Our open-source RAG app, Verba, can now run Ollama... models locally to embed documents into Weaviate and generate answers without your data leaving your device! I tested it with Llama3, and it works great + super quickly on my M2; In this recording, I'm doing a little Verba-ception, asking Verba what Verba is 🤤 You can also use open-source models like Mistral, Claude, or your own custom LLMs. This will make doing RAG with sensitive data possible since you won't depend on APIs anymore. Looking forward to everyone trying it out 🤗 Update's coming next week!show more

The Dawn of a New Era on $SUI (9)... Still in the festive spirit, let’s look at Tusky , Tusky is a storage service that's not controlled by one company. It uses something called WalrusProtocol to keep your data safe. Your data is encrypted from start to finish, so only you can see it. Instead of one place, your data goes to many different spots. This setup makes your data less likely to be lost or stolen. It helps keep your information safe and always available. Tusky gives you control over your files. You can easily manage them with the tools provided. You decide who gets to see your data. This makes it great for personal storage or working with others. It works with SuiNetwork for even more privacy. You can log in without sharing personal info, keeping everything more secure. This means only you can get to your data, with no third party involved. It is growing fast, with 100,000 uploads already. This indicates its increasing acceptance in the tech community focused on data sovereignty. It's good at managing lots of data safely. In tech, where you want to own your data, TuskyTools is popular. It gives users control over their information. This platform helps keep your data secure and gives you freedom.show more

✨ 3d models are now LIVE on Photo AI... 😊 You can now turn any AI photo you make into a 3d model by pressing [ 📦 Make 3d model ] And then you can view it inside Photo AI or download it as a .GLB 3d model file It's still very early in AI generated 3d model world but it's nice to have this feature working already As always, the models will keep improving, so this feature will keep getting better (like it did with video, it sucked before, now it's getting passable) Next would be nice to switch to .USDZ so you can load it straight into your iPhone with ARKit and put it in your room Available now for everyone on the Premium and Ultra planshow more

Some folks are saying Deep Seek censors certain topics... (like Tiannamen Square) because it's a Chinese app. This is not true. Deep Seek is an open source LLM. You can download it, or host it outside China, and use it however you want. If you use its chat interface that's based in China, it will have to comply with the Chinese regulations. But outside China, you can do pretty much anything. For our app Research Kick, we are hosting it in the US. You can see, it answers my question about Tiannamen Square.show more

Despite being told no, I'm open-sourcing Chatpack. You can... now deploy production-ready chat to any app with 30+ native chat features in a single command using npx chatpack@latest I wanted to build a simple chat layer where anyone could add 24/7 live messaging to their app without spending weeks rebuilding the same infrastructure from scratch. Connect your existing auth and database, and Chatpack handles everything underneath. So today, we're open-sourcing Chatpack. > 24/7 real-time messaging between your users > typing, presence, read receipts, permissions, and conversation history > works with your existing auth + database, so your users and data stay yours Run it as a CLI or library. Fully open source. Repo is MIT licensed. If I were starting an AI company today, I'd clone this, pick a market, and begin shipping with Claude Code. Truly excited to see what comes out of this.show more

Announcing Stack Auth Payments! 💸💸 This is the fastest... way to integrate payments into your app, with just a few lines of code. All payment information will be right where it belongs — next to your user data. Sick of split brains? Just create the price plans you want, and we will deal with the billing & webhooks. Usage-based billing is also supported! Lots of love to our open-source contributors, who helped make this happen — especially Moritz, who was invaluable in this project!show more

🤯 THIS FEELS ILLEGAL AND I LOVE IT. I... found a personal AI assistant that actually runs on your computer 24/7 and gets smarter the more you use it. It is called Mercury. 100% FREE. Think of it like having a smart assistant who never forgets anything. Here is what it does: ↳ Remembers everything about you ↳ Asks before doing anything risky It will not run commands or touch your files without permission. You stay in control always. ↳ You can message it from anywhere ↳ Has 31 tools built in ↳ Protects your AI credits One command to install: npx @cosmicstack/mercury-agent 100% OpenSource. Works on Mac, Windows, and Linux.show more

"It's on my todo to build my own stack... of apple minis and run Llama on my own little cluster on my desk." - Garry Tan Quick AI homelab tutorial: - Install EXO Labs on each mini (open source, steps in README) - Make sure all the minis are on the same WiFi network or for faster/more reliable results, connected over Thunderbolt/Ethernet. Devices will auto-discover each other and auto-shard the LLMs. - Now you can chat to your cluster with your preferred LLM GUI (the tiny corp tinychat ships with exo)show more

Fine-tune DeepSeek-OCR on your own language! (100% local) DeepSeek-OCR... is a 3B-parameter vision model that achieves 97% precision while using 10× fewer vision tokens than text-based LLMs. It handles tables, papers, and handwriting without killing your GPU or budget. Why it matters: Most vision models treat documents as massive sequences of tokens, making long-context processing expensive and slow. DeepSeek-OCR uses context optical compression to convert 2D layouts into vision tokens, enabling efficient processing of complex documents. The best part? You can easily fine-tune it for your specific use case on a single GPU. I used Unsloth to run this experiment on Persian text and saw an 88.26% improvement in character error rate. ↳ Base model: 149% character error rate (CER) ↳ Fine-tuned model: 60% CER (57% more accurate) ↳ Training time: 60 steps on a single GPU Persian was just the test case. You can swap in your own dataset for any language, document type, or specific domain you're working with. I've shared the complete guide in the next tweet - all the code, notebooks, and environment setup ready to run with a single click. Everything is 100% open-source!show more

AI’s next frontier is Spatial Intelligence, a technology that... will turn seeing into reasoning, perception into action, and imagination into creation. But what is it? Why does it matter? How do we build it? And how can we use it? Today, I want to share with you my thoughts on building and using world models to unlock spatial intelligence in this essay below. 1/nshow more

Sharing my new skill! It keeps track of high-signal... X accounts for top AI news, papers, projects, etc. Total gamechanger for me. Built with X MCP tools. Give your agent the skill and tell it to generate the artifact with top stories. Works for Codex, Claude, Hermes, OpenClaw, or whatever you use. 3 steps: 1. Set up X MCP - X API: 2. Install skill here: 3. Run prompt: "Use the x-agent-intelligence skill to build a self-contained local feed from my X MCP connection; ask for my source handles if needed, save feed.html, and validate it." It should generate a nice, beautiful HTML artifact like the one shown in the clip. You can tune it however you want. You can then set a schedule/automation to do this daily or whatever cadence you prefer. I have it every 4 hours. You will need to curate the X accounts yourself, but I have shared a few good ones under the assets. You can ask your agent to tune it to however you like. I have also shared my personal feed with our community here: I understand if it gets tricky to set up. Please reach out to me in the community forum. I plan to do a little tutorial or live session soon to help others reproduce the process. You can also store the feed as a wiki, as I have in my own implementation, but that's optional. If you encounter any issues or have ideas on how to improve it, please open a PR.show more

OpenClaw, but built for normal people. Sim is an... open-source platform that lets you build AI agent workflows on a drag-and-drop canvas. Connect them to channels like Telegram and WhatsApp and deploy without writing a single line of code. They also have a built-in Copilot that generates entire workflows from plain English, which you can then tweak and customize in the UI. Key features: - Free and open-source (Apache 2.0) - Vector store integration for RAG-grounded agents - Self-host with one command (`npx simstudio`) - Run fully local with Ollama, no API keys needed - Supports vLLM for production-grade self-hosted inference The thing I really like about Sim is the level of control you get. You can add conditional branching, parallel execution, human-in-the-loop approval gates, and even nest workflows inside other workflows. Everything is visible on the canvas, so you know exactly what your agent is doing at every step. And you can build a workflow in Sim, deploy it as an MCP server, and plug it into any agent, including OpenClaw. I've shared the link to Sim's GitHub repo in the next tweet.show more

👉 I created « Next Scene » for Qwen... Image Edit 2509 and you can make next scenes keeping character, lighting, environment . And it’s totally open-source ( no restrictions !! ) Just use the prompt « Next scene: » and explain what you want. I trained it on hundreds of paired shots to preserve characters, lighting, and mood between scenes. ( Soon I will explain what tools I created that can manage classification and caption of data when you have more than 10 000 of items, using workers and a total new way to classify data ) . Built for storytellers working with ComfyUI or other diffusers pipe ;) ! ComfyUIshow more

Right now, you may not have access to models... like GPT‑5.6 Sol, GPT‑4.6 Terra, GPT‑5.6 Luna, Claude Mythos 5, or Claude Fable 5. But you can run something surprisingly powerful today, locally, and completely free. in the next 10 mins on your 8 GB VRAM gaming laptop. Gemma 4 26B A4B QAT (MoE) delivers strong performance on a standard 8 GB VRAM GPU using Ollama, with no API, no usage limits, and no external dependencies. Out of the box, it reaches around 20 tokens per second without any optimizations. Only one command in your terminal: Ollama run gemma4:26b This means: Full offline capability (privacy by default) Zero recurring cost Competitive performance for many real world tasks Fast enough for interactive use on cheap consumer hardware If you're waiting for cutting edge cloud models, you're missing what is already practical today: a capable, local LLM that runs entirely on your own machine.show more

Today we’re open-sourcing Stable Audio Open Small, a 341M-parameter... text-to-audio model optimized to run entirely on Arm CPUs. This means 99% of smartphones can now generate music-production samples in seconds, right on-device with no internet required. Built for fast, on-the-go creation, it turns your next quick idea into up to 11 seconds of audio. Generate drum loops, foley, riffs, and textures right where you are. No cords 🔌 just chords 🎹 You can learn more here:show more

Fable 5 is INSANE for creating ads i built... an agent that studies your competition and thousands of viral ads, then gives you a full viral blueprint for your brand to copy just feed it a product photo and a landing page link and competitors names, 3 minutes later you've got a proven creative playbook for your ads, here's how it works: - scans your brand's own website (copy, offers, structure, CTAs) - scans competitor websites (you list them, or Claude finds likely ones for you) - pulls live ad data straight from Meta Ad Library + TikTok via spytools - extracts proven hooks, scripts, and visual/creative patterns from every source - synthesizes everything into one swipe-file library - output is a ready-to-paste doc, drop it into Claude and generate new ad scripts from proven angles instantly - runs locally, one command, your own API keys, no video generation step slowing you down runs 100% local, without $300/mo on spytool subscriptions or agency fees, full control, and API cost only RT + reply w/ "AGENT" and i'll send it to you so you can use it for your brand (must follow so i can DM)show more

1. Start by training ChatGPT as an academic writing... assistant. You can do this with Custom Instructions. Open ChatGPT, click on your profile photo, and select Custom Instructions. Paste the following Custom Instructions in ChatGPT: What would you like ChatGPT to know about you to provide better responses? Introduction: I am an [experienced academic /scientist] with a PhD in [your field]. I work as a [your current academic status] at the [name of your university]. Research Interests: My current research project looks at [details about your project]. I also teach undergraduate and graduate courses on [details about the courses you teach]. In the past, I have published work on [a few details about your published work]. You: You are going to act as my research assistant. You will help me with brainstorming research questions, simplifying complex topics, mock peer review, and polishing academic prose. You will help me with critiquing drafts of the papers I am working on. You will also engage with me in a Socratic dialog and challenge my opinions so that I am aware of any blind spots I may have. Based on our conversations, you will suggest new and exciting directions that I can develop my work in. How would you like ChatGPT to respond? You will respond like an academic colleague. Any claims, opinions, or figures that you cite in your responses must be cited with reference to an authentic and published source. You will never make up any sources of your own. If you are unsure about a source, you will say that you don’t know. You will never say you are an AI model since I already know that. Repeating it is a waste of both time and resources. Your responses should be clear and precise, and you will never use more words than are necessary. You will always be very economical with words, but you will not compromise on clarity and precision of your answers. You will follow my instructions strictly. If I ask you to limit your answer to two sentences, your answer must be two sentences only.show more

you paying attention? > Claude work tools (Figma, Canva,... Amplitude, and more) are now avail on mobile. > explore designs, create slides, check dashboards… all from your phone > combined with Dispatch this means you can assign tasks from your phone, use your connected tools remotely, and come back to finished work on your desktop. Anthropic is turning Claude into an operating system you carry in your pocket if you’re not paying attention to what they’re shipping week over week, you’re already falling behind without realizing itshow more

The Amiko app is live on the Solana dApp... store, and it’s our biggest release yet. Your Amiko twin doesn’t live at your desk anymore. Give your agent a task on the train. Run a compatibility profile when you meet someone. Do research, write code, build in the creative studio, whatever you need, from wherever you are. No laptop required. No waiting until you get home. Solanamobile users get two things Android and iOS won’t have at launch: Amiko token and crypto integration and on-device AI inference. Your twin runs locally on your phone if you want it to. Your behavioural profile, your data, your work, your twin. All on your hardware. AMIKO runs on OpenHermit, our own open-source agent runtime that we built in-house and released to the community. Most agent systems are designed for one agent talking to one person. OpenHermit is built for something different: agents talking to each other, coordinating across tasks, and collaborating with multiple humans simultaneously. That’s what makes features like compatibility profiling and multi-agent workflows actually work. We built it because nothing that existed was designed for this. Android and iOS are coming. Crypto integration and on-device AI are Solana Mobile exclusives. Most AI answers your questions. Amiko is an extension of you. Download →show more

NanoBanana 2 just made your static ad agency obsolete.... And I just open sourced the entire tool. Drop your product page URL. It pulls your logos, product images, fonts, colors, and brand voice automatically. Builds a full brand guide for you. Then generates ad creatives at scale using nearly 4,000 high-performing ad templates across 8 niches. It dynamically matches the best templates to your brand and brief. Here's what makes it different: → Instant resizing Get any ad in 1x1, 4x5, 9x16 with one click. No regeneration. No broken text. → Highlight-to-edit See an issue? Highlight the area and tell it what to fix. → Multiple brand profiles Run different brands or segments from one tool. → Auto persona building from real customer reviews → Multiple QC loops on briefs and final assets Catches AI-isms before you do. → Upload your own templates or use ours Runs locally. Just needs your Claude and Google API keys. This is the lite version of what we use internally. You get the full finished tool AND the open source code to make it your own. Creatives still design the system, this handles iteration and scale. Want a copy to download? 1. Like this post 2. Comment "AI" Will DM you the tool along with a tutorial shortly after.show more

Introducing my new OSS framework: OhSnap provides really simple... way to record and reproduce the data your users saw when encountering an issue (bug/crash), integration in your project should take a few minutes at most. Majority of bugs are related to data you have to deal with and often times we have to work with frequently changing data via network API's. Even if you have access to multiple environments (prod/staging/dev) it's still going to be PITA to reproduce a lot of bugs your user saw, since we often get to them a long time after the bug occured... OhSnap allows you to easily record any data your app downloads, pack it and put it on server so that you can replay it on your device later on, while connected to debugger and save hours of development time trying to figure out what exactly they experienced! Here's a demo of 2 app instances running, and me manipulating what server reply I'll be getting, there is 1 line of code needed to record and reply this data (outside of just setting up your framework). I built this so that I can show dev tool building process for the members of which I encourage you to join if you want to put your engineering efficiency at a different level😉show more