Mobile AI Lab. We train specialized models & build tools for agentic mobile development: @apex__ai + @agent_device. Hosting @AgentConf. React Native experts.
Wroclaw, Poland
Based in Poland
- Tweets 4,727
- Following 396
- Followers 17,196
- Likes 3,856
Pinned Tweet
Announcing Apex: agentic coding model for mobile and web, specialized in React.
We built Apex from a single idea: can an open-weight model deliver frontier-level performance at lower cost?
Yes. Apex is SOTA in React Native and Next.js.
Try it now: apex.callstack.com
33
47
235
Checking an invitation panel means recreating the invitation every time.
With Appduct, an AI agent can call a function your team writes to trigger the panel with test data, wait until it’s ready, and inspect the UI.
See how: clstk.com/4smYoCo
1
3
Put @apex__ai on a React issue from your backlog 🔎 It currently ranks #2 in ReactBench’s Fixing React category: finding and fixing problems in existing code while preserving behavior. Try it in your repo: clstk.com/3VJmM4Z
2
10
What evidence would make you comfortable shipping an agent’s changes?
Join us in Amsterdam on Oct 22 for three talks with speakers from Callstack, @expo, @jetbrains, and Chromatic.
Sign up here 👉 luma.com/i8wkxgyg
2
4
The printed report is out in the wild. Want a digital copy now, before you catch us in person? Download it at clstk.com/47MgFj7
React Native at Scale 2026 draws on conversations with 12 organizations and a decade of our React Native work.
3
3
16
Many proposed fixes, one accepted candidate. Carl Ross of @OpenAI joins @lukebfarrell and @lukasz_app to explain how agents explore code improvements and why discarding work is part of the process.
Why put 100 agents on code quality? Carl Ross of @OpenAI explains competing code changes, a grader that picks the best candidate, and agents that keep cleaning up as features ship. Watch the interview ⬇️
1
5
Turn mobile designs into working features with a lower-cost AI model.
@thymikee will explain the verification loops behind a rise from 60% to 98% of PRs merged on the first attempt in the workflow he’ll present.
Oct 22 · Amsterdam · Save your spot: clstk.com/3WynEcJ
1
2
4
Callstack Engineers retweeted
React Native 0.88 is now available!
This release switches to a web-based event dispatching model, adds variable fonts support, SceneDelegate on iOS, and ArrayBuffer support for Android TurboModules. And it's another non-breaking major release.
reactnative.dev/blog/2026/10…
9
70
643
SDK 58 is out 🙌
This SDK is built for iOS 27. Apps on SDK 58 will be ready for Duo on day one 📖.
The release also includes App Intents for Siri, 2x faster clean Android builds, faster Expo modules, and a CLI built for your coding agent.
Changelog: expo.dev/changelog/sdk-58
Upgrade: 𝚗𝚙𝚡 𝚎𝚡𝚙𝚘 𝚒𝚗𝚜𝚝𝚊𝚕𝚕 𝚎𝚡𝚙𝚘@^𝟻𝟾.0.0 --𝚏𝚒𝚡
45
103
927
Callstack Engineers retweeted
react-native-arrangement-view 0.4.0 is out 🧩
→ New <HingeObserver /> API to enable reading hinge state anywhere in your tree
→ New useHingeSelector() for observing a derived value from the hinge state
→ New `isOverlapping` key in useArrangementLayout()
And a new example page showcasing Tent posture ✍️
4
9
52
Agents and frameworks change. Do you rebuild the infrastructure each time? Nishant Gupta of @Meta explains a reusable control plane for agent fleets, plus why verifying outcomes still takes time.
What changes when you move beyond a single agent? Nishant Gupta of @Meta explains shared state, background ops agents, and a control plane for authentication and observability. Watch the interview ⬇️
1
2
Keep control of what ships when agents write your UI.
Craig Walker and @KasperPeulen explore how to steer and verify agent-generated UI with Storybook’s agent-native CLI and WebStorm’s design-to-browser workflows.
Save your spot at clstk.com/4BbFhz5
1
1
4
Callstack Engineers retweeted
We’re at Vercel Ship 26 in SF with @callstackio. Reach out if you’re in town and want to grab a coffee and talk about agentic infra
1
7
Keep app iteration fast as your project grows.
@cedric_dev will demo agents verifying changes in parallel on cloud simulators with Expo and EAS, returning evidence for human review.
📆 Oct 22 · Amsterdam · Save your spot: clstk.com/4zxtfye
1
Who Left the Agents Running? React Native Software Factories nitter.siddz.com/i/broadcasts/1pJkOXgnV…
1
6
Dubai, thanks for joining us at DevDay Exchange Community with our CEO and Codex Ambassador @grabbou and @OpenAIDevs!
We’re planning community demos at the next meetup. Building with Codex or the @OpenAI API? Join our WhatsApp group for updates ➡️ chat.whatsapp.com/DWdJlI0bdD…
3
Agent retries add up 📈 In our React Native evals, @apex__ai scored 87.8% on task requirements; Claude Opus 5.5 scored 88.6%. Apex’s lower estimated model cost leaves more room to iterate. Try it on a task from your repo: clstk.com/4s8cyab
3
Give a React Native component its own window on Meta Quest.
The Meta VR Layout SDK keeps it in the same React tree, with props and context intact. Watch both counters update, then build your own second panel:
More on our blog: clstk.com/4dGqgeA
3
AI makes it tempting to add every feature in sight.
Can the product handle 1,000 users an hour? What will 10,000 cost? @syke explains why scale and quality need to be part of the agent workflow.
Chapters:
00:00 Faster coding, same deployment bottleneck
00:54 Meet Matt Hargett
02:07 QA at McAfee in 1997
07:19 Product economics and estimation
11:49 Mapping the SDLC in the AI era
16:25 Shipping, quality, and operating costs
22:34 Delegating to agents: goals and guardrails
25:21 Coverage-guided fuzzing explained
28:06 Overnight testing and repair loops
30:06 How agents change engineering roles
36:55 Do agents still need Jira tickets?
44:16 Using customer pain to prioritize improvements
49:41 Finding your next delivery bottleneck
54:07 Phased deployments, staging, and telemetry
57:06 Examining how teams really work
01:01:18 Improving the SDLC incrementally
01:03:06 Measuring outcomes and getting outside help
01:06:52 Closing thoughts
1
4