Skip to content
ZHIVEXDocs
Implementation guides

Build your AI layer
with a clear path.

Start with one server-side request. Add streaming, tools, durable sessions, and production controls only when your product needs them.

server / quickstart portable
$bun add @zhivex-ai/sdk @zhivex-ai/openai
create provider model
generate, stream, or run an agent
normalized result + usage + steps
Choose your runtime

Two SDKs. One adoption model.

Keep application logic portable and opt into provider-native features deliberately.

Latest releases

See what changed before you upgrade.

Curated impact, affected packages, migration guidance, and links to the complete source changelogs.

Implementation paths

Go directly to the job at hand.

Each guide starts from the public SDK contract and calls out the boundary your application still owns.

Advanced capabilities

Add the native surface deliberately.

Each page separates stable portable contracts from beta, experimental, and provider-owned behavior.

Production boundary

The SDK runs inside your application policy.

Zhivex normalizes model and agent behavior. Your server remains responsible for identity, tenancy, credentials, tools, durable storage, billing, and retention.

Review the production guide
01ClientUI + input
02Your serverAuth + policy + SDK
03ProvidersModels + native APIs
Durable stateSessions · runs · workflows · artifacts
Source-backed documentation

These guides are distilled from the public contracts, runnable examples, and production notes in both SDK repositories.

Copied