How We Optimized Agent Device for Mobile App Automation Discover how we optimized Agent Device to reduce LLM token consumption by over 50% and speed up AI-driven mobile app automation.

Read the article ⬇️
clstk.com/4sTNfbA

Building tools for agents means different trade-offs.

One is context window use: input, reasoning, and output all compete for tokens.

See how we optimize agent-device to cut token usage and reduce errors on complex tasks like app debugging and performance profiling.

Learn how to overcome this 👇

20+ years building for the web.

From Spotify to Vercel to Xata. On stage since 2012.

@tej.as has been shaping how developers think, learn, and build.

Now he’s joining Agent Conf as a Speaker.

Get your ticket 🎟️ clstk.com/4s8OMsU

AI-Assisted Migrations to React Native: From Months to Days | Callstack Reduce migration time from months to days by using AI in real React Native workflows. Learn when to migrate incrementally and when starting fresh is the better option.

Join us for our AI-assisted React Native migration webinar ⬇️ clstk.com/4v80HKg

React Native migration in days, not weeks. We’re going live today 🎙️

🕔 5 PM

Join us ⬇️ Link in the comments

Agents Commander: A Lightweight Interface for Multi-Agent CLI Workflows Manage and connect multiple AI agents in a CLI with a simple communication protocol.

Most agents today talk through JSON and APIs.

This experiment: a simple protocol, messages passed directly between agents in a CLI.

No orchestration layer.

A different way to explore how agents collaborate. Learn more ⬇️
clstk.com/4dSuVL9

Blind bird tickets for Agent Conf are almost gone.

If you’ve been thinking about joining us in Warsaw, this is your moment.

September 17–18, 2026

Get a ticket 👉 clstk.com/4dmQLqa

Brownie: A Type-Safe Shared-State Workflow for Brownfield React Native Brownie brings stable, cross-platform shared state to brownfield React Native apps with typed models for Swift and Kotlin.

Read the full article ⬇️ clstk.com/4dQIjPV

Type-safe shared state for React Native brownfield apps: now across iOS and Android (with Kotlin support).

Less glue code, fewer mismatches. Take a look 👀

Link to the full article below 👇

@kentcdodds.com is a full-time educator focused on helping developers build quality software.

Now he’s joining Agent Conf in Warsaw as a speaker.

Get your ticket ➡️ clstk.com/413omOk

RAG Is Dead. Long Live Context Engineering for LLM Systems When should you skip RAG? Learn how structured context and direct LLM APIs can replace retrieval pipelines in many systems.

RAG trade-offs rarely get discussed:

🔹 Embedding drift
🔹 Complicated architecture
🔹 Re-indexing pipelines
🔹 Retrieval instability

Sometimes, context engineering is the better choice.
Learn more 👇
clstk.com/4sM4rQb

Agent Conf 2026 | Warsaw | Agentic Development Join 500+ engineers in Warsaw Sept 17-18 2026 for Agent Conf. Learn agentic development, orchestration, and AI-driven workflows. Hosted by Callstack.

Get your ticket & join us at Agent Conf ➡️ clstk.com/4bIvOop

From scaling a product to 2M users to co-founding Rork, Levan Kvirkvelia has spent years building products for real users.

And now he’s joining Agent Conf in Warsaw as a speaker.

📅 Sept 17–18, 2026.

Get your ticket 👇

He’s worked across cloud, AI, web, and mobile—and built a career around helping developers understand how things actually work. @dabit3.bsky.social is joining Agent Conf.

📅 Warsaw, Sept 17–18.

Get your ticket ⬇️

AI-Assisted Migrations to React Native: From Months to Days | Callstack Reduce migration time from months to days by using AI in real React Native workflows. Learn when to migrate incrementally and when starting fresh is the better option.

React Native migrations can go from months to days with AI.

Share logic across iOS and Android, reduce duplicated work, and move faster with one codebase. See how we use agents in real migration projects to speed up the process and secure outcomes.

Join us on April 2, 5 PM 👇
clstk.com/4lGhmAt

Agent Conf 2026 | Warsaw | Agentic Development Join 500+ engineers in Warsaw Sept 17-18 2026 for Agent Conf. Learn agentic development, orchestration, and AI-driven workflows. Hosted by Callstack.

Early bird tickets for Agent Conf are nearly gone!

If you’re exploring agentic development—prompting, orchestration, real-world tradeoffs—this is your last chance to join at the early price.

📅 Warsaw, Sept 17–18.

Tickets 👉 clstk.com/4lAbubS

A Practical Guide to LLM Model Naming Conventions Learn how to read LLM naming conventions and choose the right model for your hardware. Discover what Q4, INT8, GPTQ, and GGUF mean and why models appear in multiple variants.

"Which Bielik model should I run?"

The answer depends on:

🔹your hardware
🔹your latency target
🔹your cost constraints

Here’s how quantization levels (FP16, INT8, Q4) map to real deployment environments.

Read the article now ⬇️
clstk.com/3P7FWy9

Build Smarter Apps: Tool Calling & AI Orchestration Explained | Callstack Learn 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.

On-device AI can generate structured outputs, call tools, and interact with APIs.

This unlocks production-ready AI features in React Native that go beyond chat.

See how models decide when to call tools and return typed data your app can trust. Watch now ➡️ clstk.com/4rvd0xd

From Teddy Bears to Voice Agents: Kraen Hansen on Voice AI, Local-First & App Security What happens when you combine voice agents and teddy bears? A hands-on look at local-first systems, voice AI, and security lessons from poking real apps.

Listen to the full episode of React Universe on Air now🎧 clstk.com/40XWqeD

If your data and language model live on the device, why should the app need a network round trip to interact with them?

@psyche.social & @kraenhansen.dk talk about:

🔹 local-first software
🔹 mobile security practices like certificate pinning
🔹 voice AI and real engineering stories

Listen now 🎧

LLM Inference On-Device in React Native: The Practical Aspects | Callstack A practical look at reliability, performance, libraries, and tradeoffs when running LLM inference locally in React Native apps.

Move LLMs from cloud → device

Now you own:
• model capabilities & size
• memory + disk usage
• hardware acceleration support

@artus9033.bsky.social breaks down what running LLMs on-device in React Native really looks like. Watch his talk from React Universe Meetup x Zalando ➡️ clstk.com/4ujkeam

Use React Native to Navigate the Fragmented TV Ecosystem | Callstack Explore the living-room landscape with a comprehensive guide to React Native TV app development. Learn how platforms differ, how to design remote-friendly interfaces, how to manage focus and navigatio...

Download you copy of the guide here 👉 clstk.com/4b2QC8a │

On TV, focus is the UX. If D-pad navigation jumps, traps focus, or behaves differently per platform, the app feels broken. Our TV guide explains how to manage focus in React Native TV using focus guides and platform-specific rules.
Get your copy ⬇️ Link in the comments ⬇️

Full house in Wrocław!

The Callstack x @vercel.com AI SDK Meetup kicks off at 6:00 PM with talks on safe AI execution, real commerce built with Claude, and production-ready agents.

If you’re joining, see you there 👋

Building a Video Experience with React Native: Lessons from Early Adoption | Callstack How Zalando built a custom Fabric video player, reduced jank, and optimized autoplay time in a production React Native app.

Building video in React Native at scale:

🔹Custom Fabric component.
🔹Jank reduced from 24% → 3%.
🔹Autoplay optimizations.

Watch production lessons from React Universe Meetup x @zalando.com by Eugene Verichev now 👇
clstk.com/4rJG1pX

Sparkling: The Missing App Layer for Lynx.js A hands-on look at Sparkling for Lynx.js: CLI, native navigation, and the tooling layer that turns Lynx into a full mobile app framework.

Read the article here ➡️ [https://clstk.com/4sbX0Rs](clstk.com/4sbX0Rs

What does a freshly generated Sparkling app actually give you?

🔸Full Android & iOS projects
🔸Multi-bundle Lynx entries
🔸Native, scheme-driven navigation
🔸Autolinking + typed APIs

We walked through the setup and tested the workflow. Read the article ⬇️ Link in the comments ⬇️

React Native Brownfield v3 with Expo Config Plugin Use React Native Brownfield v3 and Expo to migrate native apps incrementally with artifact-based integration for iOS and Android.

Read the full article ⬇️

clstk.com/3ZXpd2G

Introducing React Native Brownfield v3 with Expo Config Plugin.

There’s never been a better time to migrate your legacy native stack to Expo.

Start in minutest using our battle-tested library ⬇️

Use React Native to Navigate the Fragmented TV Ecosystem | Callstack Explore the living-room landscape with a comprehensive guide to React Native TV app development. Learn how platforms differ, how to design remote-friendly interfaces, how to manage focus and navigatio...

Grab your copy for free 📖 clstk.com/47e94JZ