Jakub Chmura
@_jakubchmura
Followers
69
Following
179
Media
3
Statuses
112
Check out our new deep-dive blog series on building AI agents with LangGraph. 🤖 In part #1, we cover environment setup, a GCD workflow, and an LLM chat flow. ✨ Give it a read:
blog.swmansion.com
Part 1 of our LangGraph series: learn environment setup, build a GCD workflow, and create a basic LLM chat flow for AI agents.
1
5
29
We’re kicking off a new tutorial series on building an on-device AI note-taking app in React Native. 🤖 In Part 1, we explain how to add text semantic search to your app using react-native-rag and react-native-executorch. Be sure to give it a read 👇 https://t.co/uxsJp27tOx
blog.swmansion.com
In the first part of our series, you’ll learn how to build an AI note taking app with semantic search using RN ExecuTorch and RN RAG.
2
13
121
We’re open-sourcing React Native Godot this Sunday. After a year of testing, polishing, and making it scalable across all the different Android devices. Over the next few days, we’ll share all the different features we’ve built and best practices on how to use them. We built
103
167
2K
On a plane? In the woods? Offline? 🤔 Check out new Private Mind – your fast, secure & totally free on-device AI app. 🚀 ✅Chat with your PDFs – Upload documents and ask questions, get summaries, or extract insights. All processing happens locally on your device. ✅ Keep your
3
14
77
More and more people are turning to edge AI! In just last week we had >50% increase in npm downloads! This happened soon after we reached 1k github stars 🌟milestone! And we still have more great things to come!
1
4
17
Wspólnie z @Meta i 5 innymi firmami zakładamy React Foundation!⚛️ Tworzymy nową organizację, dzięki której będziemy realnie wpływać na kierunek rozwoju technologii React i React Native i całego ekosystemu wokół nich. Więcej 👉 https://t.co/Ls3gxJbhnU
0
5
54
just got my hands on the new iPhone 17 Pro and the perf is insane 90 tokens/s using quantized Qwen 0.6B with react-native-executorch more performance updates on the way 👀
1
2
13
🔥The future of AI apps is on the device. With react-native-executorch (from @swmansion), you can run models locally in your Expo app: ♢ Private by design ♢ Zero API fees ♢ Works offline ♢ Instant response Read how it works in the blog below from @_darthez_ and
13
25
437
Not only is it faster, but also uses less energy! Faster AND more efficient? YES 🤯! Reaching 91 tokens/sec on iPhone 16 pro for Qwen3 0.6b 🚀 Check out latest version 0.5.8 here https://t.co/14jn43sJjR
1
4
10
Comment on the live if you have any questions about the on-device AI! https://t.co/305Oe3WJfQ
0
3
14
2x faster LLM inference coming to ExecuTorch soon. Went from 25 tok/s to 62 tok/s on the same prompts. Patch for react-native-executorch drops in a few days 👀
0
4
24
Join us for a live stream with @czernekm & @Nklockiewicz this Wednesday at 5:00 PM CEST 🚀 We’ll cover ✅ Pros and cons of on-device AI ✅ Using React Native ExecuTorch in projects ✅ Where to get language models and how to swap them for existing use cases ✅ RAG in React Native
0
6
24
Another week, another issue 😄 This week, along with @piaskowyk we've conducted another issue for This Week in React. As always, we brought you lots of awesome stuff to read. Fans of TanStack and React Router will especially like this one 🤠 Enjoy! 😋
This Week In React 251 - By @tboba_ & @piaskowyk 🍿 Read/subscribe: https://t.co/LgmphWKLwj ⚛️ React - TanStack Start 1.0 RC - React Router RSC - React ESLint plugins - Vite - <ViewTransition> 📱 RN - Nitro Modules / Fetch - Live Activity - localStorage - Workflows TestFlight
0
1
5
We don’t have flying cars in 2025 yet, but we do have on-device Stable Diffusion in React Native! 👀 Coming soon to React Native ExecuTorch 🚀
3
13
144
We’re excited to share that NVIDIA is investing in ElevenLabs, with support from Jensen Huang. Last week’s U.S. state visit to the UK strengthened AI ties. With our roots growing deeper in both places, this partnership and conversation were the perfect way to cap it off.
103
168
2K
.@iwoplaza invites you 🔥to his talk: "TypeScript on the GPU – Bridging the Gap Between Realms." Can’t wait to see you at JSNation US, Nov. 17 & 20!
2
14
91
LLMs are great with language, but not always with facts. They hit cutoffs, miss context, and sometimes just make things up. 🤖 Retrieval-Augmented Generation helps with that by pulling in relevant data. In our new post we broke down how it works, and where it helps (and hurts).
1
7
36
🚨BREAKING: Google Chrome just leveled up with AI. Chrome's new AI can instantly understand and describe anything displayed on your screen. Here're 11 powerful Chrome features you'll wish you knew sooner:
85
258
2K