Introducing: Starlight — everything we know about building docs,... wrapped up in an easy-to-use template. 🧩 built-in site search, navigation, i18n, a11y, seo, clean typography, code highlighting, dark mode, "edit in GitHub", MDX, Markdoc AND MORE! 🌟show more

Astro
195,684 views • 3 years ago
We built the best codebase search to give any... agent grounded information from GitHub repos. Introducing Sandbox Search. Point it at any repo, and we’ll spin up a secure coding agent in its own sandbox to do research for you. Use inside claude code, openclaw, cursor, and more.show more

Arlan
12,412 views • 4 months ago
you can now use mintlify to automatically build docs... for arbitrary github repos (e.g. n8n here) with an agent powered by a skill reflecting everything we know about quality docs simply swap "github" with "mintlify" in the URL for any reposhow more

Nick Khami
74,522 views • 6 months ago
Introducing exa-code, a big step towards eliminating LLM code... hallucination. We indexed 1B+ docs pages, Github repos, StackOverflow posts, and more. Given a query, exa-code initiates a hybrid search over this data, chunks it, and returns a concatenated, token-efficient string. In our code hallucination eval, exa-code outperforms every popular web search tool (including Exa!). Available for free: How we built it:show more

Exa
206,853 views • 11 months ago
we built an extremely good code search agent. it’s... called tracer, and it can search across the entire github in less than 5 minutes and come back with a clean report. you can try it by running 'bunx nia-wizard'show more

Arlan
91,438 views • 6 months ago
Claude Code Weekly Roundup Last week we added support... for Azure, let you use "&" in the CLI to send tasks to the background, added image upload to Claude Code Web, improved Claude Code's ability to look up its docs and we're continuing to make hooks and subagents more powerful.show more

Thariq
70,840 views • 9 months ago
𝗪𝗲𝗹𝗰𝗼𝗺𝗲 𝘁𝗼 𝗬𝗼𝘂𝘁𝗵 𝗪𝗼𝗿𝗸 𝗪𝗲𝗲𝗸 𝟮𝟬𝟮𝟰! For the next... seven days we are celebrating the value of youth work to young people in a range of communities and with diverse needs, and we invite you to do the same! Use the hashtags #YWW24 #YouthWorkWeek to share your celebrations and #ArtofYouthWork pieces, and we hope to see you at our daily practice sessions on Zoom. Here’s everything you need to know about the week in one easy link:show more

NYA
11,191 views • 1 year ago
Open-Source Multi-Sensor Data Platform for Neural 3D Reconstruction and... Physical AI [📍github] It handles cameras, LiDAR, radar, poses, calibrations & labels in one clean format. No more messy custom parsers. • Super efficient (non-redundant storage) • New .itar single-file format with lightning-fast random access • Streams straight from S3/GCS/Azure – perfect for huge datasets • Built-in converters for Waymo, ScanNet++ & more • Already powers NVIDIA NuRec, 3DGRUT & gsplat Saw this at Janick Martinez Esturo, thanks for sharing! Easy to try: • pip install nvidia-ncore • GitHub: • Docs & project page: NCore slashes data wrangling time, cuts storage waste, and makes large-scale neural 3D training faster and simpler than ever. A real standard for physical AI. ——- Weekly robotics and AI insights. Subscribe free:show more

Ilir Aliu
32,717 views • 4 months ago
Today, two of us who have built billion dollar... companies are launching the ULTIMATE guide for founders on how to start a lean, AI-native startup in 2025. This covers every single tool Founders should use when building their startup from the ground up, from legal, finance, payroll, sales, tech and more. My coauthor Henry has built Super and I have built Glean into both $100M+ businesses and we've invested in 100+ startups between us in the last few years, and this is a constant question we get. And it's completely FREE. The article drops midnight tonight. Bookmark this post. Link below:show more

Deedy
323,554 views • 1 year ago
🌍 As some of you might know, last year... we started building an app that required a 3D Map, and we were taken aback by the lack of good SDKs. They’re all clunky, slow, and unstable.🤔 Today, we're thrilled to introduce Cartes - a fast, easy-to-use, and visually appealing 3D Map SDK for Unity. This tool is built to empower your creativity in developing delightful apps and games for the Real World Metaverse. 📱🤳 ⚡️ With blazing-fast performance, our SDK offers a seamless integration for your (modern) Unity projects. We provide default navigation features, intuitive gestures, and clustering capabilities that we meticulously refined over hundreds of hours and proof-tested in guerilla tests. 🏞️ We wanted to build a genuinely 3D map, with 3D terrain, monuments and decorations, able to transition smoothly from a global view down to the human eye level. 🔍 #Unity #AR #Maps #LBEshow more

Tina Debove ᯅ
15,210 views • 3 years ago
Still using AI tools that can’t turn your ideas... into real apps? Most tools can write bits of code but fail when it’s time to actually build something complete. That’s where Replit ⠕ changes everything. I just asked Replit: “can you redesign this website in professional way.." In minutes, it built the entire website— clean design, full logic, animations, and dark/light mode included. No setup. No debugging. Just pure vibe coding. Here’s why Replit stands out 👇 ✅ Build with plain English – Describe what you want, Replit builds it. ✅ All-in-one platform – Code, AI help, hosting, database, and auth in one place. ✅ Create anywhere – Use the Replit mobile app on iOS or Android. ✅ Instant integrations – Connect to Notion, Slack, Google Drive, Dropbox, and more. ✅ From design to live app – Import from Figma and launch in minutes. No chaos. No micromanaging. Just you, your idea, and Replit doing the hard work. 👉 Try it now: 🎁 Get $10 credit when you purchase Replit Core via my link: #Replit #VibeCoding #AIApps #NoCode #BuildWithReplit #AItools #ReplitCoreshow more

Fakhr
24,152 views • 10 months ago
📐Design Systems and DESIGN.md Consistency using Design Systems and... DESIGN.md: ✨ Every new design automatically starts with a cohesive design system which GREATLY improves consistency (we heard you!) ✨ Edit the system, and all associated screens can be easily updated ✨ You can extract a design system from any URL ✨ Use DESIGN.md to export your design rules or import your design rules from other products (just ask your agent to create you a DESIGN.md file from your code or other context) ✨ You can start a new design by choosing from popular design systems ✨ Read more about DESIGN.md in the docs (link in thread)show more

Stitch by Google
219,245 views • 5 months ago
Today, we're launching the ultimate guide for founders on... how to start a lean, AI-native startup in 2025. This covers every single tool founders should use when building their startup from the ground up, from legal, finance, payroll, sales, tech and more. My coauthor Deedy and I have both built Glean and Super[.]com into both $100M+ ARR businesses and we've invested in 100+ startups between us in the last few years, and this is a constant question we get. And it's completely free👇show more

Henry Shi
10,229 views • 1 year ago
I did the Danube River tour in Budapest the... other night, and I stopped to think while observing; how many civilizations are capable of building so much beauty? None come close to the level of harmony, detail, and exaltation to God as the European one has done in history. But when Africans claim they’ve built everything, I wonder how many buildings like the Hungarian Parliament are there in Africa? Just curious to know? I’m not talking about the pyramids of Egypt, because clearly we all know that those who built the pyramids are not the same Egyptians from 3000 years ago. The doctrine of marrying their cousins following the words of Muhammad completely destroyed their IQ. But seriously now, why do we keep insisting on importing people from countries where they don’t even know how to defecate in a toilet? All this art is incomprehensible to their minds, they will be incapable of recreating anything like it, and their animal instinct will end up destroying it like everything in their countries. Europe has never needed Africans, nor Indians, nor Pakistanis Europe just needs more European babies!!!show more

Joey Mannarino
32,930 views • 5 months ago
🛠️ UTXO Management Tool LIVE on Bitcoin & Fractal... — Your Wallet Just Got Smarter Did you know? There are 38.9 million+ useless inscriptions now on Bitcoin, locking up more than 179 BTC in UTXOs 🤯 At the network fee of 2 sats/vB, merging 500 of these UTXOs could help you reclaim up to 205,042 sats! 😎 UniSat UTXO Management Tool lets you reclaim those BTC trapped in UTXOs easily. 👉 We consolidate for you, so you can do it in one click! ✨More useful features like merge, batch unlock, lock and send, all in an easy interface with clear visuals of the inscription content. 🔧 Try it now: 🔗 We recommend to use it with UniSat wallet for optimal compatibility: 1/6show more

UniSat - wallet, explorer & extension for bitcoin.
57,547 views • 1 year ago
In 2007, I designed tools that let anyone draw... on top of Google Maps. People could drop pins, draw lines and shapes, and layer their own meaning onto the world with "My Maps." But nearly 20 years later, one tiny design debate has stayed with me: how should people draw a shape? At the time, we had two options. 1. Draw mode: users click and drag to create. 2. Drop + edit: the app drops a default shape, then users resize + move it. I pushed hard for draw mode. People were tracing rivers and roads, so precision mattered. A default square dropped in the middle of Kansas wasn’t going to cut it. Decades later, this same debate is still playing out in modern tools: → Figma, Illustrator, Google Slides use draw mode → Canva, Keynote, PowerPoint use drop + edit While there clearly isn't consensus, some newer products are evolving beyond these patterns: → FigJam gracefully merges draw mode and drop + edit into one concept with its semi-transparent “ghost” objects. → Apple Photos on iPhone is a great context for drop + edit. The canvas is small and the mobile user inputs are limited. After decades of using digital drawing tools, I still bristle when a tool drops an unsolicited rectangle onto my screen. At best, it feels presumptuous. At worst, it feels lazy. When we built My Maps, we designed tools that invited users to create. We provided the means, but we let people lead. That same principle applies to every product today: understand who you’re building for and what they need, then design the simplest, most intuitive workflows — ones that let users lead. Because in the end, the best tools don’t assume what users want. They respond. Full breakdown in comments below.show more

Elizabeth Laraki
175,676 views • 10 months ago
What if creating AI was as easy as posting... content? ➜ Theoriq is here to shake up AI. It’s not another walled garden this protocol lets you build, stack, & evolve AI agents that actually talk to each other. Fully composable, fully decentralized. It’s built to grow with tech, powered by the community & open to devs, creators, and anyone who wants in. You can build with no code tools, help govern the protocol or earn by staking on powerful agents. It’s collective intelligence with real ownership Not just AI you use AI you shape. If you’re about building the future, Theoriq’s your arena.show more

evans
87,843 views • 1 year ago
MiniMax H3 is now 50% OFF on Magnific for... 2K video, only until September 1. 🔥 I’ve been trying MiniMax H3 on Magnific, and it feels like a big upgrade for AI video creation. It’s not just about turning text into videos. You can use text, images, videos, and audio together in one prompt, giving you more control over the final video. Here’s what makes it stand out: - Multimodal: Use text, images, video, and audio in one prompt. - Multiple references: Add up to 9 images, 3 videos, and 3 audio files. - 2K video: Create videos up to 15 seconds long. - Built-in sound: Generate voice, music, and sound effects with the video. - Easy editing: Remove objects or transfer motion easily. - More control: Control the camera, characters, and voice. You can use it to turn posters into videos, moodboards into short films, and product images into ads. It also helps bring your ideas to life with realistic movement, lighting, reflections, and sound. The workflow is simple: give it your references → generate → edit → refine. Try MiniMax H3 on Magnific:show more

Markandey Sharma
96,964 views • 17 days ago
The Fondant Custom Normals Blender addon is being tested,... and we're aiming for a 1.0 release next week! The first feature is the Weighted Normals + Laplacian Smoothing Geometry Nodes modifier. This let's you calculate Normals that are as clean as a nice quad mesh even if your topology is a mess and triangulated! We'll be following up with more tools to support creating high quality Normals for 3D anime and vtuber characters. We have an optimized adjustable Face Normal Transfer proxy mesh nearly ready to go. Check out the Docs to see more about the Addon's features and workflow (link in the reply.)show more

aVersionOfReality
54,088 views • 1 year ago
Claude Code + Google Stitch 2.0 is f*cking cracked... 🤯 Google just dropped a free AI design agent that solves Claude Code's biggest weakness: frontend design. One screenshot of a high-converting landing page → a production-ready site for your brand in minutes. All inside Google Stitch + Claude Code. Perfect for DTC brands and agencies who are building advertorial pages and product launch pages for Meta but burning days on designer back-and-forth. If you're running Meta ads and need 5-10 different landing pages testing different hooks, angles, and offers — each one targeting a different audience and pain point — you know the bottleneck isn't the ads. It's the pages. Briefing designers, waiting for revisions, paying $2-5K per page. Stitch eliminates the design bottleneck: → Find a high-converting advertorial that's scaling on Meta → Screenshot it and drop it into Stitch (powered by Gemini 3.1) → Stitch redesigns it with your brand's colors, fonts, and imagery using Nano Banana 2 → Edit sections visually — headlines, CTAs, layouts — without touching code → Export the code and paste it into Claude Code → Claude builds the full production site and deploys to Vercel or Netlify in 60 seconds No designer. No $3K per landing page. No Claude Code frontend that looks like a template from 2019. What you get: → Designer-quality landing pages and advertorials built in minutes, not weeks → Visual editing so you actually see the design before you code it → Nano Banana 2 generating on-brand product imagery and hero shots → A repeatable system — new angle, new page, same pipeline Built 100% with Google Stitch 2.0 + Claude Code. I put together a full playbook showing the exact workflow: how to find winning pages, redesign them in Stitch, and deploy with Claude Code. Want it for free? > Like this post > Comment "STITCH" And I'll send it over (must be following so I can DM)show more

Mike Futia
126,262 views • 5 months ago