Tamas Gabor

Building websites, apps, startup products & everything AI. Also a photographer. Budapest.

[Astryx from Meta @Astryxdesign]

🚀 Introducing Astryx from Meta – an open source design system that’s AI fluent and fully customizable without dependencies. 150+ accessible components, brand-level theming, ship-ready templates, and a CLI. Built at Meta over 8 years, now yours. Astryx Design → https://t.co/rBHFBYS76h and GitHub → https://t.co/OyHbxy4Jrl

[Fish Audio @FishAudio]

Our best voice model is now free for developers.
S2.1 Pro- the same TTS on our paid tier, free API, 83 languages, no hard usage cap, same endpoint you already call.
Already integrated? Set model: "s2.1-pro-free" and you're on S2.1 Pro.

[gaut @0xgaut]

Meet June: private AI on your Mac.

We’re handing AI our most precious data: our thoughts, our work, and access to our lives.

We believe it should stay private.

June bundles an agent, voice dictation, meeting notes, and privacy all in one workspace.

Open source. MIT.

[Rabi Shanker Guha @rabi_guha]

Today we're launching OpenUI Cloud

We've spent months arguing AI deserves more than text.
The uncomfortable truth is Generative UI in production needs much more than just rendering.

The boring parts - validation, error correction, fallbacks, versioning, audit trails - eat up 80% of the time and become the critical factor in deciding whether your Generative UI agent reaches production or dies trying.

OpenUI (open source) handles the rendering.
OpenUI Cloud handles that 80% nobody should have to rebuild.

> npx @openuidev/cli@latest create

[Stephen Haney @stephenhaney]

Paper Shaders: now fully open source and FREE

Yes, you can make a: plugin, tool, template, site, app, library. Resell it. Make a Figma plugin. It's already code. Go for it!

We're pushing shaders forward. New Paper Shaders on the way.

[xAI @xai]

Introducing Voice Agent Builder: a no-code platform to create human-like voice agents with Grok Voice.

Available today at $0.05 / min.

https://t.co/kUkF7zqvfR

[Higgsfield AI 🧩 @higgsfield_ai]

We also tested Sonnet 5 against Opus 4.8 on agentic prompting, specifically on dynamic scenes through Seedance 2.0 via Higgsfield MCP.

Here is the result:

[How To Prompt @HowToPrompt__]

Someone open-sourced a tool that converts pdfs to markdown at 122 pages per second.

→ PDFs, DOCX, PPTX, XLSX, EPUB, images
→ Tables, equations, forms, inline math
→ Works on GPU, CPU, or even your Mac
→ Every language

100% Open Source. 36.6k stars on GitHub.

[Matt @codermatt]

🍷 Cellar 0.3.0 is here; our biggest release yet. A faster, friendlier database client. Here’s what’s new since 0.2.0 👇

[Higgsfield AI 🧩 @higgsfield_ai]

Sonnet 5 vs Opus 4.8 on another agentic video pipeline.

Both generated a storyboard with GPT Images 2.0, then fed it into Seedance 2.0, all through Higgsfield MCP on Claude.

Same quality, but each directed Seedance 2.0 completely differently.

[Nuevo.Tokyo™ @nuevo_tokyo]

After 6 years in the works, we are very excited to introduce:

JAPANESE GRADIENTS [ FOR UI ]™
ONLINE TOOLKIT

Gradients are everywhere. In Japan, they've existed for centuries.

Explore, make and export the most beautiful colour combinations and gradients in any format and size

[Vercel Developers @vercel_dev]

You can now run multiple frameworks in one project on Vercel.

Declare each service under the 𝚜𝚎𝚛𝚟𝚒𝚌𝚎𝚜 key in 𝚟𝚎𝚛𝚌𝚎𝚕.𝚓𝚜𝚘𝚗 and route between them explicitly.
https://t.co/rTBzLCxZcV

[Claude @claudeai]

Introducing Claude Science, a new app designed with every stage of research in mind.

Artifacts traced to their code, environments managed on demand, and 60+ optional scientific databases that you can connect.

Available now in beta.

[Higgsfield AI 🧩 @higgsfield_ai]

Seed Audio 1.0 is live!

The best audio model for anything you make.
Change a voice, narrate from text, or dub a video into 18 languages.

Available on Higgsfield and on Claude via Higgsfield MCP.

[OpenClaw🦞 @openclaw]

OpenClaw is now on iOS + Android 🦞

📱 Native mobile apps, finally
💬 Agents in your pocket
🔔 Channels, tasks, replies on the go

Run agents from wherever your thumbs are.

iOS: https://t.co/7LHHc9htgM
Android: https://t.co/X0Wuh2uA8w

[Amjad Masad @amasad]

AI is expensive to run partly because most workloads today run on generic hardware designed pre-LLMs. Etched is the first system designed from the ground up for modern inference.

[Vercel @vercel]

You can now run any Dockerfile on Vercel.

# 𝙳𝚘𝚌𝚔𝚎𝚛𝚏𝚒𝚕𝚎.𝚟𝚎𝚛𝚌𝚎𝚕
𝙵𝚁𝙾𝙼 𝚐𝚘𝚕𝚊𝚗𝚐:𝟷.𝟸𝟺
𝙲𝙾𝙿𝚈 . .
𝚁𝚄𝙽 𝚐𝚘 𝚋𝚞𝚒𝚕𝚍 -𝚘 /𝚜𝚎𝚛𝚟𝚎𝚛 .
𝙲𝙼𝙳 ["/𝚜𝚎𝚛𝚟𝚎𝚛"]

https://t.co/xOUMi4zxpD

[Developers @XDevelopers]

Announcing the hosted X MCP.

Agents now have access to the best real-time information source in the world.

Connect Grok, Cursor, or any MCP-compatible AI tool to the X API without any setup!

Check it out here: https://t.co/5MzPYwGFzD

[Steve (Builder.io) @Steve8708]

How I have Claude automate anything I do on my computer just by showing it:

I use the free Clips app and hit record to start recording.

Then I just do the action - like navigating to Rippling and approving any unapproved time off - and I’ll often just talk out loud as I do it explaining any add’l details like I would when showing a human.

The Clips app captures everything on your screen and everything you say, and transforms it into a format Claude can “see and hear”.

You'll then get a link that you can easily share with Claude (or humans too).

I’ll paste it to Claude and say something like, "automate this for me every day at 8:00 AM."

The link has special metadata that agents like Claude can discover.

It exposes APIs to see the full transcript with timestamps and grab screenshots of what was on your screen at any of those timestamps.

Once it's created the routine, you can go to the Routines tab in Claude Code desktop app.

This also works with the CLI, Claude Cowork, Codex etc.

You’ll see your new routine there, and you can just hit Run Now to have it start running it.

Video attached shows this step by step.

The Clips apps is free and open source - I’ll link to it and the source code in the thread.

[Vercel @vercel]

Voice agents, now on Vercel.

Realtime, speech and transcription are now live on AI Gateway. Build with 𝚞𝚜𝚎𝚁𝚎𝚊𝚕𝚝𝚒𝚖𝚎, 𝚐𝚎𝚗𝚎𝚛𝚊𝚝𝚎𝚂𝚙𝚎𝚎𝚌𝚑 & 𝚝𝚛𝚊𝚗𝚜𝚌𝚛𝚒𝚋𝚎 on AI SDK 7.