PRODUCTS

The deployment and optimization layer for sovereign AI.

Yi Labs deploys AI products to the compute centre you choose, then optimizes them for the chips there. Data, models and inference never leave your environment.

CODE → EVAL → GUARD

Build, test, guard: three products, one line.

An agent passes three checks on its way to production: is the code right, does it hold up before launch, does it follow the rules once it runs. Each product handles one.

  • Eval tests the pull requests Code opens. They merge once they pass the release gate.
  • What Eval finds can go into Guard and become rules once reviewed.

MODELS · COMPUTE

Yi Cloud runs a model API, sandboxes and VMs.

One API key works for all three. Models are billed per token, sandboxes per second, VMs per hour.

HOW WE WORK

Start with a PoC.

  1. 01

    PoC

    You bring the code, models and target chips. We analyze, migrate, optimize and verify, and hand over production-ready code with an evaluation report.

  2. 02

    Private deployment

    Once the PoC meets its targets, we deploy into your own compute centre.

  3. 03

    Scale

    Add repositories and teams, and more execution hosts and compute as you need them.

Our engineers work on site with you, analyzing how the code runs and adapting it to your compute. You can also start on the cloud service, or run fully offline.

Next step

Want to try it on your own chips?

Book a PoC