Tool UI is a React framework for conversation-native UIs.... Tools return JSON, and Tool UI renders it as inline, narrated, referenceable surfaces inside messages, optimized for chat width and scroll. It’s schema-first: every surface is driven by a serializable schema with stable IDs, so results stay consistent and reusable. It’s assistant-anchored and stack-agnostic, working with any LLM/provider and orchestration layer. If you’re building agents, it’s a clean bridge from tool outputs to real product UX.show more

The AI party just got a major upgrade. 🦞✨... Today, we’re launching AgentHub by PIN AI — the interaction layer where agents finally talk to each other. Let’s be real: ❌ Siloed agents = Garbage out. ✅ Connected agents = Compounding output. We’re not just building a tool; we’re building the Open Agent Network. It’s time to stop the isolation and start the collaboration. Repost if you’re ready for the era of Personal Intelligence Network! 🚀show more

just vibe-coded an internal search tool that finds any... file on my computer and answers questions related to them. it's a custom Raycast extension powered by Anthropic's MCP (thanks Alex Albert & Marc Klingen for showing me!)—but it works with any LLM for Q&A across my local files. given Raycast’s slick UX + deep integrations, I’ve always thought it’s perfectly positioned to solve internal search like Glean does with enterprises, so I built one. code is in the comments—curious to hear your thoughtsshow more

Turn complex docs into clean, LLM-ready data! Every AI... company I've talked to is solving the same problem: how do you build systems that don't hallucinate and back up every answer with proper citations? Tensorlake is a tool that extracts custom-defined structured data from any unstructured document in 3 steps: ↳ Define your schema ↳ Enable citations ↳ Extract You get RAG-ready data with precise citations and bounding boxes. Feed this to your LLM, and you'll generate responses that are citation-backed and fully auditable. This is the difference between a demo and a production system. When your AI can show exactly where it got its information, you move from proof-of-concept to something people can actually trust and deploy. I've shared the Tensorlake GitHub repo in the replies!show more

🛑 A powerful OSINT tool for exploring global sanctions... data If you ever need to check sanctions across different authorities, this tool brings everything together in one place and it’s FREE to use. It’s called Sanctions Explorer, and it provides: ✅ Current + historical sanctions data 📚 ✅ Coverage from major bodies like the UN, EU, OFAC, and more ✅ Clean filtering to track individuals, companies, and entities ✅ A unified view instead of searching each authority separately 🌍 The project was initiated by Archer (a Berkeley-based nonprofit focused on human rights) and later fully developed by the C4ADS Data & Technology team known for their evidence-based research on global conflict and transnational security. If sanctions research is part of your OSINT workflow, this tool is worth bookmarking. And in the next post, I’ll share a quick OSINT tip for checking phone numbers on Telegram Check it out here: __________ P.S. ♻️ Repost if you found this helpful. If you liked this post and would like to learn more methods and techniques to discover information about people, check out my OSINT Mastery courseshow more

LangGraph. CrewAI. Agno. Which one to pick? The good... news is that this will not matter soon! Finally, we have a full picture of how the industry is solving this with just three open protocols that work across ALL frameworks. It's not about picking the best framework. Instead, it's about understanding how protocols create interoperability. The Agent Protocol Landscape shows how three complementary protocols are creating a universal language for Agents: > AG-UI (Agent-User Interaction): - The bi-directional connection between agentic backends and frontends. - This is how agents become truly interactive inside your apps, not just as chatbots, but collaborative co-workers. > MCP (Model Context Protocol): - The standard for how agents connect to tools, data, and workflows. > A2A (Agent-to-Agent): - The protocol for multi-agent coordination. - How agents delegate tasks and share intent across systems. These aren't competing standards. They're layers of the same stack and have handshakes with each other. So instead of building point-to-point integrations, you build to protocols. Moreover, you can integrate LangGraph, CrewAI, or Agno into the same frontend, without rewriting your UI logic. These protocols let everything work together. For instance: - Your LangGraph agent pulls data via MCP. - It delegates analysis to a CrewAI agent via A2A. - Results stream to your React app via AG-UI. - Users see real-time collaboration in your interface. This way, you can focus on building agent capabilities instead of integration mechanics. The protocols handle interoperability automatically. CopilotKit unifies this entire stack into one framework so you can build "Cursor for X" style apps without implementing each protocol from scratch. It gives you all three protocols, generative UI support, and production-ready infrastructure in one framework. I have shared this playbook in the replies! It breaks down handshakes, misconceptions, and real examples and shows exactly how to start building.show more

Bone Tide is officially out on the App Store... and Google Play 🎉 The React Native Expo version runs on the exact same TypeGPU engine as the Web game, shared 1:1 between both platforms. Only the UI was ported to React This was made possible by some amazing work across the React Native open source ecosystem. Huge thanks to William Candillon for react-native-webgpu and for always helping me resolve any issues incredibly quickly :D I think it’s a pretty cool showcase of what can be built with React Native nowadays. More details about the libraries used in the 🧵 featuring what might be the ultimate Software Mansion stack iOS: Android: Web:show more

Introducing fx, a tiny, open, native coding agent from... Vercel Labs. Originally an internal tool, fx is a harness and CLI written in Zig, optimized for research and embedding in larger systems. Today, we're open sourcing it. fx is built on three principles: 1. Fast. A single native binary, no runtime to install. It cold starts in 10µs and does no unnecessary work or I/O before accepting input. fx is the answer to "how fast can a coding agent be?" 2. Light. The 6.3MiB binary uses single-digit megabytes of memory at baseline, made for instant installation and embedding in resource-constrained environments and agent sandboxes. 3. Open. Apache-2.0, model and provider agnostic, suitable for local and cloud inference. Its small core extends through skills, plugins, and MCP. Minimalism is an obsession throughout the entire harness: system prompt, tools, features, binary. The goal was to keep context usage and time to first token low, and make fx optimal for model benchmarking, sandboxing, evals, and gyms. You can use fx directly or embed it as infrastructure. The CLI feels more like a Unix shell than an IDE in the terminal: it preserves scroll history, produces minimal output, and uses complex TUI rendering very, very sparingly. Programmatically, 𝚏𝚡 𝚊𝚜𝚔 --𝚓𝚜𝚘𝚗 gives structured output, 𝚏𝚡 𝚊𝚌𝚙 connects to editors and other clients, and WebAssembly can even run the whole thing inside the browser (see: Privacy is a design constraint: no product telemetry, sessions and usage stay local, and no source code or prompts are shared with any endpoint other than inference. With local inference and auto-updates off, fx is fully hermetic. fx is experimental. Use at your own risk and expect frequent changes. Chat with us on X ( or file issues ( 𝚌𝚞𝚛𝚕 -𝚏𝚜𝚂𝙻 𝚏𝚡.𝚜𝚑/𝚜𝚎𝚝𝚞𝚙.𝚜𝚑 | 𝚋𝚊𝚜𝚑show more

FIVE LAYERS OF AGENT ENGINEERING, EACH ONE WRAPS THE... ONE BELOW IT. IF YOU SKIP LAYER 2, YOUR LAYER 5 WILL LOOK BROKEN WHEN IT IS ACTUALLY JUST STANDING ON NOTHING. for weeks i debated harness vs loop vs graph like they were competing choices. then a stack diagram made the shape obvious. they are not choices. they are floors. 01 | prompt engineering. the message. unit of work: one input. inputs are role, instructions, examples, format. output is a single raw response. 02 | context engineering. the memory. unit of work: what stays in the window. a curator selects, compresses, and drops from query, docs, memory, prior turns, and tool outputs before the prompt runs. 03 | harness engineering. the machine. unit of work: the machine itself. gather (context + prompt) → LLM → tools or sub-agents → verifier → final response. the article calls this the operating environment. 04 | loop engineering. the system. unit of work: the run. goal + success criteria + max iterations + budget + completion check wrap around one harness pass. failed pass appends results to context and retries. 05 | graph engineering. the topology. unit of work: the graph run. goal + nodes + edges + state schema. graph routes to agent nodes, tool nodes, or human approval. a reviewer node with a different model and fresh context checks the final answer. the wrapping is the whole point. layer 5 assumes layer 4 works. layer 4 assumes layer 3 works. skip layer 2 and layer 3's verifier keeps failing without a clear reason. this is why swapping the model is a one-day project and swapping the stack is a quarter. the model is the commodity. the five layers around it are the engineering. full three-layer breakdown of the top of the stack (harness, loop, graph) in the post below.show more

Kling AI 3.0 is here And it’s a serious... step forward for AI video. This update isn’t about small tweaks. It’s about refinement, realism, and making AI video feel ready for real-world use. What stands out with Kling 3.0? Stronger visual quality. Movements feel smoother. Lighting looks more natural. Scenes feel intentional instead of generated. Better prompt understanding. You can describe complex scenes, moods, or camera directions, and Kling 3.0 interprets them with much more accuracy. Less trial and error. More usable results. Improved motion and consistency. Characters stay consistent. Objects behave logically. Shots flow more naturally from start to finish. Greater creative control. From product-style visuals to cinematic storytelling, Kling 3.0 gives creators the flexibility to move beyond simple clips and into structured, high-quality sequences. The difference is subtle until you see it, and then it’s obvious. AI video is evolving quickly, and Kling AI 3.0 shows how far the technology has come. It’s not just about generating video anymore. It’s about generating video that’s usable, polished, and ready for campaigns, storytelling, and branded content. If you’re building with AI, this is one of the tools worth paying attention to, best AI video model for pro & commercial productionshow more

this is f*cking beyond comprehension. Google engineers just shipped... the entire agent lifecycle in one release: build, scale, govern. and every piece answers a specific way agents die in production > context layers (Static, Turn, User, Cache): you decide what the model carries between turns, so token spend stops being a mystery > a self heal plugin: the agent notices a tool call failed and retries it a different way instead of dying mid run > adk deploy: one command from your laptop to the managed runtime, no packaging, no infra ticket > Go joins Python and Java, with its own A2A SDK then the part nobody builds for themselves: > a dashboard on token consumption, latency, error rates and tool calls: the four things that actually kill an agent > a traces tab that opens the real sequence of actions the agent took, step by step > a playground wired to the deployed agent, past sessions included, so debugging is not a redeploy loop > an Evaluation Layer with a User Simulator, because you cannot unit test a non deterministic system and the part that decides whether it ever ships: > agents get native identities as first class IAM principals: least privilege applies to them like it does to people > Model Armor screens prompt injection, tool calls and responses, inline for Gemini or over REST > Security Command Center inventories every agentic asset and flags data exfiltration by an agent ADK is already at 7 million downloads. the runtime has a free tier, and express mode runs off a Gmail address. the prototype was never the hard part.show more

I found an AI tool that turns a product... image into a viral ugc ad Just upload a single product photo → type a description → Hit generate. What came out looked like a $1000 studio shoot. The feature is called "Product Showcase" and it’s available in Arcads. Here's the exact workflow DTC founders are using: → Go to and open composer → Click "See more" → Select "Product Showcase" → Pick any conversion-optimized template → Upload your product image → Add a short description and hit generate These templates are already optimized for 9:16 TikTok and Meta ads. Ready to publish the second they render. While competitors wait 2 weeks for influencer content and $500/clip, smart advertisers are testing 10 variations before lunch for pennies. Same quality. 1% of the cost. Zero delays. I am giving away a step-by-step guide to build an n8n automation that can create unlimited viral ads with Arcads. To get access, like + comment “arcads” and I’ll send it to you.show more

Just look at this Axe which the Co-Pilot used... to attack the Captain in the Fly Dubai incident. It’s a heavy-duty emergency axe with a sharp cutting edge, built to break through tough aircraft materials when normal access is blocked. It looks and is like a serious piece of equipment. In the wrong hands, a tool with this kind of weight and cutting edge could cause devastating injuries. And for your information, this tool is a must to have inside an aircraft. Aviation regulations require aircraft with more than 19 passenger seats to carry emergency equipment such as a crash axe. An emergency tool designed to help save lives suddenly became part of an attack inside Fly Dubai cockpit! The UAE Attorney-General confirmed that the co-pilot attacked Captain Smit Machchhar with the aircraft’s crash axe inside the cockpit before attempting to take control of the aircraft. The axe is for an A320 corkpit, not the exact one which was used.show more

Agentic traces contain perfect information about an agent’s behavior... with every plan, action, and retry. But that information gets lost in a sea of JSON. So we built AgentPrism: open source React components that turn traces into visual diagrams for debugging AI agents. You can plug in your OpenTelemetry data and see your agent’s process unfold: messages, tool calls, retries. Quotient AI automatically monitors, analyzes, and improves AI agents. Being able to review traces quickly is paramount for their research, and for their customers. “Dealing with agent traces was one of the biggest frustrations for our researchers and a huge time sink. All of that has gone away since adding AgentPrism, and we’re excited to bring that functionality to our users.” — Julia Neagushow more

The startup world runs on iMessage. The problem is,... the Mac messages app is not designed for productivity and there’s no alternative online. If you’re responding to 100+ texts a day, it’s painful and messages get lost easily. As a weekend project, I used Fable to vibecode an AI-native iMessage wrapper. It has: - AI autodrafting that continually learns from your edits - Time sensitive message detection as a separate section - The ability to archive messages so you can get to inbox zero. It reads from the local chat.db on your Mac, and sends messages via AppleScript, so it’s fully secure since it still uses the iMessage protocol on your computer. At Trajectory, we’re all about using AI to accelerate our company as much as possible as possible, and natively bake in CL into all of our processes. This is just one example of how we operate. If there’s enough interest, I’ll clean up the code and send the GH link!show more

THIS FREE BROWSER TOOL LETS YOU BUILD REAL-TIME DITHER... ANIMATIONS AND EXPORT THEM AS VIDEO dither is everywhere right now (Spotify, websites, album covers) but every tool for making it is either a Photoshop plugin or some after effects rabbit hole. this one runs in your browser and gives you full control over the motion. what you can do: > choose from Bayer 4x4, 8x8, halftone, blue noise, crosshatch, diamond, spiral, and ASCII patterns > animate with speed, intensity, scale, and FPS controls > add text or 3D rotation with auto-spin and flatten > tune foreground, background, and accent colors or pick from palettes > post-processing effects layered on top > export as PNG, WebM, MP4, or embed HTML to drop on a site > save presets to reuse your favorite looks resolution presets go up to 1920x1080 for landscape and 1080x1920 for portrait, plus custom sizes. most generative art tools online are single-style gimmicks. this is a full-blown animation studio for one specific aesthetic, and it looks like a real product. link in replies 👇show more

React Native now has its own shadcn/ui equivalent —... introducing 𝗡𝗮𝘁𝗶𝘃𝗲𝗨𝗜. If you love the flexibility of copying customisable components directly into your project (avoiding heavy, dependency-laden packages), NativeUI is designed for you. 𝗡𝗮𝘁𝗶𝘃𝗲𝗨𝗜 offers beautifully crafted, accessible components tailored for React Native, following the same copy-paste philosophy as shadcn/ui. Built with 𝗡𝗮𝘁𝗶𝘃𝗲𝗪𝗶𝗻𝗱 for fast, declarative, and flexible styling optimised for React Native. ➡️ 𝗖𝗼𝗽𝘆 𝗰𝗼𝗺𝗽𝗼𝗻𝗲𝗻𝘁 𝗰𝗼𝗱𝗲 𝗱𝗶𝗿𝗲𝗰𝘁𝗹𝘆 𝗶𝗻𝘁𝗼 𝘆𝗼𝘂𝗿 𝗽𝗿𝗼𝗷𝗲𝗰𝘁 — no black-box dependencies required. ➡️ 𝗖𝗼𝗺𝗽𝗼𝗻𝗲𝗻𝘁𝘀 𝗮𝗿𝗲 𝗮𝗰𝗰𝗲𝘀𝘀𝗶𝗯𝗹𝗲 𝗯𝘆 𝗱𝗲𝗳𝗮𝘂𝗹𝘁, supporting screen readers and keyboard navigation, and designed to align with native iOS and Android UX patterns. ➡️ 𝗙𝘂𝗹𝗹 𝗰𝗼𝗻𝘁𝗿𝗼𝗹 𝗼𝘃𝗲𝗿 𝘆𝗼𝘂𝗿 𝗨𝗜 without rebuilding common elements like buttons, inputs, or sliders from scratch. ➡️ 𝗖𝗼𝗺𝗽𝗮𝘁𝗶𝗯𝗹𝗲 𝘄𝗶𝘁𝗵 𝗘𝘅𝗽𝗼 𝗮𝗻𝗱 𝘃𝗮𝗻𝗶𝗹𝗹𝗮 𝗥𝗲𝗮𝗰𝘁 𝗡𝗮𝘁𝗶𝘃𝗲 𝗽𝗿𝗼𝗷𝗲𝗰𝘁𝘀, but not yet integrated with Tamagui’s styling system (future support may be planned). ➡️ 𝗦𝘂𝗽𝗽𝗼𝗿𝘁𝘀 𝘁𝗵𝗲𝗺𝗶𝗻𝗴 𝘃𝗶𝗮 𝗡𝗮𝘁𝗶𝘃𝗲𝗪𝗶𝗻𝗱 — though you’ll need to wire it up manually using Tailwind variables, context providers, and config files. Note: The term “install” in the documentation refers to using the shadcn CLI (e.g., npx shadcn@latest add component) to fetch and copy component code into your project, not adding a package to your dependencies. NativeUI isn’t a plug-and-play library; it’s a lightweight toolbox that empowers you to shape your UI with precision and control. 𝗪𝗵𝗮𝘁’𝘀 𝘆𝗼𝘂𝗿 𝗽𝗿𝗲𝗳𝗲𝗿𝗲𝗻𝗰𝗲: npm install a pre-built UI kit for speed, or copy/paste NativeUI components for ultimate customisation? #ReactNative #KeyboardUX #MobileDev #OpenSource #JSDev #Performance #iOSDev #KeyboardExtensions #ReactNativeKeyboard #UIUX #shadcn #nativeuishow more

HTML enters 3D! Or vice versa? With the new... HTML in Canvas by WICG, we can finally put native DOM elements directly into WebGL/WebGPU scenes. It is experimental for now, but the possibilities for 3D interfaces and special effects are huge. This demo was built using Three.js and Omma AI (tool by Spline ) It’s a fun new way to explore what the web can do! Are you interested in seeing the demo?show more

today’s experiment: chimera. a little tool that let’s you... realtime morph through a design system matrix generated by 4 reference images. this one was inspired by listening to techbimbo talk about her process on Dive Club with Ridd 🤿 and How I AI with claire vo 🖤. her approach to choosing moodboards over prompts made me wonder what might be possible if we applied that same approach to generative UI. and after a few dead ends, the idea turned into chimera. the results are very generic at the moment but I might tune it up if people seem interested. the big reminder for me is how much more inspiring a tool feels when you can explore in realtime instead of waiting for results every time you make a change. lots more things to try in that direction.show more