01 · BUILD
Yi CodeLive
Tell it what to change. It edits the code in an isolated sandbox, runs the tests and opens a draft PR for you to review.
Explore Yi Code Read the docsPRODUCTS
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
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.
01 · BUILD
Tell it what to change. It edits the code in an isolated sandbox, runs the tests and opens a draft PR for you to review.
Explore Yi Code Read the docs02 · BEFORE LAUNCH
Runs your agent for real in a sandbox, through normal tasks, tool faults and attacks. A version that fails the release gate does not ship.
Explore Yi Eval Read the docsYi Eval is billed by usage, with a free plan that needs no card. See pricing →
03 · AT RUN TIME
Before an agent calls a tool, runs a command or goes out to the network, Guard checks it against your rules.
Explore Yi Guard Read the docsMODELS · COMPUTE
One API key works for all three. Models are billed per token, sandboxes per second, VMs per hour.
MODELS · COMPUTE
Works with the OpenAI and Anthropic SDKs. Change the base URL and call models. Each sandbox and VM is a separate virtual machine, created and deleted through the API.
Explore Yi Cloud Read the docsHOW WE WORK
You bring the code, models and target chips. We analyze, migrate, optimize and verify, and hand over production-ready code with an evaluation report.
Once the PoC meets its targets, we deploy into your own compute centre.
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