapest, fastest inference cloud Inference has surpassed training as AI’s largest compute cost, accelerated by increasing dema…
About OneTriangle
YC company profile
The cheapest, fastest inference cloud
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.
- YC batch: Summer 2026
- Founded: 2026
- Team size: 4
- Location: San Francisco
- Country: US
- Status: Active
- Industry: B2B
- Stage: Early
- Tags: Open Source, Infrastructure, AI
- YC partner: Ankit Gupta
Founders
Hannah Chung — Founder/CEO
MIT CS & Econ → @Virtu Financial → Fastest, Cheapest Lightweight Inference @OneTriangle
Medha Venkatapathy — Founder/CTO
Hi! I studied physics + cs at mit, and we're building the cheapest/fastest inference with KV cache transferability. In my free time, I like to bike and get lost.
How did your company get started? (i.e., How did the founders meet? How did you come up with the idea? How did you decide to be a founder?)
Hi, we’re Hannah and Medha! Three years ago, we met at MIT, and now are co-founding OneTriangle. Hannah loves scaling companies and Medha loves making ideas become real products. Together, we built OneTriangle to push the limits on latency, cost, and quality.
What is your long-term vision? If you truly succeed, what will be different about the world?
We believe the future of AI will be defined by intelligence and trust. AI agents will reliably carry out human intent while recognizing and refusing actions that are unsafe, unlawful, or harmful. With the rate of advancing ML systems, we will bridge this ever-increasing gap. We provide a compliance standard for all agents to follow, ensuring that humans and agents are perfectly aligned in their intentions.
Source: Y Combinator · Retrieved 2026-11-02. Company information is self-reported on YC.