Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Introducing Unsloth Desktop 🦥 The first desktop app to run and train models locally. • Open-source. Runs on Mac, Windows and Linux • Supports MLX, diffusion image/video, audio, GGUF • Connect Claude Code and Codex to local LLMs • 50% more accurate, self-healing tool calls + sandboxed code exec... show more

Unsloth AI

98,317 subscribers

865,557 views • 1 month ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

35 Comments

Unsloth AI1 month ago

You can download Unsloth Desktop via GitHub or our main site: CPU and Mac setups are supported, yes. Thank you for the support! 🥰

NVIDIA AI1 month ago

Great release! 🔥

MiniMax (official)1 month ago

Congratulations! This is super cool.

Daniel Han1 month ago

We did a small update to fix: 1. Slow Windows downloads (200x slower as it was throttling!) 2. Strix Halo not being detected 3. Fixed Mac asking to download command line tools (uv bug) 4. Better MiniMax-H3 support

Cua1 month ago

🫶

Marcel Spatz1 month ago

Might try that out, might fry my macbook in the processs

Pedro Amaral1 month ago

One more day and another Unsloth AI special occasion

Filecoin1 month ago

it is great for privacy, and freedom to move the data and outputs later lets you stay independent of one machine.

witcheer1 month ago

congratulations! that's huge

Yuval Avidani (יובל אבידני)1 month ago

How is it different from unsloth studio?

Alexey Fateev1 month ago

Guys, this is all awesome, but, you know, I’d really love to be able to install this on my Mac while having the entire deployment on my server - since my GPU server is separate and all the hardware is there. Could you add SSH connection support in your future updates?

Maziyar PANAHI1 month ago

this looks dope! congratulations! 🥳 any extra love for Apple Silicon or is it only for GGUFs? (any metal)

Eric ⚡️ Building...1 month ago

👏

Ivan Fioravanti ᯅ1 month ago

You rock 🙌

JΞNSΞN1 month ago

@ycombinator Totally did not expect this! I’m still testing zcode!

Flapjack Frog1 month ago

Have the various AMD bugs been fixed yet? Last I tried a few weeks ago it was totally unusable on the Strix Halo platform (Linux), with several open bugs on the GH tracker. Examples: (Not all are SH specific) #7485, #7624, #7669, #7380, #7371, #7331,

Eyera1 month ago

Let's gooo! 🔥

tecto1 month ago

Local AI is moving from terminal gymnastics to desktop workflow. nice.

Gargeya1 month ago

What a pleasant surprise, truly! I can't wait to download it and try it. Thank you so much - you are really contributing in making this the best week of the month so far.

Vasko1 month ago

this is cool asf

Aman 𝕏 Senpai1 month ago

Going to burn my Mac mini tonight!

X41 month ago

So Awesome!! Love it!! Do you support MLX, MTPLX and Diffusion models on Apple Silicon?

Broadstreet1 month ago

Congratulations guys, you’ve done amazing things so far

alex okita1 month ago

Always looking at having fun with local AI.

Pearl1 month ago

been using it, it's impressive! well done.

kiri491 month ago

i've tried this and it's great, integrates everything into one app. updating can be a bit weird though, it shows an error even if the update worked just fine

NIFFY1 month ago

This looks amazing and cool, the deep research, rag and mcp is a game changer.🤭🤩

Sabbir Hossain1 month ago

ok so now Unsloth is in the game but with model training capabilities , this is one of the big wins

AO'AbuZ81 month ago

OMG THank you! You just helped me answer how to set that up! I am building an operating system within an operating system and you just shown me exactly what i needed to finish my next hurdle! God Bless you @UnslothAI

Swetank Sisodia1 month ago

I will have to multi clone myself to keep up 🤯

Stephanie F.1 month ago

nice! been waiting for this one to drop

Zero1 month ago

This is also cool

HealthRanger1 month ago

Well, this is a huge deal. There goes my weekend! Gotta download and try this ASAP... your team produces amazing innovations!

Trust⭕️1 month ago

Legends

Arif1 month ago

Amazing

Related Videos

Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX • Self-healing tool calling and code execution • Compare models side by side + export to GGUF GitHub: Blog and Guide: Available now on Hugging Face, NVIDIA, Docker and Colab.

Introducing Unsloth Studio ✨ A new open-source web UI to train and run LLMs. • Run models locally on Mac, Windows, Linux • Train 500+ models 2x faster with 70% less VRAM • Supports GGUF, vision, audio, embedding models • Auto-create datasets from PDF, CSV, DOCX • Self-healing tool calling and code execution • Compare models side by side + export to GGUF GitHub: Blog and Guide: Available now on Hugging Face, NVIDIA, Docker and Colab.

Unsloth AI

1,741,340 views • 6 months ago

finetuning LLMs will never be the same! Unsloth just launched an open-source web UI to run and fine-tune 500+ LLMs without writing any code. key features - run models locally on Mac, Windows, Linux - train 500+ models 2x faster with 70% less VRAM - supports GGUF, vision, audio, embedding models - auto-create datasets from PDF, CSV, DOCX - self-healing tool calling and code execution - compare models side by side + export to GGUF to get started, I've shared links in the next tweet.

finetuning LLMs will never be the same! Unsloth just launched an open-source web UI to run and fine-tune 500+ LLMs without writing any code. key features - run models locally on Mac, Windows, Linux - train 500+ models 2x faster with 70% less VRAM - supports GGUF, vision, audio, embedding models - auto-create datasets from PDF, CSV, DOCX - self-healing tool calling and code execution - compare models side by side + export to GGUF to get started, I've shared links in the next tweet.

Akshay 🚀

45,225 views • 6 months ago

Which models can your machine actually run? Magnitude is a 100% free, open source desktop app that: - profiles your hardware and runs sample calculations - predicts tok/s for every model before you download - recommends the best models, from fast to smart Pick your models and it handles the rest: - downloads and tunes the models for your hardware - connects agents like pi, opencode, hermes in one click - runs models on demand as your agent works Works on whatever hardware you already own: MacBook (Intel or Apple Silicon), Mac Mini, Mac Studio, DGX Spark, Strix Halo, any NVIDIA/AMD GPU, or just a CPU Download it on macOS, Windows, or Linux: Open source:

Which models can your machine actually run? Magnitude is a 100% free, open source desktop app that: - profiles your hardware and runs sample calculations - predicts tok/s for every model before you download - recommends the best models, from fast to smart Pick your models and it handles the rest: - downloads and tunes the models for your hardware - connects agents like pi, opencode, hermes in one click - runs models on demand as your agent works Works on whatever hardware you already own: MacBook (Intel or Apple Silicon), Mac Mini, Mac Studio, DGX Spark, Strix Halo, any NVIDIA/AMD GPU, or just a CPU Download it on macOS, Windows, or Linux: Open source:

Tom Greenwald

47,785 views • 8 days ago

Introducing AQ: a multiplayer harness of harnesses. • Run it on any cloud you already have, or use ours. • Connect any coding harness you like: Claude Code, Codex, OpenCode, Cursor, Kimi, Grok, Devin and more. • Work with your teammates live, way beyond sharing a session. • 17 open-weights models, one click. • Use it from anywhere: Mac, Linux, Windows, iPhone, Android.

Introducing AQ: a multiplayer harness of harnesses. • Run it on any cloud you already have, or use ours. • Connect any coding harness you like: Claude Code, Codex, OpenCode, Cursor, Kimi, Grok, Devin and more. • Work with your teammates live, way beyond sharing a session. • 17 open-weights models, one click. • Use it from anywhere: Mac, Linux, Windows, iPhone, Android.

Khaled

69,613 views • 24 days ago

Here's what happened with OpenAI and Anthropic this past week (even with OpenAI on company-wide spring break) OpenAI closed $122B funding round at $852B valuation with $2B monthly revenue, launched ChatGPT in Apple CarPlay, acquired media company TBPN, introduced Codex pay-as-you-go pricing for teams with ChatGPT Business price drop, Codex plugin for Claude Code, Vanity Fair reported upcoming policy push for superintelligence era, ChatGPT for Excel now available worldwide except EU consumer plans, executive changes with Fidji Simo on medical leave and Brad Lightcap moving to special projects, hosted disaster response AI workshop in Bangkok, and spotted three suspected new OpenAI image models on Arena codenamed maskingtape, packingtape, and gaffertape Anthropic signed Memorandum of Understanding with Australian government, published emotion interpretability research, released model diffing tool for AI models, acquired Coefficient Bio for about $400M, launched computer use in Claude Code, Claude Code auto mode for Enterprise and API users, Microsoft 365 connectors on all plans, computer use on Windows, Claude subscriptions will no longer cover usage on third-party tools like OpenClaw, plus Claude Code source code leaked via npm map file revealing undercover mode and unreleased features, discovered new "Epitaxy" mode in Claude desktop app, and Claude Code /buddy virtual pet easter egg for April 1st, and more

Here's what happened with OpenAI and Anthropic this past week (even with OpenAI on company-wide spring break) OpenAI closed $122B funding round at $852B valuation with $2B monthly revenue, launched ChatGPT in Apple CarPlay, acquired media company TBPN, introduced Codex pay-as-you-go pricing for teams with ChatGPT Business price drop, Codex plugin for Claude Code, Vanity Fair reported upcoming policy push for superintelligence era, ChatGPT for Excel now available worldwide except EU consumer plans, executive changes with Fidji Simo on medical leave and Brad Lightcap moving to special projects, hosted disaster response AI workshop in Bangkok, and spotted three suspected new OpenAI image models on Arena codenamed maskingtape, packingtape, and gaffertape Anthropic signed Memorandum of Understanding with Australian government, published emotion interpretability research, released model diffing tool for AI models, acquired Coefficient Bio for about $400M, launched computer use in Claude Code, Claude Code auto mode for Enterprise and API users, Microsoft 365 connectors on all plans, computer use on Windows, Claude subscriptions will no longer cover usage on third-party tools like OpenClaw, plus Claude Code source code leaked via npm map file revealing undercover mode and unreleased features, discovered new "Epitaxy" mode in Claude desktop app, and Claude Code /buddy virtual pet easter egg for April 1st, and more

Tibor Blaho

29,532 views • 5 months ago

introducing Ascii: The pocket CTO you send it voice memos on Telegram or instructions from your desktop then Ascii handles it all: > writes code and sends you demos, PDF reports and hosted builds when finished > orchestrates many cloud coding agents working in parallel that can plan, code, test and use their desktop > uses codex, claude code SDKs & subscriptions, no API keys required > works on multiple repositories at once > setups cron jobs and webhooks to schedule work when you sleep > supports secrets, git hooks, full cloud machines config with sudo & 60fps desktop access Welcome to a new era of software building where coding agents aren't mere assistants anymore, now they're as valuable and proactive as a world-class CTO, always at arm's reach, in your pocket

introducing Ascii: The pocket CTO you send it voice memos on Telegram or instructions from your desktop then Ascii handles it all: > writes code and sends you demos, PDF reports and hosted builds when finished > orchestrates many cloud coding agents working in parallel that can plan, code, test and use their desktop > uses codex, claude code SDKs & subscriptions, no API keys required > works on multiple repositories at once > setups cron jobs and webhooks to schedule work when you sleep > supports secrets, git hooks, full cloud machines config with sudo & 60fps desktop access Welcome to a new era of software building where coding agents aren't mere assistants anymore, now they're as valuable and proactive as a world-class CTO, always at arm's reach, in your pocket

Anicet

23,468 views • 5 months ago

Onyx just hit #1 on GitHub trending. Open source AI platform — self-hostable, works with every major LLM provider, and ships with: - Agentic RAG - Deep research mode - Custom agents - Web search - Code execution - Voice mode - Image generation - 50+ connectors out of the box This is what a self-hosted AI stack is starting to look like.

Onyx just hit #1 on GitHub trending. Open source AI platform — self-hostable, works with every major LLM provider, and ships with: - Agentic RAG - Deep research mode - Custom agents - Web search - Code execution - Voice mode - Image generation - 50+ connectors out of the box This is what a self-hosted AI stack is starting to look like.

0xMarioNawfal

75,559 views • 5 months ago

Introducing Workshop: cloud + on-device agentic AI. And to celebrate, we're giving away $250k in Google Gemini AI credits. (details below). The future of AI work is neither cloud-based nor local. It's both. In Workshop Cloud, you can use agents powered by frontier models like Claude and/or open source models like Z.ai's GLM-5 to build internal tools, dashboards, and AI web apps. Or, breeze through tasks like managing your Google and Meta Ads. In Workshop Desktop, you can do all the same right on your computer, plus make desktop apps, mobile apps, and 3D creations. Our favorite part? You can power the full agent experience with local models like Qwen 3.5 family on your computer. Fully offline. 2026 is the year in which local models for agentic tasks will become viable for mainstream use. But the setup for tools like OpenClaw is like setting up Linux from scratch on your computer. Workshop Desktop is one-click to install on Windows, Mac, and Linux. It recommends which open source model you should use for your hardware and lets you download and run it right in the app. And its agent harness allows you to chat, create websites, build personal utilities, and analyze data. 100% offline. Or multitask with AI models in the cloud while running other agent threads locally. Start in Workshop Cloud when you want flexibility and speed. Download your project and continue in Workshop Desktop when you want local files, privacy, and/or better performance on large code bases. Publish from either. The agent tooling space is maturing and discerning users have come to expect a lot from their tools. We've packed Workshop with features to help you 10x your productivity. - Native support for skills - Autocompaction for seamless context management - Built-in AI for your apps - Dozens of connectors, like Google Drive, Big Query, and Supabase - dbt integration to ground your dashboards in your semantic layer - Native Github integration - Private app deployment - ... and more (+ we're shipping super fast) To access the free credit offer, RT this post and reply with "Workshop". Make sure you are following us so we can DM you the instructions to redeem. - First 100 to RT + comment get $500 in credits. - Everyone else gets up to $250 And thanks to our partners Modal, Google Gemini, and Z.ai!

Introducing Workshop: cloud + on-device agentic AI. And to celebrate, we're giving away $250k in Google Gemini AI credits. (details below). The future of AI work is neither cloud-based nor local. It's both. In Workshop Cloud, you can use agents powered by frontier models like Claude and/or open source models like Z.ai's GLM-5 to build internal tools, dashboards, and AI web apps. Or, breeze through tasks like managing your Google and Meta Ads. In Workshop Desktop, you can do all the same right on your computer, plus make desktop apps, mobile apps, and 3D creations. Our favorite part? You can power the full agent experience with local models like Qwen 3.5 family on your computer. Fully offline. 2026 is the year in which local models for agentic tasks will become viable for mainstream use. But the setup for tools like OpenClaw is like setting up Linux from scratch on your computer. Workshop Desktop is one-click to install on Windows, Mac, and Linux. It recommends which open source model you should use for your hardware and lets you download and run it right in the app. And its agent harness allows you to chat, create websites, build personal utilities, and analyze data. 100% offline. Or multitask with AI models in the cloud while running other agent threads locally. Start in Workshop Cloud when you want flexibility and speed. Download your project and continue in Workshop Desktop when you want local files, privacy, and/or better performance on large code bases. Publish from either. The agent tooling space is maturing and discerning users have come to expect a lot from their tools. We've packed Workshop with features to help you 10x your productivity. - Native support for skills - Autocompaction for seamless context management - Built-in AI for your apps - Dozens of connectors, like Google Drive, Big Query, and Supabase - dbt integration to ground your dashboards in your semantic layer - Native Github integration - Private app deployment - ... and more (+ we're shipping super fast) To access the free credit offer, RT this post and reply with "Workshop". Make sure you are following us so we can DM you the instructions to redeem. - First 100 to RT + comment get $500 in credits. - Everyone else gets up to $250 And thanks to our partners Modal, Google Gemini, and Z.ai!

Workshop AI

29,379 views • 6 months ago

🐆 Rapid-MLX v0.12 is here. We’ve officially evolved from a simple chat app into a full-fledged, on-device AI studio for Apple Silicon! 🖥️✨ We didn't just push the MLX inference engine to its limits and expand support for a massive lineup of local open-source models—we are alpha-launching the highly anticipated Desktop Version. (A huge shoutout to the IoTeX community for grinding through the closed beta with us. Your feedback was incredible and helped shape this beast.) Here are the game-changing features you can run on your Mac right now, 100% free and 100% offline 👇 🚀 Blazing Fast Local LLMs Run anything from 4B up to Qwen3.5-122B completely offline. No guessing games—we recommend models matched perfectly to your Mac's actual RAM. Rich chat includes syntax highlighting, markdown tables, and honest tok/s metrics. 🎨 Local Image Generation A brand new Images tab to render directly on your machine. Pick a model (FLUX.2-klein, Z-Image-Turbo), prompt, and refine. Everything lands in a visual filmstrip. 👁️ Vision & Live Web Tools Attach an image and chat about it with local vision. Need real-time data? Our built-in web tools (weather, search, page-fetch) run mid-answer with strict, transparent privacy controls. 🤖 Plug-and-Play Coding Agents Wire up Claude Code, Codex, Cline, or Continue in seconds. One copy-paste from the Launch tab spins up a local OpenAI/Anthropic-compatible endpoint. 🔒 Private by Design Everything runs on-device. Signed, notarized, and entirely local. Your data stays yours. Turn your Mac into an AI powerhouse today. ⚡️

raullen

34,148 views • 1 month ago

Introducing Magnitude: your actually local agent 100% private and offline. No token costs, no API keys. Open source. Today's agents are local. The model isn't. Every prompt, every file, every secret gets sent straight to Anthropic and OpenAI. Magnitude is built around local models and runs the whole stack itself. The inference engine is part of the agent, so the models run inside it, right on your computer. It lives in your terminal, and setup is one command. Magnitude profiles your hardware and shows you which models fit, with the trade-offs between quality, speed, and memory. Pick one and start working. No painful config or server to babysit. Out of the box, it can use your shell, edit files, and run scripts. Add skills and it can work with Excel, PowerPoint, PDFs or Chrome. Use it for everyday work: - Analyze sensitive data - Manage private notes - Review code and logs - Search and organize files - Build docs or slides npm i -g @magnitudedev/cli GitHub:

Introducing Magnitude: your actually local agent 100% private and offline. No token costs, no API keys. Open source. Today's agents are local. The model isn't. Every prompt, every file, every secret gets sent straight to Anthropic and OpenAI. Magnitude is built around local models and runs the whole stack itself. The inference engine is part of the agent, so the models run inside it, right on your computer. It lives in your terminal, and setup is one command. Magnitude profiles your hardware and shows you which models fit, with the trade-offs between quality, speed, and memory. Pick one and start working. No painful config or server to babysit. Out of the box, it can use your shell, edit files, and run scripts. Add skills and it can work with Excel, PowerPoint, PDFs or Chrome. Use it for everyday work: - Analyze sensitive data - Manage private notes - Review code and logs - Search and organize files - Build docs or slides npm i -g @magnitudedev/cli GitHub:

Tom Greenwald

397,093 views • 1 month ago

Claude Code on desktop just added an embedded loop that can run your dev server, view the app, review local changes, and watch pull requests until they merge. It can now preview a running app inside the desktop UI while it iterates on fixes. It can also monitor CI for an open PR and either fix failures or merge when checks go green. Earlier “agentic coding” workflows usually bounced between a terminal, a browser, and GitHub, so the model could not directly see what the app rendered or stay attached to CI results without manual babysitting. The new server preview flow starts and stops dev servers from a Preview control, shows the app in an embedded browser, reads logs, and can interact with the page to verify changes. That closes a common gap where a model edits code but cannot reliably confirm the UI and runtime behavior match the intent. The local “Review code” step runs before pushing, and it leaves inline comments on the diff so basic bugs and risky changes get caught earlier. For PR monitoring, the desktop app will track status and CI checks, and it can use auto-fix to attempt repairs and auto-merge to land the PR once checks pass, using GitHub tooling under the hood. Session mobility adds a /desktop command to move a CLI session into the desktop app, and sessions can be pushed to the cloud to resume from web or phone.

Claude Code on desktop just added an embedded loop that can run your dev server, view the app, review local changes, and watch pull requests until they merge. It can now preview a running app inside the desktop UI while it iterates on fixes. It can also monitor CI for an open PR and either fix failures or merge when checks go green. Earlier “agentic coding” workflows usually bounced between a terminal, a browser, and GitHub, so the model could not directly see what the app rendered or stay attached to CI results without manual babysitting. The new server preview flow starts and stops dev servers from a Preview control, shows the app in an embedded browser, reads logs, and can interact with the page to verify changes. That closes a common gap where a model edits code but cannot reliably confirm the UI and runtime behavior match the intent. The local “Review code” step runs before pushing, and it leaves inline comments on the diff so basic bugs and risky changes get caught earlier. For PR monitoring, the desktop app will track status and CI checks, and it can use auto-fix to attempt repairs and auto-merge to land the PR once checks pass, using GitHub tooling under the hood. Session mobility adds a /desktop command to move a CLI session into the desktop app, and sessions can be pushed to the cloud to resume from web or phone.

Rohan Paul

33,431 views • 7 months ago

QVAC SDK 0.13.0 is live, and this version brings a lot of exciting updates! Local AI now plugs into your coding agent, ships as a desktop app in one command, and runs even more models. Highlights: NEW INTEGRATIONS - OpenCode and coding agents: the new @qvac/ai-sdk-provider makes QVAC a local provider. Less setup, same-model requests queue cleanly, and managed mode starts and supervises qvac serve for you. - Broader OpenAI-compatible API, validated across supported flows so covered capabilities stay consistent and testable. - Turn your QVAC project into a real desktop app for Mac, Windows, or Linux with a single command. The new Electron plugin handles the packaging and keeps the app small by including only what it needs. NEW MODELS - New pi0.5 model support - run a vision-language "robot brain" on a single ordinary graphics card, at full accuracy. - Image-to-video, fully local, via the Wan2.1 model in the Diffusion addon. - New BCI add-on: brain-computer interface transcription, fully local. Decode recorded neural signals into text on-device via the Whisper.cpp-based BCI model. IMPROVEMENTS - Whisper GPU transcription on Android, auto-picking the best backend (OpenCL on Adreno 700+, Vulkan elsewhere), unified on one ggml engine. - Parakeet steadier on mobile, with real end-of-utterance detection for streaming. - Supertonic TTS now runs full GPU across Metal, Vulkan, and OpenCL, with native streaming.

QVAC SDK 0.13.0 is live, and this version brings a lot of exciting updates! Local AI now plugs into your coding agent, ships as a desktop app in one command, and runs even more models. Highlights: NEW INTEGRATIONS - OpenCode and coding agents: the new @qvac/ai-sdk-provider makes QVAC a local provider. Less setup, same-model requests queue cleanly, and managed mode starts and supervises qvac serve for you. - Broader OpenAI-compatible API, validated across supported flows so covered capabilities stay consistent and testable. - Turn your QVAC project into a real desktop app for Mac, Windows, or Linux with a single command. The new Electron plugin handles the packaging and keeps the app small by including only what it needs. NEW MODELS - New pi0.5 model support - run a vision-language "robot brain" on a single ordinary graphics card, at full accuracy. - Image-to-video, fully local, via the Wan2.1 model in the Diffusion addon. - New BCI add-on: brain-computer interface transcription, fully local. Decode recorded neural signals into text on-device via the Whisper.cpp-based BCI model. IMPROVEMENTS - Whisper GPU transcription on Android, auto-picking the best backend (OpenCL on Adreno 700+, Vulkan elsewhere), unified on one ggml engine. - Parakeet steadier on mobile, with real end-of-utterance detection for streaming. - Supertonic TTS now runs full GPU across Metal, Vulkan, and OpenCL, with native streaming.

QVAC

20,932,195 views • 3 months ago

BREAKING $AMD is ready to ship Ryzen AI Halo 🆕 in June 2026!!!! 🚀🚀🚀 AKA Personal/Local AI system. Ryzen AI Max+ 395 (Strix Halo APU) with 128 GB of unified LPDDR5X memory, 40 RDNA 3.5 GPU compute units, and a full ROCm software stack preloaded for both Windows and Linux. AMD Halo is $2,000-$3,000 vs $NVDA Spark $4,699 The main purpose of the AMD Ryzen AI Halo is to serve as a compact, developer focused workstation for running intensive AI workloads locally, specifically building, testing, prototyping, fine-tuning, and deploying generative AI models (like LLMs) and Agentic AI applications without relying on the cloud. Run models with up to 200 billion parameters on your desk using 128 GB of unified memory (shared across CPU, GPU, and NPU). This eliminates cloud costs, latency, data privacy concerns, and internet dependency. ~This is for AI developers, researchers, engineers, and creators. ~Teams or individuals wanting faster iteration, data privacy, and cost savings compared to cloud APIs. ~Users experimenting with open-source models, fine-tuning, inference, and production-like local deployment Source: AMD CES 2026

BREAKING $AMD is ready to ship Ryzen AI Halo 🆕 in June 2026!!!! 🚀🚀🚀 AKA Personal/Local AI system. Ryzen AI Max+ 395 (Strix Halo APU) with 128 GB of unified LPDDR5X memory, 40 RDNA 3.5 GPU compute units, and a full ROCm software stack preloaded for both Windows and Linux. AMD Halo is $2,000-$3,000 vs $NVDA Spark $4,699 The main purpose of the AMD Ryzen AI Halo is to serve as a compact, developer focused workstation for running intensive AI workloads locally, specifically building, testing, prototyping, fine-tuning, and deploying generative AI models (like LLMs) and Agentic AI applications without relying on the cloud. Run models with up to 200 billion parameters on your desk using 128 GB of unified memory (shared across CPU, GPU, and NPU). This eliminates cloud costs, latency, data privacy concerns, and internet dependency. ~This is for AI developers, researchers, engineers, and creators. ~Teams or individuals wanting faster iteration, data privacy, and cost savings compared to cloud APIs. ~Users experimenting with open-source models, fine-tuning, inference, and production-like local deployment Source: AMD CES 2026

Mike

16,097 views • 4 months ago

New course: MCP: Build Rich-Context AI Apps with Anthropic. Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic Anthropic and taught by Elie Schoppik Elie Schoppik, its Head of Technical Education. Connecting AI applications to external systems that bring rich context to LLM-based applications has often meant writing custom integrations for each use case. MCP is an open protocol that standardizes how LLMs access tools, data, and prompts from external sources, and simplifies how you provide context to your LLM-based applications. For example, you can provide context via third-party tools that let your LLM make API calls to search the web, access data from local docs, retrieve code from a GitHub repo, and so on. MCP, developed by Anthropic, is based on a client-server architecture that defines the communication details between an MCP client, hosted inside the AI application, and an MCP server that exposes tools, resources, and prompt templates. The server can be a subprocess launched by the client that runs locally or an independent process running remotely. In this hands-on course, you'll learn the core architecture behind MCP. You’ll create an MCP-compatible chatbot, build and deploy an MCP server, and connect the chatbot to your MCP server and other open-source servers. Here’s what you’ll do: - Understand why MCP makes AI development less fragmented and standardizes connections between AI applications and external data sources - Learn the core components of the client-server architecture of MCP and the underlying communication mechanism - Build a chatbot with custom tools for searching academic papers, and transform it into an MCP-compatible application - Build a local MCP server that exposes tools, resources, and prompt templates using FastMCP, and test it using MCP Inspector - Create an MCP client inside your chatbot to dynamically connect to your server - Connect your chatbot to reference servers built by Anthropic’s MCP team, such as filesystem, which implements filesystem operations, and fetch, which extracts contents from the web as markdown - Configure Claude Desktop to connect to your server and others, and explore how it abstracts away the low-level logic of MCP clients - Deploy your MCP server remotely and test it with the Inspector or other MCP-compatible applications - Learn about the roadmap for future MCP development, such as multi-agent architecture, MCP registry API, server discovery, authorization, and authentication MCP is an exciting and important technology that lets you build rich-context AI applications that connect to a growing ecosystem of MCP servers, with minimal integration work. Please sign up here!

New course: MCP: Build Rich-Context AI Apps with Anthropic. Learn to build AI apps that access tools, data, and prompts using the Model Context Protocol in this short course, created in partnership with Anthropic Anthropic and taught by Elie Schoppik Elie Schoppik, its Head of Technical Education. Connecting AI applications to external systems that bring rich context to LLM-based applications has often meant writing custom integrations for each use case. MCP is an open protocol that standardizes how LLMs access tools, data, and prompts from external sources, and simplifies how you provide context to your LLM-based applications. For example, you can provide context via third-party tools that let your LLM make API calls to search the web, access data from local docs, retrieve code from a GitHub repo, and so on. MCP, developed by Anthropic, is based on a client-server architecture that defines the communication details between an MCP client, hosted inside the AI application, and an MCP server that exposes tools, resources, and prompt templates. The server can be a subprocess launched by the client that runs locally or an independent process running remotely. In this hands-on course, you'll learn the core architecture behind MCP. You’ll create an MCP-compatible chatbot, build and deploy an MCP server, and connect the chatbot to your MCP server and other open-source servers. Here’s what you’ll do: - Understand why MCP makes AI development less fragmented and standardizes connections between AI applications and external data sources - Learn the core components of the client-server architecture of MCP and the underlying communication mechanism - Build a chatbot with custom tools for searching academic papers, and transform it into an MCP-compatible application - Build a local MCP server that exposes tools, resources, and prompt templates using FastMCP, and test it using MCP Inspector - Create an MCP client inside your chatbot to dynamically connect to your server - Connect your chatbot to reference servers built by Anthropic’s MCP team, such as filesystem, which implements filesystem operations, and fetch, which extracts contents from the web as markdown - Configure Claude Desktop to connect to your server and others, and explore how it abstracts away the low-level logic of MCP clients - Deploy your MCP server remotely and test it with the Inspector or other MCP-compatible applications - Learn about the roadmap for future MCP development, such as multi-agent architecture, MCP registry API, server discovery, authorization, and authentication MCP is an exciting and important technology that lets you build rich-context AI applications that connect to a growing ecosystem of MCP servers, with minimal integration work. Please sign up here!

Andrew Ng

142,256 views • 1 year ago

🚀 GeoLibre just passed 5,000 stars on GitHub, in only two months! GeoLibre went public on May 27, and the community has already pushed it past 5,100 stars and 500+ forks. Thank you to everyone who starred, forked, filed issues, opened pull requests, and shared the project. For those just discovering it: GeoLibre is a free and open-source, lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. It runs everywhere you do, in the web browser, on the desktop, on mobile, and inside Jupyter notebooks, all while keeping your data local and private. Key features of GeoLibre: - Runs anywhere: the same app ships as a native desktop app, a browser web app, a native Android app, and a Jupyter widget. - Local and private by default: load and analyze GeoJSON, GeoParquet, GeoPackage, Shapefile, COG, LiDAR, 3D Tiles, and more, right in the browser. - Powered by open source: built on MapLibre GL JS, DuckDB-WASM Spatial, Tauri, React, and TypeScript. - Spatial SQL in the browser: query your data with DuckDB Spatial, PostGIS via PGlite, and Apache Sedona. - Extensible: a growing plugin system for cloud data, federal web services, and custom tools. - Supports 12 planetary basemaps: Earth, Mars, the Moon, Mercury, Venus, and more. Two months in, we have already shipped 25 releases, the latest being v2.4.0. There is a lot more to come, and the best way to shape it is to jump in. Try it out - Launch GeoLibre Web: - GitHub: - Documentation: - Release notes: If GeoLibre is useful to you, a star on GitHub and a share here go a long way. Thank you for an incredible first two months. #geospatial #opensource #MapLibre #GeoLibre

🚀 GeoLibre just passed 5,000 stars on GitHub, in only two months! GeoLibre went public on May 27, and the community has already pushed it past 5,100 stars and 500+ forks. Thank you to everyone who starred, forked, filed issues, opened pull requests, and shared the project. For those just discovering it: GeoLibre is a free and open-source, lightweight, cloud-native GIS platform for visualizing, exploring, and analyzing geospatial data. It runs everywhere you do, in the web browser, on the desktop, on mobile, and inside Jupyter notebooks, all while keeping your data local and private. Key features of GeoLibre: - Runs anywhere: the same app ships as a native desktop app, a browser web app, a native Android app, and a Jupyter widget. - Local and private by default: load and analyze GeoJSON, GeoParquet, GeoPackage, Shapefile, COG, LiDAR, 3D Tiles, and more, right in the browser. - Powered by open source: built on MapLibre GL JS, DuckDB-WASM Spatial, Tauri, React, and TypeScript. - Spatial SQL in the browser: query your data with DuckDB Spatial, PostGIS via PGlite, and Apache Sedona. - Extensible: a growing plugin system for cloud data, federal web services, and custom tools. - Supports 12 planetary basemaps: Earth, Mars, the Moon, Mercury, Venus, and more. Two months in, we have already shipped 25 releases, the latest being v2.4.0. There is a lot more to come, and the best way to shape it is to jump in. Try it out - Launch GeoLibre Web: - GitHub: - Documentation: - Release notes: If GeoLibre is useful to you, a star on GitHub and a share here go a long way. Thank you for an incredible first two months. #geospatial #opensource #MapLibre #GeoLibre

Qiusheng Wu

94,705 views • 1 month ago

no money for grok or midjourney? this tool is for you. there's a FREE tool created by an anon dev. open-source. runs locally. 117k stars on github. it generates: > images & video > 3d models > audio > 20+ models here's how to set it up in under 5 minutes: 1️⃣download ComfyUI Desktop go to and grab the desktop app for your system. windows 10+, mac (apple silicon), or linux. it installs like any normal app, it sets up python and every dependency for you in the background. no terminal, no config files. 2️⃣open it first launch, it spins up its own environment automatically. you just wait a few seconds and you're in. you'll land on a node canvas, that's the whole interface. 3️⃣load a starter workflow top menu → Workflow → Browse Templates → Image Generation. click it. this drops a ready-made setup onto your canvas so you don't build anything from scratch. 4️⃣grab a model comfyui ships empty on purpose, the model is the brain, and you pick it. in the template, the "Load Checkpoint" node has a Download button when no model is installed. click it. it pulls one in for you (a few GB, this is the only real wait). 5️⃣install ComfyUI Manager this is the one add-on you don't skip. it lets you install models, custom nodes, and updates with a click instead of the command line. grab it from github (link in comments). it's the difference between fighting comfyui and flying in it. one honest note: an NVIDIA gpu makes this fast, apple silicon works great too, and a weak machine still runs it just slower. that's the whole setup. you now own an image, video, and 3D studio that costs you nothing per month. save this. and the next time grok or midjourney asks for your card. you won't need it. disclaimer: comfyui itself is 100% free. so are the local models (sdxl, flux, wan 2.2, ltx-2). some premium models like seedance are pay-per-use api models, only if you want top-tier quality. the free local ones cover most of what you need. (github link in the comments) follow and turn on post notification for daily AI contents.

no money for grok or midjourney? this tool is for you. there's a FREE tool created by an anon dev. open-source. runs locally. 117k stars on github. it generates: > images & video > 3d models > audio > 20+ models here's how to set it up in under 5 minutes: 1️⃣download ComfyUI Desktop go to and grab the desktop app for your system. windows 10+, mac (apple silicon), or linux. it installs like any normal app, it sets up python and every dependency for you in the background. no terminal, no config files. 2️⃣open it first launch, it spins up its own environment automatically. you just wait a few seconds and you're in. you'll land on a node canvas, that's the whole interface. 3️⃣load a starter workflow top menu → Workflow → Browse Templates → Image Generation. click it. this drops a ready-made setup onto your canvas so you don't build anything from scratch. 4️⃣grab a model comfyui ships empty on purpose, the model is the brain, and you pick it. in the template, the "Load Checkpoint" node has a Download button when no model is installed. click it. it pulls one in for you (a few GB, this is the only real wait). 5️⃣install ComfyUI Manager this is the one add-on you don't skip. it lets you install models, custom nodes, and updates with a click instead of the command line. grab it from github (link in comments). it's the difference between fighting comfyui and flying in it. one honest note: an NVIDIA gpu makes this fast, apple silicon works great too, and a weak machine still runs it just slower. that's the whole setup. you now own an image, video, and 3D studio that costs you nothing per month. save this. and the next time grok or midjourney asks for your card. you won't need it. disclaimer: comfyui itself is 100% free. so are the local models (sdxl, flux, wan 2.2, ltx-2). some premium models like seedance are pay-per-use api models, only if you want top-tier quality. the free local ones cover most of what you need. (github link in the comments) follow and turn on post notification for daily AI contents.

m0h

14,542 views • 3 months ago

Vibe Coding with Codex - Complete Guide Build a Web App, Desktop App & iOS App with Codex + GPT‑5.5 (No Coding Needed, Beginner Friendly) In this video you will learn: > Vibe Coding Basics + Vocab > How to build a web app using Codex > Add db, auth + storage with Firebase > Github Basics > Add AI Features (API's) > Deploy to internet (Vercel) > Convert Web App into Desktop app & iOS App Chapters 00:00 Intro 01:12 Setting up Codex 01:57 The basics of Vibe Coding and Codex 02:20 Projects, Files, App 03:45 Example App - Microsoft Paint 04:25 Running app locally 06:39 Save My Code - Use Github 10:37 Quick Review before building app 12:24 Building a web app - The Prompt 15:32 Creating Web App Project 16:34 Explaining Firebase (Database, Storage, Auth) 18:42 Setting up Firebase Project 22:54 Prompting Codex to build our app 24:49 Inspect Element - Console 26:24 Verify Data being Stored in Database 27:51 Making Changes to App 31:29 Fixing Storage Permissions with Codex 32:20 GPT API - Adding AI to our app 36:20 Making more changes using screenshots 39:02 Queuing vs Steering 40:23 Deploying our app to Vercel (App on Internet) 43:09 Convert web app to desktop app and iOS app 47:15 Web App and Desktop App work Now 48:36 Now let's run the iOS app 50:27 All three apps work! 51:11 Making Changes to iOS app 52:51 Testing agent skill feature of our app 53:55 Summary of what we did

Vibe Coding with Codex - Complete Guide Build a Web App, Desktop App & iOS App with Codex + GPT‑5.5 (No Coding Needed, Beginner Friendly) In this video you will learn: > Vibe Coding Basics + Vocab > How to build a web app using Codex > Add db, auth + storage with Firebase > Github Basics > Add AI Features (API's) > Deploy to internet (Vercel) > Convert Web App into Desktop app & iOS App Chapters 00:00 Intro 01:12 Setting up Codex 01:57 The basics of Vibe Coding and Codex 02:20 Projects, Files, App 03:45 Example App - Microsoft Paint 04:25 Running app locally 06:39 Save My Code - Use Github 10:37 Quick Review before building app 12:24 Building a web app - The Prompt 15:32 Creating Web App Project 16:34 Explaining Firebase (Database, Storage, Auth) 18:42 Setting up Firebase Project 22:54 Prompting Codex to build our app 24:49 Inspect Element - Console 26:24 Verify Data being Stored in Database 27:51 Making Changes to App 31:29 Fixing Storage Permissions with Codex 32:20 GPT API - Adding AI to our app 36:20 Making more changes using screenshots 39:02 Queuing vs Steering 40:23 Deploying our app to Vercel (App on Internet) 43:09 Convert web app to desktop app and iOS app 47:15 Web App and Desktop App work Now 48:36 Now let's run the iOS app 50:27 All three apps work! 51:11 Making Changes to iOS app 52:51 Testing agent skill feature of our app 53:55 Summary of what we did

Riley Brown

147,773 views • 4 months ago

Introducing NexaSDK for Android (Beta) — run the latest AI models locally, 9× more energy-efficient and 2× faster, on Android devices, powered by the Qualcomm Hexagon NPU. This is the first SDK to support NPU, GPU and CPU, unlocking the full power of every Android device — for example, LFM2-1.2B achieves 85 t/s on NPU vs 37 t/s on CPU. With just 3 lines of code, you can run the latest state-of-the-art models across every task, for example: Multimodal (Vision, Audio, Text): OmniNeural-4B Embedding: EmbeddingGemma from Google ASR: Parakeet-v3 from NVIDIA OCR: PaddleOCR from Baidu Inc. Rerank: Jina-reranker from Jina AI LLM: LFM2-1.2B from And we continue to deliver Day-0 model support across our framework. Build on-device AI into your Android app today and enjoy no cloud API cost, full privacy, and offline availability. Check out our Quickstart guide and example app below to get started in minutes.

Introducing NexaSDK for Android (Beta) — run the latest AI models locally, 9× more energy-efficient and 2× faster, on Android devices, powered by the Qualcomm Hexagon NPU. This is the first SDK to support NPU, GPU and CPU, unlocking the full power of every Android device — for example, LFM2-1.2B achieves 85 t/s on NPU vs 37 t/s on CPU. With just 3 lines of code, you can run the latest state-of-the-art models across every task, for example: Multimodal (Vision, Audio, Text): OmniNeural-4B Embedding: EmbeddingGemma from Google ASR: Parakeet-v3 from NVIDIA OCR: PaddleOCR from Baidu Inc. Rerank: Jina-reranker from Jina AI LLM: LFM2-1.2B from And we continue to deliver Day-0 model support across our framework. Build on-device AI into your Android app today and enjoy no cloud API cost, full privacy, and offline availability. Check out our Quickstart guide and example app below to get started in minutes.

NEXA AI

26,091 views • 10 months ago

Your OpenAI and Anthropic weekly digest (Week 16, 2026) OpenAI announced Cloudflare Agent Cloud partnership with OpenAI frontier models including GPT-5.4, Agents SDK update with native sandbox execution and model-native harness, Codex update with background computer use, image generation, memory, automations, and 90+ new plugins, introduced GPT-Rosalind life sciences reasoning model in research preview, Trusted Access for Cyber partners with GPT-5.4-Cyber, shared ChatGPT tax queries data, life sciences usage report, and closed gender gap data, re-enabled Study mode in ChatGPT, ChatGPT keyboard shortcut customization, ads rollout on Free and Go plans in Australia, New Zealand, and Canada, TeenAegis AI Danger Index lowest risk score, and Kevin Weil (OpenAI for Science lead and former CPO), Srinivas Narayanan (CTO of enterprise applications), and Bill Peebles (head of Sora) departures, with OpenAI for Science decentralized into other research teams and Prism sunset folded into Codex Anthropic released Claude Opus 4.7, launched Claude Design in research preview by Anthropic Labs, introduced routines in Claude Code research preview for scheduled, API, and webhook-triggered automations, redesigned Claude Code desktop app for parallel agents, appointed Vas Narasimhan to Board of Directors by the Long-Term Benefit Trust, published Automated Alignment Researchers study on weak-to-strong supervision, and made Claude for Word available on Pro and Max plans

Your OpenAI and Anthropic weekly digest (Week 16, 2026) OpenAI announced Cloudflare Agent Cloud partnership with OpenAI frontier models including GPT-5.4, Agents SDK update with native sandbox execution and model-native harness, Codex update with background computer use, image generation, memory, automations, and 90+ new plugins, introduced GPT-Rosalind life sciences reasoning model in research preview, Trusted Access for Cyber partners with GPT-5.4-Cyber, shared ChatGPT tax queries data, life sciences usage report, and closed gender gap data, re-enabled Study mode in ChatGPT, ChatGPT keyboard shortcut customization, ads rollout on Free and Go plans in Australia, New Zealand, and Canada, TeenAegis AI Danger Index lowest risk score, and Kevin Weil (OpenAI for Science lead and former CPO), Srinivas Narayanan (CTO of enterprise applications), and Bill Peebles (head of Sora) departures, with OpenAI for Science decentralized into other research teams and Prism sunset folded into Codex Anthropic released Claude Opus 4.7, launched Claude Design in research preview by Anthropic Labs, introduced routines in Claude Code research preview for scheduled, API, and webhook-triggered automations, redesigned Claude Code desktop app for parallel agents, appointed Vas Narasimhan to Board of Directors by the Long-Term Benefit Trust, published Automated Alignment Researchers study on weak-to-strong supervision, and made Claude for Word available on Pro and Max plans

Tibor Blaho

11,057 views • 5 months ago