Apex Is Now Generally Available: Agentic Coding Model for Mobile and Web, Specialized in React
Agentic Delivery
/
Custom & Private Models
Use the right AI model, locally or in the cloud.
Tell us where hosted models fall short for your team today. We'll come back with the right approach for your data and workload, and what the rollout path looks like.
- Keep sensitive data off third-party systems
- Get better output from the model
- Choose where the model runs
Use Cases
On-Premise LLM Deployment
LLM Fine-Tuning
Model Evaluation
Backed by Viking Global
·
ISO 27001
·
React Foundation
·
100+ Enterprise Clients
·
Used by 39M+ Developers
·
7B+ active clients users
·
Backed by Viking Global
·
ISO 27001
·
React Foundation
·
100+ Enterprise Clients
·
Used by 39M+ Developers
·
7B+ active clients users
·
Backed by Viking Global
·
ISO 27001
·
React Foundation
·
100+ Enterprise Clients
·
Used by 20M+ Developers
·
7B+ active clients users
·
Backed by Viking Global
·
ISO 27001
·
React Foundation
·
100+ Enterprise Clients
·
Used by 20M+ Developers
·
7B+ active clients users
·
Insights
Learn more about AI
Here's everything we published recently on this topic.
Article9/17/2026Exploring Jev for AI-Driven QA with agent-deviceExplore faster, lower-cost mobile QA with Jev and agent-device. Watch the demo, see the code, and try the CLI proof of concept yourself.
Article7/30/20263 Minutes With an Agent, 9 Seconds on ReplaySee how agent-device replay cuts repeated mobile QA flows from minutes to seconds, reduces model calls, and shows when repair is worth the cost.
Article7/22/2026Building Vault: A Dual-Screen Terminal for Self-Hosted AI AgentsSee how Vault uses an ESP32, OLED, and e-paper display to control an OpenClaw agent and a locally served LLM on a DGX Spark.
Article7/20/2026An AI Agent for Measured React Native Performance FixesSee how Metrognome combines Callstack tools for device control, render analysis, and guidance with repeated measurements to validate React Native fixes.
Article6/26/2026How Expensify Uses Agent-Device for Mobile Bug Evidence and Performance ProfilingExpensify app team uses agent-device to give AI agents hands and eyes on real devices for bug-fix evidence, Sentry span measurement, and React profiling.
Article6/19/2026Building Mobile QA Agents With Vercel EveSee how Eve helps turn a mobile QA agent into a reviewable, durable part of a CI workflow.
Live StreamLive Stream8/27/2026Graph Agentic Coding Extends AI WorkflowsHow connected state, retrieval, memory, and verification carry coding agents across complex, multi-step workflows. Kewin Wereszczyński and Lech Kalinowski discuss the structures that let agents plan, retrieve context, use tools, and keep working across longer tasks.
Live StreamLive Stream8/13/2026What Apex shows about React Native AI modelsSee how Apex, Callstack's React Native model, compares with frontier models on navigation, animations, async state, and performance-heavy UI work.
Live StreamLive Stream7/30/2026How We Built a React Native News Agent With EveSee how we built and deployed an Eve agent that tracks React and React Native repositories, filters commit noise, and publishes daily Slack updates.
Podcast9/7/2026Running AI in the Browser With Transformers.jsNico Martin explains how Transformers.js uses WebGPU and ONNX to run AI in the browser, plus the limits of local models and on-device agents.
Podcast7/7/2026What AI Changes for Paywalls and MonetizationPerttu Lähteenlahti (RevenueCat) talks about AI-generated paywalls, MCP tooling, monetization experiments, and what RevenueCat is building next across mobile and web.
Podcast6/29/2026How Voice Agents Handle Latency, Turn-Taking, and SafetyKræn Hansen (ElevenLabs) talks voice-agent UX, from turn-taking and safety to layered SDK design for React and React Native.
TutorialMarch 19, 2026The Hard Way vs. The React Native AI SDK Way: Stop Writing Custom Modules for Every ModelLearn how React Native AI uses a unified provider model to switch between cloud and on-device LLMs without rewriting application logic, enabling reliable AI experiences online and offline.
TutorialMarch 12, 2026Build Smarter Apps: Tool Calling & AI Orchestration ExplainedLearn how on-device models in React Native can call tools, interact with external APIs, and return structured outputs you can use directly in application logic.
TutorialMarch 5, 2026MLC LLM + React Native: On-Device AI Without the PainLearn how to run third-party on-device LLMs in React Native using MLC LLM. Choose your models, run them efficiently across platforms, and keep a unified JavaScript API with React Native AI.
TutorialFebruary 24, 2026Intelligent Fallbacks with Apple Intelligence in React NativeLearn how to use Apple’s built-in Foundation Models in React Native apps, reduce memory usage, and enable fast, fully on-device AI with React Native AI Apple.
TutorialFebruary 10, 2026What Is the React Native AI SDK? A Complete Intro & QuickstartLearn why on-device AI matters for React Native apps, how local LLMs behave offline, and what problems React Native AI is designed to solve from day one.
TutorialJanuary 29, 2026Implementing an Android TurboModule with KotlinLearn how to implement a React Native TurboModule on Android, from the TypeScript spec and Codegen to the Kotlin implementation and package registration.
TutorialJanuary 19, 2026Working with Different Threads in Swift TurboModulesLearn how JavaScript, native module, background, and main threads interact in React Native TurboModules, and how to use GCD queues to run async work safely in Swift.
TutorialJanuary 9, 2026How to Add Type-Safe Constants to Swift TurboModulesLearn how to expose typed, immutable constants from a Swift TurboModule using Codegen, and get full end-to-end type safety between native and JavaScript.
TutorialDecember 30, 2025Adding Event Emitters to Your TurboModule in SwiftLearn how to emit native events from a Swift TurboModule and subscribe to them in JavaScript, including proper memory management and Codegen integration.
TutorialDecember 22, 2025Writing Your First TurboModule in SwiftLearn how to build a fully working TurboModule in Swift, integrate it with Codegen, and bridge it through Objective‑C inside an Expo app.