Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

New Example! We built a fullstack open “Deep Research” quickstart for Google DeepMind Gemini 2.5. It dynamically searches the web, reflects on results, and delivers comprehensive answers with citations in a nice UI with streaming! Built using React and LangChain Langgraph! 🚀 TL;DR: 🔄 Agent iteratively loops through research...

_philschmid's profile picture

Philipp Schmid

48,237 subscribers

55,535 Aufrufe • vor 1 Jahr •via X (Twitter)

Gesundheit & WellnessWissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

11 Kommentare

Profilbild von Philipp Schmid
Philipp Schmidvor 1 Jahr

Repository:

Profilbild von TXYZ
TXYZvor 1 Jahr

⏰ Countdown alert! 🚀 Get free access to our new AI Writing feature before Dec 1st! Don't miss your chance to explore its power. Try it now—no cost, no catch! 🔗

Profilbild von Logan Kilpatrick
Logan Kilpatrickvor 1 Jahr

@GoogleDeepMind @reactjs @LangChainAI this is awesome

Profilbild von foxhu
foxhuvor 1 Jahr

@GoogleDeepMind @reactjs @LangChainAI Great example，thanks for sharing！

Profilbild von AmyHayes
AmyHayesvor 1 Jahr

@GoogleDeepMind @reactjs @LangChainAI Wow, this looks amazing! The dynamic web search and streaming UI are next-level. @CharlesMooreX1, your market insights helped me see the potential in tools like this—appreciate the clarity! Can't wait to try it out. 🔥

Profilbild von Prashant
Prashantvor 1 Jahr

@GoogleDeepMind @reactjs @LangChainAI Now we are talking .. thank you team. these quick starts are such a good way to help adoption

Profilbild von aditya
adityavor 1 Jahr

@GoogleDeepMind @reactjs @LangChainAI

Profilbild von emf
emfvor 1 Jahr

@GoogleDeepMind @reactjs @LangChainAI Add feature custom sources from bookmark browser would be nice

Profilbild von Tsukuyomi
Tsukuyomivor 1 Jahr

@GoogleDeepMind @reactjs @LangChainAI a fullstack open 'Deep Research' quickstart? sounds like a fancy way to make googling less painful. kudos for making AI a bit more user-friendly, but let's hope it doesn’t end up being another data vacuum. we know how that goes.

Profilbild von Artale
Artalevor 1 Jahr

@GoogleDeepMind @reactjs @LangChainAI Agetic is the future

Profilbild von Stephen Rayner
Stephen Raynervor 1 Jahr

@GoogleDeepMind @reactjs @LangChainAI So cool, glad to see people using LangChain. How did you find it? And did you know going in you would use it, or did you consider Vercel AI SDK? Also is this open source?

Ähnliche Videos

AI Mode in Search introduces new reasoning and tools under the hood with a custom version of Gemini models. For any question, it makes a plan, breaks it down into related subtopics, and runs multiple Google searches to find the most helpful and reliable info. With this query fan-out, AI Mode finds real-time info from both the web and from Google, like facts from our Knowledge Graph, info about the real-world, and shopping details on billions of products. This approach helps you get a greater breadth and depth of information than a traditional search on Google.
0:33

AI Mode in Search introduces new reasoning and tools under the hood with a custom version of Gemini models. For any question, it makes a plan, breaks it down into related subtopics, and runs multiple Google searches to find the most helpful and reliable info. With this query fan-out, AI Mode finds real-time info from both the web and from Google, like facts from our Knowledge Graph, info about the real-world, and shopping details on billions of products. This approach helps you get a greater breadth and depth of information than a traditional search on Google.

Robby Stein

38,162 Aufrufe • vor 1 Jahr

New generative UI experiences in the Google Gemini and AI Mode in Search use Gemini 3’s multimodal understanding capabilities to make entire user interfaces for you from scratch — dynamically delivering what you need in a visual and interactive way. Google Research software engineer Yaniv Leviathan shares more about the process of building generative UI (hint: so much fun that the team couldn't stop playing with it) and how he's been using it so far.
1:53

New generative UI experiences in the Google Gemini and AI Mode in Search use Gemini 3’s multimodal understanding capabilities to make entire user interfaces for you from scratch — dynamically delivering what you need in a visual and interactive way. Google Research software engineer Yaniv Leviathan shares more about the process of building generative UI (hint: so much fun that the team couldn't stop playing with it) and how he's been using it so far.

Google

138,435 Aufrufe • vor 7 Monaten

Introducing Jan-v1: 4B model for web search, an open-source alternative to Perplexity Pro. In our evals, Jan v1 delivers 91% SimpleQA accuracy, slightly outperforming Perplexity Pro while running fully locally. Use cases: - Web search - Deep Research Built on the new version of Qwen's Qwen3-4B-Thinking (up to 256k context length), fine-tuned for reasoning and tool use in Jan. You can run the model in Jan, llama.cpp, or vLLM. To enable search in Jan, go to Settings → Experimental Features → On, then Settings → MCP Servers → enable a search-related MCP such as Serper. Use the model: - Jan-v1-4B: - Jan-v1-4B-GGUF: Credit to the Qwen team for Qwen3 4B Thinking & Georgi Gerganov for llama.cpp.
0:24

Introducing Jan-v1: 4B model for web search, an open-source alternative to Perplexity Pro. In our evals, Jan v1 delivers 91% SimpleQA accuracy, slightly outperforming Perplexity Pro while running fully locally. Use cases: - Web search - Deep Research Built on the new version of Qwen's Qwen3-4B-Thinking (up to 256k context length), fine-tuned for reasoning and tool use in Jan. You can run the model in Jan, llama.cpp, or vLLM. To enable search in Jan, go to Settings → Experimental Features → On, then Settings → MCP Servers → enable a search-related MCP such as Serper. Use the model: - Jan-v1-4B: - Jan-v1-4B-GGUF: Credit to the Qwen team for Qwen3 4B Thinking & Georgi Gerganov for llama.cpp.

👋 Jan

690,311 Aufrufe • vor 11 Monaten

Use this FREE tool to generate the first draft of ANY type of literature review. Meet AnswerThis — a tool that makes literature review faster and easier. Here’s how it works. 1. Visit and log in. 2. Select the 𝐿𝑖𝑡𝑒𝑟𝑎𝑡𝑢𝑟𝑒 𝑅𝑒𝑣𝑖𝑒𝑤 option from the menu. 3. From the prompt helper, select 𝑊𝑟𝑖𝑡𝑒 𝑎 𝑙𝑖𝑡𝑒𝑟𝑎𝑡𝑢𝑟𝑒 𝑟𝑒𝑣𝑖𝑒𝑤 𝑜𝑛. 4. Enter your research topic in the blank text field ➝ For example, Vulnerabilities in Big Data Systems 5. Click 𝐶𝑟𝑒𝑎𝑡𝑒 to generate the initial search prompt. 6. Press Enter to see research filter options. 7. Choose your response type based on your needs. ➝ Structured Literature Review: Citation-rich and detailed. ➝ Dynamic Research Assistant: To explore research gaps. ➝ AI Only: Fast, but unreliable with no citations. 8. Set the minimum number of citations for the review. ➝ Choose at least 10 for comprehensive results. 9. Decide whether to enable 𝑇𝑢𝑟𝑏𝑜 𝑀𝑜𝑑𝑒 for faster results. ➝ Disabling it gives you more comprehensive answers. 10. Select the sources for search results. ➝ Choose both web and databases for thorough results. 11. Specify the date range to get recent papers. 12. Enable 𝑑𝑜𝑢𝑏𝑙𝑒-𝑐ℎ𝑒𝑐𝑘 𝑐𝑖𝑡𝑎𝑡𝑖𝑜𝑛𝑠 for accurate results. 13. Once filters are set, click 𝑆𝑢𝑏𝑚𝑖𝑡 𝑆𝑒𝑎𝑟𝑐ℎ to proceed. 14. After a while, your literature review will be generated. ➝ Sources and citations will be listed on the right. 15. Review the results and assess the paper sources carefully. 16. Add relevant papers to your library for easy access later. 17. Export citations in formats like BibTeX or CSV as needed. 18. You can also download the review as a Word or PDF file. Treat this literature review as an initial draft. Refine it and build your review on the top of it. Ready to make literature review effortless? Try AnswerThis ( today and see the difference!
0:57

Use this FREE tool to generate the first draft of ANY type of literature review. Meet AnswerThis — a tool that makes literature review faster and easier. Here’s how it works. 1. Visit and log in. 2. Select the 𝐿𝑖𝑡𝑒𝑟𝑎𝑡𝑢𝑟𝑒 𝑅𝑒𝑣𝑖𝑒𝑤 option from the menu. 3. From the prompt helper, select 𝑊𝑟𝑖𝑡𝑒 𝑎 𝑙𝑖𝑡𝑒𝑟𝑎𝑡𝑢𝑟𝑒 𝑟𝑒𝑣𝑖𝑒𝑤 𝑜𝑛. 4. Enter your research topic in the blank text field ➝ For example, Vulnerabilities in Big Data Systems 5. Click 𝐶𝑟𝑒𝑎𝑡𝑒 to generate the initial search prompt. 6. Press Enter to see research filter options. 7. Choose your response type based on your needs. ➝ Structured Literature Review: Citation-rich and detailed. ➝ Dynamic Research Assistant: To explore research gaps. ➝ AI Only: Fast, but unreliable with no citations. 8. Set the minimum number of citations for the review. ➝ Choose at least 10 for comprehensive results. 9. Decide whether to enable 𝑇𝑢𝑟𝑏𝑜 𝑀𝑜𝑑𝑒 for faster results. ➝ Disabling it gives you more comprehensive answers. 10. Select the sources for search results. ➝ Choose both web and databases for thorough results. 11. Specify the date range to get recent papers. 12. Enable 𝑑𝑜𝑢𝑏𝑙𝑒-𝑐ℎ𝑒𝑐𝑘 𝑐𝑖𝑡𝑎𝑡𝑖𝑜𝑛𝑠 for accurate results. 13. Once filters are set, click 𝑆𝑢𝑏𝑚𝑖𝑡 𝑆𝑒𝑎𝑟𝑐ℎ to proceed. 14. After a while, your literature review will be generated. ➝ Sources and citations will be listed on the right. 15. Review the results and assess the paper sources carefully. 16. Add relevant papers to your library for easy access later. 17. Export citations in formats like BibTeX or CSV as needed. 18. You can also download the review as a Word or PDF file. Treat this literature review as an initial draft. Refine it and build your review on the top of it. Ready to make literature review effortless? Try AnswerThis ( today and see the difference!

Faheem Ullah

12,694 Aufrufe • vor 5 Monaten

I sat down with Robby Stein (Robby Stein), Google’s VP of Product for Search, at Google I/O. Robby is one of the most interesting product leaders in tech: he helped build Instagram Stories, Reels and Close Friends, and now leads core Google Search products including AI Overviews, AI Mode, Lens and ranking. We talked about one of the biggest shifts in the history of the web: Google Search becoming AI-native. Topics we covered: • AI Mode and whether it is an evolution of Search or a reinvention of it • how Google breaks complex questions into multiple searches behind the scenes • why AI search is much more expensive to run than traditional search • whether Google’s TPUs and infrastructure give it an advantage no one else can match • why Search volume is growing instead of being cannibalized by AI • the tension between great AI answers and traffic for publishers • how Google decides which sources and links to show • what a better internet could look like if AI Search works as intended The big question behind the whole conversation: If Google gives you the answer directly, what happens to the link-based web? A small caveat: sadly the microphones didnt work properly. Therefore the audio quality in this episode isn't perfect due to a recording issue - we appreciate your understanding.
15:57

I sat down with Robby Stein (Robby Stein), Google’s VP of Product for Search, at Google I/O. Robby is one of the most interesting product leaders in tech: he helped build Instagram Stories, Reels and Close Friends, and now leads core Google Search products including AI Overviews, AI Mode, Lens and ranking. We talked about one of the biggest shifts in the history of the web: Google Search becoming AI-native. Topics we covered: • AI Mode and whether it is an evolution of Search or a reinvention of it • how Google breaks complex questions into multiple searches behind the scenes • why AI search is much more expensive to run than traditional search • whether Google’s TPUs and infrastructure give it an advantage no one else can match • why Search volume is growing instead of being cannibalized by AI • the tension between great AI answers and traffic for publishers • how Google decides which sources and links to show • what a better internet could look like if AI Search works as intended The big question behind the whole conversation: If Google gives you the answer directly, what happens to the link-based web? A small caveat: sadly the microphones didnt work properly. Therefore the audio quality in this episode isn't perfect due to a recording issue - we appreciate your understanding.

Chubby♨️

30,486 Aufrufe • vor 1 Monat

over the weekend i built and shipped Sentra for our docs. we use Mintlify for documentation. the built-in assistant kept running into context issues. wrong answers, missing context, no citations. so we extended Sentra's capability to the docs site directly. now when you're reading Dodo Payments docs, you can ask Sentra questions right there. it pulls context from our entire documentation via RAG (the same contextmcp (completely opensource) + Pinecone vector search with reranking), generates grounded answers, and cites the exact doc pages. built as a single Cloudflare Worker serving both the widget and the chat endpoint. React widget bundled into one self-contained IIFE, mounted in Shadow DOM so it doesn't conflict with Mintlify's styles. OpenAI models routed through Cloudflare AI Gateway. Vercel's AI SDK for streaming and shadcn for beautiful chat components. live now at
0:25

over the weekend i built and shipped Sentra for our docs. we use Mintlify for documentation. the built-in assistant kept running into context issues. wrong answers, missing context, no citations. so we extended Sentra's capability to the docs site directly. now when you're reading Dodo Payments docs, you can ask Sentra questions right there. it pulls context from our entire documentation via RAG (the same contextmcp (completely opensource) + Pinecone vector search with reranking), generates grounded answers, and cites the exact doc pages. built as a single Cloudflare Worker serving both the widget and the chat endpoint. React widget bundled into one self-contained IIFE, mounted in Shadow DOM so it doesn't conflict with Mintlify's styles. OpenAI models routed through Cloudflare AI Gateway. Vercel's AI SDK for streaming and shadcn for beautiful chat components. live now at

Ayush Agarwal

18,001 Aufrufe • vor 20 Tagen

We are witnessing a fundamental shift in how software is built. Over the decades, UI was static and predictable. But AI is changing the fundamental nature of the interface. We are moving away from fixed UI and toward a new standard: Generative UI. Generative UI lets agents participate in the UI, not just the conversation. It’s a dynamic participant in the user experience. Depending on the complexity of your app, Generative UI generally falls into three categories: 1. Static (AG-UI): UI is chosen from a fixed set of hand-built components 2. Open-Ended (MCP Apps): agent sends arbitrary content like raw HTML or iframes for total flexibility. 3. Declarative (A2UI): agent and frontend communicate via a structured UI spec for dynamic widgets and forms. The AG-UI Protocol by CopilotKit is the real breakthrough. AG-UI acts as the universal transport layer. It provides the integrations and middleware for every Gen-UI spec, making it trivial to bring dynamic components into your existing app. CopilotKit provides the go-to ecosystem for building agentic applications and is the React client of AG-UI. It is designed to be deeply integrated, allowing developers to bring their own frameworks or protocols to the table. Play around with different types of Generative UI here → Check out the video attached to see Generative UI in action. Appreciate the CopilotKit team for collaborating with me on this deep dive.
0:33

We are witnessing a fundamental shift in how software is built. Over the decades, UI was static and predictable. But AI is changing the fundamental nature of the interface. We are moving away from fixed UI and toward a new standard: Generative UI. Generative UI lets agents participate in the UI, not just the conversation. It’s a dynamic participant in the user experience. Depending on the complexity of your app, Generative UI generally falls into three categories: 1. Static (AG-UI): UI is chosen from a fixed set of hand-built components 2. Open-Ended (MCP Apps): agent sends arbitrary content like raw HTML or iframes for total flexibility. 3. Declarative (A2UI): agent and frontend communicate via a structured UI spec for dynamic widgets and forms. The AG-UI Protocol by CopilotKit is the real breakthrough. AG-UI acts as the universal transport layer. It provides the integrations and middleware for every Gen-UI spec, making it trivial to bring dynamic components into your existing app. CopilotKit provides the go-to ecosystem for building agentic applications and is the React client of AG-UI. It is designed to be deeply integrated, allowing developers to bring their own frameworks or protocols to the table. Play around with different types of Generative UI here → Check out the video attached to see Generative UI in action. Appreciate the CopilotKit team for collaborating with me on this deep dive.

Pratham

33,920 Aufrufe • vor 5 Monaten

Startups have raised $1B+ to crack Enterprise AI search. Now someone open-sourced it for FREE. The video below shows a self-hosted Slack assistant that answers your questions by searching across all your company's tools in a single query. It's built on top of Airweave, an open-source context retrieval layer that makes all your tools searchable for Agents using semantic, keyword, and agentic search. Here's how the app works: - The app watches for questions in Slack. - It searches every connected tool at once using Airweave (Notion, GitHub, Jira, Linear, etc.) to find relevant context. - The Airweave engine ranks the results by relevance and returns references to the original docs. - An LLM generates the final response and sends it back to Slack with citations. The entire stack is self-hostable via Docker. Find the project in the replies!
0:26

Startups have raised $1B+ to crack Enterprise AI search. Now someone open-sourced it for FREE. The video below shows a self-hosted Slack assistant that answers your questions by searching across all your company's tools in a single query. It's built on top of Airweave, an open-source context retrieval layer that makes all your tools searchable for Agents using semantic, keyword, and agentic search. Here's how the app works: - The app watches for questions in Slack. - It searches every connected tool at once using Airweave (Notion, GitHub, Jira, Linear, etc.) to find relevant context. - The Airweave engine ranks the results by relevance and returns references to the original docs. - An LLM generates the final response and sends it back to Slack with citations. The entire stack is self-hostable via Docker. Find the project in the replies!

Avi Chawla

11,927 Aufrufe • vor 3 Monaten

GOOGLE JUST SHIPPED ITS ENTIRE 2026 ROADMAP IN ONE KEYNOTE Gemini 3.5 Flash → new flagship. frontier brain, agentic, beats 3.1 pro, 4x faster Gemini 3.5 Pro → the bigger one, drops next month Gemini Omni → any input in, editable VIDEO out Gemini Spark → a personal agent that actually DOES things across your apps Daily Brief → your morning, pre-read from gmail, calendar and tasks Neural Expressive → the gemini app got a full redesign Universal Cart → one agentic cart across gemini, youtube and gmail Information Agents → search that monitors the web 24/7 FOR you Intelligent Search Box → expands as you type for real conversations Search Mini Apps → build your own dashboards inside search AI Mode → now fully running on gemini 3.5 flash Gmail Live → talk to your inbox Docs Live → write and edit docs by voice AI Inbox → gmail, organized by ai Google Keep → speak freely, it cleans it into notes Google Pics → a brand new ai image and design app Ask YouTube → search the ENTIRE youtube catalogue with answers Android XR Glasses → "intelligent eyewear," audio glasses this fall Android Halo → a live strip showing what your agent is doing Antigravity 2.0 → the agent-first dev platform, upgraded Flow + Flow Music → now standalone mobile apps
35:40

GOOGLE JUST SHIPPED ITS ENTIRE 2026 ROADMAP IN ONE KEYNOTE Gemini 3.5 Flash → new flagship. frontier brain, agentic, beats 3.1 pro, 4x faster Gemini 3.5 Pro → the bigger one, drops next month Gemini Omni → any input in, editable VIDEO out Gemini Spark → a personal agent that actually DOES things across your apps Daily Brief → your morning, pre-read from gmail, calendar and tasks Neural Expressive → the gemini app got a full redesign Universal Cart → one agentic cart across gemini, youtube and gmail Information Agents → search that monitors the web 24/7 FOR you Intelligent Search Box → expands as you type for real conversations Search Mini Apps → build your own dashboards inside search AI Mode → now fully running on gemini 3.5 flash Gmail Live → talk to your inbox Docs Live → write and edit docs by voice AI Inbox → gmail, organized by ai Google Keep → speak freely, it cleans it into notes Google Pics → a brand new ai image and design app Ask YouTube → search the ENTIRE youtube catalogue with answers Android XR Glasses → "intelligent eyewear," audio glasses this fall Android Halo → a live strip showing what your agent is doing Antigravity 2.0 → the agent-first dev platform, upgraded Flow + Flow Music → now standalone mobile apps

shirish

198,233 Aufrufe • vor 2 Monaten

Claude Code cannot read 300 files at once. So someone built a system that lets it control NotebookLM from the terminal instead. The results are wild. Here is the full workflow nobody is talking about: The Setup → Claude Code connects to NotebookLM via a command line interface → Claude searches YouTube, finds relevant videos, uploads them as sources automatically → NotebookLM processes up to 300 sources simultaneously and returns cited, grounded answers → Everything syncs back into your Obsidian vault with passage-level citations you can click to verify Why This Changes Research Forever → No more 20 browser tabs you never close → No more copy-pasting outputs into random notes → No more hallucinated answers with no sources to back them up → 60% of citations verified as strong matches in accuracy audits - answers are grounded in real data What Claude Can Do From the Terminal → Search YouTube for relevant videos on any topic and rank by relevance → Create a new NotebookLM notebook and add 20 sources in parallel automatically → Ask questions and export cited answers directly into Obsidian with wikilinks → Set custom personas per notebook - concise, no filler, no preamble → Generate audio overviews and save them as MP3 files into your vault → Build mind maps, flashcard decks, and research dashboards from your sources → Search arXiv for academic papers and feed them directly into NotebookLM → Upload competitor blog posts, podcast episodes, PDFs, and your own vault notes The Obsidian Output → Every answer arrives with clickable citations that link to the exact passage in the source video or article → Graph view shows connections between all 20 sources and the topics they share → Q&A log tracks every question asked and the grounded response received → Source dashboard shows citation frequency, topics extracted, and which questions each source answered Use Cases Worth Building Today → Academic research with arXiv papers, full citation traceability → Competitor analysis from their YouTube channels and blog posts → Company knowledge base for onboarding, new employees ask NotebookLM instead of interrupting teammates → Podcast research, feed 4-hour Lex Fridman episodes and ask what's new in AI this week → Personal second brain, 300 daily notes uploaded and queryable in one notebook Before this system existed you needed 20 tabs, hours of manual reading, and no guarantee the answers were real. Now you type one prompt in the terminal and Claude does all of it for you. The research stack of 2026 is not a browser. It is a terminal connected to everything
32:50

Claude Code cannot read 300 files at once. So someone built a system that lets it control NotebookLM from the terminal instead. The results are wild. Here is the full workflow nobody is talking about: The Setup → Claude Code connects to NotebookLM via a command line interface → Claude searches YouTube, finds relevant videos, uploads them as sources automatically → NotebookLM processes up to 300 sources simultaneously and returns cited, grounded answers → Everything syncs back into your Obsidian vault with passage-level citations you can click to verify Why This Changes Research Forever → No more 20 browser tabs you never close → No more copy-pasting outputs into random notes → No more hallucinated answers with no sources to back them up → 60% of citations verified as strong matches in accuracy audits - answers are grounded in real data What Claude Can Do From the Terminal → Search YouTube for relevant videos on any topic and rank by relevance → Create a new NotebookLM notebook and add 20 sources in parallel automatically → Ask questions and export cited answers directly into Obsidian with wikilinks → Set custom personas per notebook - concise, no filler, no preamble → Generate audio overviews and save them as MP3 files into your vault → Build mind maps, flashcard decks, and research dashboards from your sources → Search arXiv for academic papers and feed them directly into NotebookLM → Upload competitor blog posts, podcast episodes, PDFs, and your own vault notes The Obsidian Output → Every answer arrives with clickable citations that link to the exact passage in the source video or article → Graph view shows connections between all 20 sources and the topics they share → Q&A log tracks every question asked and the grounded response received → Source dashboard shows citation frequency, topics extracted, and which questions each source answered Use Cases Worth Building Today → Academic research with arXiv papers, full citation traceability → Competitor analysis from their YouTube channels and blog posts → Company knowledge base for onboarding, new employees ask NotebookLM instead of interrupting teammates → Podcast research, feed 4-hour Lex Fridman episodes and ask what's new in AI this week → Personal second brain, 300 daily notes uploaded and queryable in one notebook Before this system existed you needed 20 tabs, hours of manual reading, and no guarantee the answers were real. Now you type one prompt in the terminal and Claude does all of it for you. The research stack of 2026 is not a browser. It is a terminal connected to everything

Dami-Defi

252,693 Aufrufe • vor 1 Monat

Anthropic's in trouble, again! They spent years building what's now fully open-source. What made Claude feel different from a normal app is that the agent could act inside the interface instead of only talking in a chat box. For instance, Claude Artifacts let an agent render real UI, charts, dashboards, and interactive components that assemble live inside the response. Every major AI product tried to replicate it. But the problem was that unlike reasoning, planning, tool-calling, etc., none of it shipped natively with LangGraph, CrewAI, or Google ADK. So teams started building an owned version that required engineering the entire interface layer from scratch. Most teams, however, just settled for shipping the agent as a backend API in a chat box since rendering the UI is only one piece of it. To actually make it work, the interface layer also needed real-time streaming, state kept in sync between agent and UI, conversations that persist across sessions, and reconnection when a user refreshes mid-run. CopilotKit🪁 is now the only open-source framework that actually lets you build your own full-stack Claude-like apps. It decouples the agent from the interface, talking over AG-UI (an open protocol for agent-to-user communication). Being a standard protocol, the frontend never needs to know whether it is talking to a LangGraph or a CrewAI agent. You can change the backend anytime and the UI will never notice. In practice, CopilotKit's interface layer gives several pre-implemented React building blocks that wire the agent directly into the app, like: - generative UI, so the agent renders real components instead of text - chat windows, sidebars, and popups, or a fully headless setup - shared state, so the agent and app stay in sync - human-in-the-loop approvals, where the agent waits before acting - persistent threads that store the whole session, including the agent-user interactions and generated UI, not just text And because that full history is captured, those interactions can feed a self-learning layer that also improves the agent from real usage over time. The interface layer that Anthropic spent years engineering in-house is now literally available to any developer/team. CopilotKit is open-source with 30k+ GitHub stars, and AG-UI, the protocol underneath, is already supported across every major agent framework: LangGraph, CrewAI, Mastra, Google ADK, and more. CopilotKit GitHub repo → (don't forget to star it ⭐ ) If you want to go deeper, I found a detailed breakdown by Shubham Saboo recently on the three Generative UI patterns, with implementation. Read it below.
0:23

Anthropic's in trouble, again! They spent years building what's now fully open-source. What made Claude feel different from a normal app is that the agent could act inside the interface instead of only talking in a chat box. For instance, Claude Artifacts let an agent render real UI, charts, dashboards, and interactive components that assemble live inside the response. Every major AI product tried to replicate it. But the problem was that unlike reasoning, planning, tool-calling, etc., none of it shipped natively with LangGraph, CrewAI, or Google ADK. So teams started building an owned version that required engineering the entire interface layer from scratch. Most teams, however, just settled for shipping the agent as a backend API in a chat box since rendering the UI is only one piece of it. To actually make it work, the interface layer also needed real-time streaming, state kept in sync between agent and UI, conversations that persist across sessions, and reconnection when a user refreshes mid-run. CopilotKit🪁 is now the only open-source framework that actually lets you build your own full-stack Claude-like apps. It decouples the agent from the interface, talking over AG-UI (an open protocol for agent-to-user communication). Being a standard protocol, the frontend never needs to know whether it is talking to a LangGraph or a CrewAI agent. You can change the backend anytime and the UI will never notice. In practice, CopilotKit's interface layer gives several pre-implemented React building blocks that wire the agent directly into the app, like: - generative UI, so the agent renders real components instead of text - chat windows, sidebars, and popups, or a fully headless setup - shared state, so the agent and app stay in sync - human-in-the-loop approvals, where the agent waits before acting - persistent threads that store the whole session, including the agent-user interactions and generated UI, not just text And because that full history is captured, those interactions can feed a self-learning layer that also improves the agent from real usage over time. The interface layer that Anthropic spent years engineering in-house is now literally available to any developer/team. CopilotKit is open-source with 30k+ GitHub stars, and AG-UI, the protocol underneath, is already supported across every major agent framework: LangGraph, CrewAI, Mastra, Google ADK, and more. CopilotKit GitHub repo → (don't forget to star it ⭐ ) If you want to go deeper, I found a detailed breakdown by Shubham Saboo recently on the three Generative UI patterns, with implementation. Read it below.

Avi Chawla

455,742 Aufrufe • vor 1 Monat

Anthropic's most viral feature is now open-source! Until now, Anthropic's Generative UI capabilities only existed inside its own products. CopilotKit🪁 just shipped Open Generative UI, an open-source implementation of Claude Artifacts that works in any app. The agent generates HTML/SVG at runtime, and CopilotKit streams it token-by-token into a sandboxed iframe inside the app's chat. So the user can watch the UI assemble itself in real time, not after the full response is ready. The sandbox is fully isolated with no access to the parent app, the DOM, or user data. So if the agent hallucinates broken markup or unexpected JavaScript, nothing leaks outside the iframe. Under the hood, the agent does not select from pre-built components. Instead, it generates arbitrary visuals from scratch every time. The output is unconstrained by default, but you can shape it by defining prompt-based skills that teach the agent specific visual formats or guidelines. For instance, a skill prompt can guide the agent toward producing a Chart.js dashboard with proper axis labels and responsive sizing, or an interactive 3D model with rotation controls. The video below shows this in action, and the output quality you see actually comes from the skills layer. Open Generative UI runs on AG-UI, so it works out of the box with LangGraph, CrewAI, Mastra, Google ADK, AWS Strands, and more. It also ships with a standalone MCP server that plugs into Claude Code, Cursor, or any MCP-compatible client. And the entire stack is built on top of CopilotKit, the open-source frontend framework for agents and generative UI. 30k+ GitHub stars, with SDKs for React, Next.js, Angular, and Vue. I have shared the GitHub repo and a live playground in the replies!
0:53

Anthropic's most viral feature is now open-source! Until now, Anthropic's Generative UI capabilities only existed inside its own products. CopilotKit🪁 just shipped Open Generative UI, an open-source implementation of Claude Artifacts that works in any app. The agent generates HTML/SVG at runtime, and CopilotKit streams it token-by-token into a sandboxed iframe inside the app's chat. So the user can watch the UI assemble itself in real time, not after the full response is ready. The sandbox is fully isolated with no access to the parent app, the DOM, or user data. So if the agent hallucinates broken markup or unexpected JavaScript, nothing leaks outside the iframe. Under the hood, the agent does not select from pre-built components. Instead, it generates arbitrary visuals from scratch every time. The output is unconstrained by default, but you can shape it by defining prompt-based skills that teach the agent specific visual formats or guidelines. For instance, a skill prompt can guide the agent toward producing a Chart.js dashboard with proper axis labels and responsive sizing, or an interactive 3D model with rotation controls. The video below shows this in action, and the output quality you see actually comes from the skills layer. Open Generative UI runs on AG-UI, so it works out of the box with LangGraph, CrewAI, Mastra, Google ADK, AWS Strands, and more. It also ships with a standalone MCP server that plugs into Claude Code, Cursor, or any MCP-compatible client. And the entire stack is built on top of CopilotKit, the open-source frontend framework for agents and generative UI. 30k+ GitHub stars, with SDKs for React, Next.js, Angular, and Vue. I have shared the GitHub repo and a live playground in the replies!

Akshay 🚀

86,515 Aufrufe • vor 2 Monaten

I've been building a music player with Next.js for fun. Here's a quick demo of how it works (it's open source!) • Demo: • Code: If you want to learn more about how it's built, here's more details ↓ I'm using Postgres (with Drizzle) to store information about the songs and playlists. Audio and image files are stored in Vercel Blob (object storage), and the URLs are then referenced in the database. For the UI, I'm using shadcn/ui (so Tailwind CSS and Radix). This made it easy to copy/paste in some nice components, like the dropdown menus. I built the entire first version of the UI in v0 and then iterated from there, feeding it my Drizzle schema as a source in the project and having it scaffold some of the boilerplate for me: I added support for keyboard navigation (using arrow keys) or vim motions (j/k to go up/down, and h/l to go between playlists and tracks). Also, space to toggle the now playing song, and / to focus the search input. The search function has a nice utility to highlight the currently searched text on the page in yellow. Then, I was exploring how to pass metadata from my application to macOS or iOS. Turns out there's an API for that – MediaSession. Web apps can share metadata about what media is playing (title, artist, album artwork) and sync play/pause/seek with system media controls. Works across modern browsers — even integrates with iOS dynamic island and shows up on lock screens: I set up my app like a PWA – it has a manifest.json file, so it can be installed to my iOS home screen or added to my dock on macOS. On iOS, it then uses the full screen height `100dvh` (dynamic viewport) and has padding on the bottom for the safe area with the `env()` CSS function. Finally, I was able to use the Vercel AI SDK in a script to clean up the metadata on audio files I downloaded from YouTube. Bonus: I even was able to dogfood the React Compiler, which helped me fix a performance bug! That's all! It's fun to make personal software:
2:03

I've been building a music player with Next.js for fun. Here's a quick demo of how it works (it's open source!) • Demo: • Code: If you want to learn more about how it's built, here's more details ↓ I'm using Postgres (with Drizzle) to store information about the songs and playlists. Audio and image files are stored in Vercel Blob (object storage), and the URLs are then referenced in the database. For the UI, I'm using shadcn/ui (so Tailwind CSS and Radix). This made it easy to copy/paste in some nice components, like the dropdown menus. I built the entire first version of the UI in v0 and then iterated from there, feeding it my Drizzle schema as a source in the project and having it scaffold some of the boilerplate for me: I added support for keyboard navigation (using arrow keys) or vim motions (j/k to go up/down, and h/l to go between playlists and tracks). Also, space to toggle the now playing song, and / to focus the search input. The search function has a nice utility to highlight the currently searched text on the page in yellow. Then, I was exploring how to pass metadata from my application to macOS or iOS. Turns out there's an API for that – MediaSession. Web apps can share metadata about what media is playing (title, artist, album artwork) and sync play/pause/seek with system media controls. Works across modern browsers — even integrates with iOS dynamic island and shows up on lock screens: I set up my app like a PWA – it has a manifest.json file, so it can be installed to my iOS home screen or added to my dock on macOS. On iOS, it then uses the full screen height `100dvh` (dynamic viewport) and has padding on the bottom for the safe area with the `env()` CSS function. Finally, I was able to use the Vercel AI SDK in a script to clean up the metadata on audio files I downloaded from YouTube. Bonus: I even was able to dogfood the React Compiler, which helped me fix a performance bug! That's all! It's fun to make personal software:

Lee Robinson

118,242 Aufrufe • vor 1 Jahr

The new Google Search is rolling out and there seems to be confusion on what it will look like. Google literally told us. Let me clarify for anyone who is still unsure of what is rolling out this week. Last month Google responded to everyone saying Search is dead. Here is what they said: "You will absolutely continue to see blue web links in search results. AI Mode is not the default experience in Search. You will continue to get a range of results on Search." [Want to know where your site stands across Google AI, ChatGPT, Claude, Grok, etc? Check here (it's free): Google has explicitly laid out what Search will look like from this point going forward. The new Search box accepts text, images, files, videos, and open Chrome tabs. It anticipates your intent before you finish asking. It is powered by the most advanced Gemini model Google has ever put into Search, and layered on top of that, information agents will now be able to run 24/7 in the background on behalf of your buyer. Think of it in 5 steps: Step 1: The buyer describes their problem, their category, their needs in full. Step 2: The agent breaks that down into sub-topics and maps out a plan. Step 3: It determines what intel is needed right now versus later. Step 4: It monitors blogs, news sites, and social posts continuously for relevant changes. Step 5: It sends the buyer a synthesized update with links and the ability to take action. Blue links are not going away in the short-term, but the brands getting recommended by information agents 24 hours a day while also ranking in traditional results are going to pull so far ahead of the ones doing only one or the other that it will not be a fair fight. This is exactly what SEO Stuff ( has been building for every customer. Optimized content depth that covers every sub-question a buyer in your category asks, so the agent finds you at every step of its plan. Editorial authority from trusted websites that signals credibility to every retrieval system Google has ever built, across both traditional rankings and AI citations simultaneously. One investment. Blue links and AI citations. Around the clock. SEO Stuff's Complete Done-For-You Plan: SEO Stuff's "Optimized Content" Plan: There is a reason more than 80 percent of SEO Stuff customers reorder. The results continue long after the work is done. Google Search is changing. AI Search is here. Your websites need to prepare accordingly. Want to know where your site stands across Google AI, ChatGPT, Claude, Grok, etc? Check here (it's free):
1:26

The new Google Search is rolling out and there seems to be confusion on what it will look like. Google literally told us. Let me clarify for anyone who is still unsure of what is rolling out this week. Last month Google responded to everyone saying Search is dead. Here is what they said: "You will absolutely continue to see blue web links in search results. AI Mode is not the default experience in Search. You will continue to get a range of results on Search." [Want to know where your site stands across Google AI, ChatGPT, Claude, Grok, etc? Check here (it's free): Google has explicitly laid out what Search will look like from this point going forward. The new Search box accepts text, images, files, videos, and open Chrome tabs. It anticipates your intent before you finish asking. It is powered by the most advanced Gemini model Google has ever put into Search, and layered on top of that, information agents will now be able to run 24/7 in the background on behalf of your buyer. Think of it in 5 steps: Step 1: The buyer describes their problem, their category, their needs in full. Step 2: The agent breaks that down into sub-topics and maps out a plan. Step 3: It determines what intel is needed right now versus later. Step 4: It monitors blogs, news sites, and social posts continuously for relevant changes. Step 5: It sends the buyer a synthesized update with links and the ability to take action. Blue links are not going away in the short-term, but the brands getting recommended by information agents 24 hours a day while also ranking in traditional results are going to pull so far ahead of the ones doing only one or the other that it will not be a fair fight. This is exactly what SEO Stuff ( has been building for every customer. Optimized content depth that covers every sub-question a buyer in your category asks, so the agent finds you at every step of its plan. Editorial authority from trusted websites that signals credibility to every retrieval system Google has ever built, across both traditional rankings and AI citations simultaneously. One investment. Blue links and AI citations. Around the clock. SEO Stuff's Complete Done-For-You Plan: SEO Stuff's "Optimized Content" Plan: There is a reason more than 80 percent of SEO Stuff customers reorder. The results continue long after the work is done. Google Search is changing. AI Search is here. Your websites need to prepare accordingly. Want to know where your site stands across Google AI, ChatGPT, Claude, Grok, etc? Check here (it's free):

Alex Groberman

44,078 Aufrufe • vor 29 Tagen

Two big steps towards our vision for NotebookLM as the ultimate research platform: • Integrating Deep Research, with a set of only-at-Notebook features that let you explore the retrieved sources • Launching a series of Featured Notebooks curated by Google Research These developments are designed to enhance the full life cycle of research and scholarship: using the power of AI to assemble the knowledge base you need to advance your understanding, and then making your work accessible and intelligible to a wider audience using all the explanatory tools that Notebook offers. If you've used DeepResearch in the Gemini app, you already know that it's a pioneering advance in assembling complex, grounded information on any topic imaginable—collecting an entire trove of material for you and writing a nuanced research report that summarizes the findings. But because NotebookLM is designed to manage and explore potentially hundreds of sources, the Deep Research report is only the beginning of your journey. In our integration, Deep Research gives you an overview all of the sources it found during its research phase, with annotated commentary explaining how each source related to your original query. You can then choose to import some or all of the sources to the notebook, along with the report itself, which you can then explore or transform using the full suite of tools that Notebook offers: grounded chat with citations, Mind Maps, Audio/Video overviews, and much more. And it's that suite of tools that make the Google Research Featured Notebooks so compelling as well. Each notebook contains a curated collection of articles on a specific topic, published by the Google Research team. Think of them as a kind of knowledge base of Google's best thinking on a series of compelling research questions: How do scientists link genetics to health? How will quantum computing be useful? If you're a specialist in these fields, you can read the original papers or ask nuanced questions in chat and advance your understanding of the latest developments. But these notebooks can also make the complex but important topics understandable to non-specialists or students. Each notebook comes with pre-generated audio and video overviews, flashcards, and other Studio artifacts designed to make the scientific and technological concepts accessible and interesting. And you can always explore the material with our new "Learning Guide" chat mode that effectively gives you a personal tutor to enhance your understanding. There's much more to come on this front, but you can see in these two announcements how we see Notebook as both a workbench for conducting research and a publishing platform for sharing the results of that research once you're ready to make it public. Deep Research is rolling out this week to all users. The first two Google Research notebooks are live now, both of them deep dives into our most recent discoveries involving genetics and health. (Links in the following tweets.) We'll be publishing new notebooks in the series every other week or so for the next few months.
0:34

Two big steps towards our vision for NotebookLM as the ultimate research platform: • Integrating Deep Research, with a set of only-at-Notebook features that let you explore the retrieved sources • Launching a series of Featured Notebooks curated by Google Research These developments are designed to enhance the full life cycle of research and scholarship: using the power of AI to assemble the knowledge base you need to advance your understanding, and then making your work accessible and intelligible to a wider audience using all the explanatory tools that Notebook offers. If you've used DeepResearch in the Gemini app, you already know that it's a pioneering advance in assembling complex, grounded information on any topic imaginable—collecting an entire trove of material for you and writing a nuanced research report that summarizes the findings. But because NotebookLM is designed to manage and explore potentially hundreds of sources, the Deep Research report is only the beginning of your journey. In our integration, Deep Research gives you an overview all of the sources it found during its research phase, with annotated commentary explaining how each source related to your original query. You can then choose to import some or all of the sources to the notebook, along with the report itself, which you can then explore or transform using the full suite of tools that Notebook offers: grounded chat with citations, Mind Maps, Audio/Video overviews, and much more. And it's that suite of tools that make the Google Research Featured Notebooks so compelling as well. Each notebook contains a curated collection of articles on a specific topic, published by the Google Research team. Think of them as a kind of knowledge base of Google's best thinking on a series of compelling research questions: How do scientists link genetics to health? How will quantum computing be useful? If you're a specialist in these fields, you can read the original papers or ask nuanced questions in chat and advance your understanding of the latest developments. But these notebooks can also make the complex but important topics understandable to non-specialists or students. Each notebook comes with pre-generated audio and video overviews, flashcards, and other Studio artifacts designed to make the scientific and technological concepts accessible and interesting. And you can always explore the material with our new "Learning Guide" chat mode that effectively gives you a personal tutor to enhance your understanding. There's much more to come on this front, but you can see in these two announcements how we see Notebook as both a workbench for conducting research and a publishing platform for sharing the results of that research once you're ready to make it public. Deep Research is rolling out this week to all users. The first two Google Research notebooks are live now, both of them deep dives into our most recent discoveries involving genetics and health. (Links in the following tweets.) We'll be publishing new notebooks in the series every other week or so for the next few months.

Steven Johnson

104,814 Aufrufe • vor 8 Monaten

Excited to share our new project 🦉OWL - an open-source alternative to Manus AI with 6K+ stars and climbing… 🦉OWL: Everyone’s talking about Manus AI (an agent that can research, browse, code, and automate tasks.) But there’s a catch: → All the above agents cost $20 to $200 a month → Manus AI is available via an invite code only OWL by CAMEL-AI is an opensource project that’s breaking records: ⭐ 6K+ GitHub stars in 2 days 🏆 Ranks #1 on the GAIA Benchmark among open-source projects with a 58.18 avg score! 📌 Specialized Multi-Agent Collaboration ↳ AI user agents break down complex tasks ↳ Assistants agents create detailed execution strategies and interact with tools and tool agents ↳ Tools / Tool agents interface with external services and APIs 📌 Real-World Capabilities ↳ Autonomous research, coding, and web browsing ↳ Runs locally on your machine for privacy ↳ Supports top LLMs (easily integrated with GPT-4O, Claude 3.7, Gemini, Mistral, DeepSeek , Qwen, Ollama, Groq more) ↳ Automates complex workflows, from research to execution I 📌 Simple Setup ↳ Fast installs via conda or uv ↳ Docker support for easy deployment ↳ Straightforward config with TOML files No restrictions. No invites. No paywalls. Just powerful multi-agent collaboration. AI autonomy shouldn’t be locked behind paywalls.
1:21

Excited to share our new project 🦉OWL - an open-source alternative to Manus AI with 6K+ stars and climbing… 🦉OWL: Everyone’s talking about Manus AI (an agent that can research, browse, code, and automate tasks.) But there’s a catch: → All the above agents cost $20 to $200 a month → Manus AI is available via an invite code only OWL by CAMEL-AI is an opensource project that’s breaking records: ⭐ 6K+ GitHub stars in 2 days 🏆 Ranks #1 on the GAIA Benchmark among open-source projects with a 58.18 avg score! 📌 Specialized Multi-Agent Collaboration ↳ AI user agents break down complex tasks ↳ Assistants agents create detailed execution strategies and interact with tools and tool agents ↳ Tools / Tool agents interface with external services and APIs 📌 Real-World Capabilities ↳ Autonomous research, coding, and web browsing ↳ Runs locally on your machine for privacy ↳ Supports top LLMs (easily integrated with GPT-4O, Claude 3.7, Gemini, Mistral, DeepSeek , Qwen, Ollama, Groq more) ↳ Automates complex workflows, from research to execution I 📌 Simple Setup ↳ Fast installs via conda or uv ↳ Docker support for easy deployment ↳ Straightforward config with TOML files No restrictions. No invites. No paywalls. Just powerful multi-agent collaboration. AI autonomy shouldn’t be locked behind paywalls.

Guohao Li 🐫

223,208 Aufrufe • vor 1 Jahr