TS v1.36.0 · Python v0.29.0

Build AI systems
that stay portable

TypeScript 1.36.0 availablePython 0.29.0 available

A standalone TypeScript SDK for any developer: durable agents, tools, streaming, and an experimental MCP server for Claude Code, Cursor, and other MCP clients. The same contract is the integration layer under Zhivex Harness.

Server-firstBun · Node.js · Python 3.11+
Provider-flexiblePortable core · Native control
quickstart.mts Ready
01import { generateText } from "@zhivex-ai/sdk";
02import { createOpenAI } from "@zhivex-ai/openai";
03
04const model = createOpenAI()("gpt-6-astra");
05
06const result = await generateText({
07  model,
08  prompt: "Ship something remarkable."
09});
10
11console.log(result.text);
TOOLStyped
STATEdurable
ROUTINGportable

Built for a multi-provider world

OpenAIAnthropicAzure OpenAIGeminiVertex AIQwenKimixAIDeepSeekBedrockOpenRouterOllamaMetaZ.AI
Why Zhivex

Your app should outlive
today’s model choice

Provider APIs move fast. Zhivex gives your product a stable application layer while keeping advanced provider features within reach.

Your product
Application logicOne integration surface
Zhivex layer
Portable coreAgents · tools · streams · state
Model ecosystem
OpenAI ↗
Anthropic ↗
Gemini ↗
Qwen ↗
+ native providers
Choose your runtime

Two SDKs. One design language

Use the ecosystem your team already knows. Both SDKs are designed around portable AI foundations and deliberate provider-specific control.

TS
v1.36.0Released

@zhivex-ai/sdk

Built for Bun and modern Node.js

A unified, ESM-first toolkit for generation, agents, durable workflows, artifacts, observability, provider routing, and production controls.

bun add @zhivex-ai/sdk
  • ✓ Stable agents, workflows, artifacts, and CLI
  • ✓ Experimental MCP server for Claude Code and Cursor
  • ✓ Opt-in providers, Docker sandbox, trace viewer, and AG-UI
PY
v0.29.0Beta

zhivex-ai-sdk

Agent-first for Python 3.11+

Build orchestrated AI systems with agents, handoffs, approvals, durable run state, tools, traces, and portable provider foundations.

pip install zhivex-ai-sdk
  • ✓ Async-first agent runtime
  • ✓ Stable local run stores and catalog contracts
  • ✓ Python 3.11 through 3.14
Release updates

The latest releases
Ready to explore

TypeScript 1.36.0 shipped on 2026-10-26 with Core 1.37.0, OpenAI 0.18.0, Gateway 1.8.2, Kimi 0.8.1, and Qwen 0.18.1. npm latest was checked the same day. The other adapter patches only raise the Core floor or update dependencies.

What's new in 1.36

GPT-6.1 Terra, Kimi K3.1 Pro, PixVerse V6, and OpenAI Decisions GA

OpenAI gpt-6.1-terra joins the catalog with a 1,050,000-token combined context window and 128,000 max output tokens. Standard rates are $1 input, $0.05 cached input, and $5 output per million tokens. Prompts above 272K input tokens use 2x input and cache rates and 1.5x output. @zhivex-ai/openai@0.18.0 recognizes it for text and image input. Tool calling requires the Responses API.

kimi-k3.1-pro and kimi-k3.1-pro-highspeed have a 1,048,576-token combined context window, and kimi-k3 stays the Kimi default. Qwen adds PixVerse V6 text-to-video, image-to-video, keyframe, and reference-to-video models. The default Qwen host is unchanged. The default catalog snapshot 2026-10-26 lists 284 models.

decisionModel targets the GA OpenAI Decisions API with JSON, image URLs, message history, prompt-cache options, safety identifiers, and score descriptions. experimentalDecisionModel remains a deprecated alias, and the default decision model stays gpt-6-luna. Core 1.37.0 exports the new Decision* types, and the SDK re-exports them. Optional GA fields are sent only when you set them.

bun add @zhivex-ai/sdk@1.36.0 @zhivex-ai/openai@0.18.0
Read the 1.36 release notes
Published on npm

TypeScript 1.36.0

GPT-6.1 Terra, Kimi K3.1 Pro, and Qwen PixVerse V6 in the catalog, plus the GA OpenAI Decisions API. Default model ids are unchanged.

  • Packages: sdk 1.36.0, core 1.37.0, gateway 1.8.2, react 0.10.0, agents 1.12.0, sandbox-docker 0.2.2, ag-ui 0.2.0, trace-viewer 0.2.0.
  • Providers: anthropic 0.15.0, azure-openai 0.8.0, bedrock 2.1.0, deepseek 0.6.1, gemini 0.14.0, kimi 0.8.1, meta 0.3.1, ollama 0.6.1, openai 0.18.0, openrouter 0.7.1, qwen 0.18.1, vertex 1.3.1, xai 0.4.1, zai 0.3.1.
  • Catalog: 284 models in the 2026-10-26 snapshot, including gpt-6.1-terra, kimi-k3.1-pro, and four PixVerse V6 ids.
  • Decisions: decisionModel for the GA API. experimentalDecisionModel remains a deprecated alias.
Read TypeScript release notes
Published on PyPI · Beta

Python 0.29.0

Version 0.29.0 adds experimental application-owned computer execution. The Python distribution remains Beta.

  • Computer use: experimental OpenAI Responses executor with application-owned authorization and independent verification.
  • Failure handling: interrupted effects stay unknown and are not retried. Missing handlers and denied approvals stop the run.
  • Previous: 0.28.4 tightens guardrails, safety budgets, and stream cleanup. 0.28.3 remains the prior documented snapshot.
Read Python release notes

Also released: React 0.10.0

useObject streams structured output. useApproval sends client decisions to a server gate. The AG-UI adapter stays in @zhivex-ai/ag-ui and is not part of @zhivex-ai/sdk.

React release notes

See versions and updates for all 14 provider adapters. Features vary by provider and API. Catalog entries and release availability do not imply live certification for every model.

Shared foundations

Useful from prototype
to production

Adopt one layer at a time. The shared contract stays small while operational capabilities remain available when your system needs them.

01

Portable contracts

Keep messages, tools, streaming events, usage, and structured output consistent as models change.

02

Agent-ready runtimes

Build tool-using agents with sessions, handoffs, approvals, durable state, replay, and governed control-plane primitives.

03

Production controls

Add safety policies, evaluation gates, bounded artifacts, OpenTelemetry, model catalogs, and provider-aware routing.

04

Native escape hatches

Start portable, then reach provider-specific capabilities without leaking them through your whole app.

05

Multimodal foundations

Use text, tools, structured output, embeddings, audio, files, and realtime features where supported.

06

Server-first by design

Keep credentials, tools, databases, and policy on trusted server runtimes—not inside browser clients.

Quickstart

From install to first response in minutes

Pick your language, copy the command, and follow the focused quickstart for your runtime.

Start with the local verification in the guide to avoid model charges. The code below makes a billable call. Set OPENAI_API_KEY and ZHIVEX_MODEL: API keys and credentials.

quickstart.mts

Install: bun add @zhivex-ai/sdk@1.36.0 @zhivex-ai/openai@0.18.0 (or npm install). Run: bun run quickstart.mts or npx tsx quickstart.mts. See the guide for project setup.

import { generateText } from "@zhivex-ai/sdk";
import { createOpenAI } from "@zhivex-ai/openai";

const openai = createOpenAI();
const result = await generateText({
  model: openai(process.env.ZHIVEX_MODEL!),
  prompt: "What should we build next?"
});

console.log(result.text);
A production path

Adopt only what you need
Add rigor when it matters

01
Start small

Choose the stable surface

Begin with generation or the agent runtime and install only the provider adapters your app needs.

02
Scale safely

Move state to durable stores

Add shared SQL state, approval queues, artifacts, privacy-aware telemetry, and regression gates before real users arrive.

03
Stay flexible

Route without rewriting

Use the shared contract for portable behavior and native namespaces only for deliberate provider features.

Ready when you are

Build the AI layer
your product can grow on

Copied to clipboard