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.

We just open-sourced an entire game studio. Introducing GameDev OS by Scenario. It gives your coding agent 9 specialists and 64 skills. 📁 GameDev OS ┃ ┣ 📁 2D Artist ┃ ┣ 📁 Concept Sketches ┃ ┗ 📁 Sprites and VFX ┃ ┣ 📁 3D Artist ┃ ┣ 📁... Image to 3D ┃ ┗ 📁 Rigging and Retargeting ┃ ┣ 📁 Environment Artist ┃ ┣ 📁 Textures and Skyboxes ┃ ┗ 📁 Walkable 3D Worlds ┃ ┣ 📁 Art Director ┃ ┣ 📁 One Character, Every Shot ┃ ┗ 📁 Quality Check Before It Ships ┃ ┣ 📁 Sound Designer ┃ ┣ 📁 Music and Score ┃ ┗ 📁 Gunfire and SFX ┃ ┣ 📁 Video Producer ┃ ┣ 📁 Cinematic Trailers ┃ ┗ 📁 Captions for Every Platform ┃ ┣ 📁 Marketing Artist ┃ ┣ 📁 Store Art for Every Platform ┃ ┗ 📁 Ads From One Shot ┃ ┣ 📁 Technical Director ┃ ┣ 📁 Workflows Imported From ComfyUI ┃ ┗ 📁 Custom Pipelines ┃ ┗ 📁 Cost Manager ┣ 📁 Model Bake-Offs With Cost ┗ 📁 Team Budgets Each specialist knows the major models for its job: Seedance, GPT, Meshy, Rodin and more. And they work together. 2D Artist sketches the gun → 3D Artist builds it → Environment Artist builds the world around it → Sound Designer adds the gunfire → Video Producer cuts the trailer. One agent. An entire game studio behind it. Free to install. Runs on your agent. Comment “OS” and I’ll send you the entire skill library.show more

Emm | scenario.com

57,917 subscribers

270,489 views • 1 day ago •via X (Twitter)

Gaming Science & Technology

Anya Rossi• Live Now

Private livecam show

37 Comments

GutenLeinad1 day ago

why do I have to play some stupid engagement game if it is "open-source"?

Emm | scenario.com1 day ago

This is all powered by @Scenario_gg. We help creative teams orchestrate and scale everything they produce. Try it out here ↓

Alessandro Zambon1 day ago

thats cool however i think 3D generative models currently give better results then the agent modelling in Blender

Emm | scenario.com1 day ago

We orchestrate LLMs too!

Alessandro Zambon1 day ago

I meant these models give better output compared to blender agentic modelling far from perfect (you still have to fix some things manually/ maybe with agentic modelling) but still very impressive

Emad1 day ago

OS

Scenario1 day ago

What a launch! OS

Freeman1 day ago

this is wild, the pipeline handoffs between specialists actually make sense

GifCo1 day ago

OMG just think of the slop I could turn out with this!!!!

ImX1 day ago

Os

Agentic Sports1 day ago

very cool, well done!

ahad1 day ago

OS

Bitmax $DOG CITY 🌃1 day ago

Os

Balance1 day ago

OS

Aapakari1 day ago

Huge congrats! Cost Manager feels like unsung hero

Denjino 🐂🀄️1 day ago

I'll give it a look OS

Ghazi1 day ago

os

SomeGuyInternet1 day ago

Where is the most important part, Handling gameplay? Like thats core of a game, There needs to be a skill to remind the AI to check existing gameplay mechanics and how changes will affect it. also based on the vid u really need an animation one lmao

Rafsby | a KID called BEAST1 day ago

OS

_k11i_1 day ago

Os

Nick Diaz Of Nauts1 day ago

OS!! FOR THE LOVE OF GOD OS!

Ray Youssef1 day ago

This is awesome

Durtal 🖤1 day ago

Os

Ricardo Augusto1 day ago

OS

Octavianus Bastian A1 day ago

OS

Future Now1 day ago

OS. Love to try it out!

Rich Klein1 day ago

OS

Marouan Mesri (Minpex)1 day ago

Os

snjivo1 day ago

OS

Lee Skies1 day ago

os

j emo r1 day ago

OS

User1 day ago

OS

Jared Daines1 day ago

OS!

Derya Unutmaz, MD1 day ago

@thecsguy This looks pretty cool, interested in this gamedev OS

Filip Pankau1 day ago

OS

Onur Zencirli1 day ago

OS

Nate Tomforde1 day ago

OS

Related Videos

We just open-sourced an entire marketing department. Introducing Marketing OS by Arcads. It does the work of your first six marketing hires. 📁 Marketing Department ┃ ┣ 📁 Head of Marketing ┃ ┣ 📁 Positioning ┃ ┣ 📁 Pricing ┃ ┗ 📁 Competitor Teardowns ┃ ┣ 📁 Copywriter ┃ ┣ 📁 Copy, Graded Before You See It ┃ ┣ 📁 Email Sequences ┃ ┗ 📁 Social Posts ┃ ┣ 📁 Creative Strategist ┃ ┣ 📁 Hooks, Written Out ┃ ┣ 📁 Creative Fatigue vs Dead Audience ┃ ┗ 📁 Next Tests, Ranked ┃ ┣ 📁 Launch Lead ┃ ┣ 📁 The 4 Weeks Before ┃ ┗ 📁 Product Hunt, Hour by Hour ┃ ┣ 📁 SEO Lead ┃ ┣ 📁 GEO ┃ ┗ 📁 App Store Rankings ┃ ┗ 📁 Analyst ┣ 📁 Site Audits, Scored 0-100 ┣ 📁 Test Design ┗ 📁 Spotting AI Slop And they hand work to each other: Analyst finds the leak → Copywriter rewrites it → Creative Strategist tests it → Analyst grades the result One Claude skill. Comment "OS" and I'll send you the setup.

We just open-sourced an entire marketing department. Introducing Marketing OS by Arcads. It does the work of your first six marketing hires. 📁 Marketing Department ┃ ┣ 📁 Head of Marketing ┃ ┣ 📁 Positioning ┃ ┣ 📁 Pricing ┃ ┗ 📁 Competitor Teardowns ┃ ┣ 📁 Copywriter ┃ ┣ 📁 Copy, Graded Before You See It ┃ ┣ 📁 Email Sequences ┃ ┗ 📁 Social Posts ┃ ┣ 📁 Creative Strategist ┃ ┣ 📁 Hooks, Written Out ┃ ┣ 📁 Creative Fatigue vs Dead Audience ┃ ┗ 📁 Next Tests, Ranked ┃ ┣ 📁 Launch Lead ┃ ┣ 📁 The 4 Weeks Before ┃ ┗ 📁 Product Hunt, Hour by Hour ┃ ┣ 📁 SEO Lead ┃ ┣ 📁 GEO ┃ ┗ 📁 App Store Rankings ┃ ┗ 📁 Analyst ┣ 📁 Site Audits, Scored 0-100 ┣ 📁 Test Design ┗ 📁 Spotting AI Slop And they hand work to each other: Analyst finds the leak → Copywriter rewrites it → Creative Strategist tests it → Analyst grades the result One Claude skill. Comment "OS" and I'll send you the setup.

Romain Torres

427,588 views • 1 month ago

We just open-sourced our entire marketing playbook. After huge viral success with our Marketing OS running on Grok Bot, we decided to bring it to Claude. Introducing Marketing AGI by Maxfusion. You no longer need your first 5 marketing hires. 📁 Marketing Department ┃ ┣ 📁 Head of Marketing ┃ ┣ 📁 Positioning & Offer Design ┃ ┣ 📁 Pricing Strategy ┃ ┗ 📁 Competitor Teardowns, Public Data Only ┃ ┣ 📁 Copywriter ┃ ┣ 📁 20 Variants, Panel-Scored ┃ ┣ 📁 Email Sequences, Written in Full ┃ ┗ 📁 Posts Built to Survive the Feed ┃ ┣ 📁 Creative Strategist ┃ ┣ 📁 The 18-Tactic Hook Engine ┃ ┣ 📁 Fatigue Caught at the Concept Level ┃ ┗ 📁 Next Tests, Ranked & Briefed ┃ ┣ 📁 Launch Lead ┃ ┣ 📁 The Runway Before Launch Day ┃ ┗ 📁 Product Hunt, Hour by Hour ┃ ┣ 📁 GEO Lead ┃ ┣ 📁 Ranked by ChatGPT & Perplexity ┃ ┗ 📁 App Store, Metadata to Screenshots ┃ ┗ 📁 Analyst ┣ 📁 Audits, Weighted 0-100 ┣ 📁 Numbers That Mean Something ┗ 📁 AI Slop, Caught on Sight And they coordinate all the work: A single Claude skill runs the whole loop: The Analyst finds the problems, the Copywriter rewrites it, the Creative Strategist tests the new version, and the Analyst grades the outcome. Comment "AGI" and I'll send you the setup.

We just open-sourced our entire marketing playbook. After huge viral success with our Marketing OS running on Grok Bot, we decided to bring it to Claude. Introducing Marketing AGI by Maxfusion. You no longer need your first 5 marketing hires. 📁 Marketing Department ┃ ┣ 📁 Head of Marketing ┃ ┣ 📁 Positioning & Offer Design ┃ ┣ 📁 Pricing Strategy ┃ ┗ 📁 Competitor Teardowns, Public Data Only ┃ ┣ 📁 Copywriter ┃ ┣ 📁 20 Variants, Panel-Scored ┃ ┣ 📁 Email Sequences, Written in Full ┃ ┗ 📁 Posts Built to Survive the Feed ┃ ┣ 📁 Creative Strategist ┃ ┣ 📁 The 18-Tactic Hook Engine ┃ ┣ 📁 Fatigue Caught at the Concept Level ┃ ┗ 📁 Next Tests, Ranked & Briefed ┃ ┣ 📁 Launch Lead ┃ ┣ 📁 The Runway Before Launch Day ┃ ┗ 📁 Product Hunt, Hour by Hour ┃ ┣ 📁 GEO Lead ┃ ┣ 📁 Ranked by ChatGPT & Perplexity ┃ ┗ 📁 App Store, Metadata to Screenshots ┃ ┗ 📁 Analyst ┣ 📁 Audits, Weighted 0-100 ┣ 📁 Numbers That Mean Something ┗ 📁 AI Slop, Caught on Sight And they coordinate all the work: A single Claude skill runs the whole loop: The Analyst finds the problems, the Copywriter rewrites it, the Creative Strategist tests the new version, and the Analyst grades the outcome. Comment "AGI" and I'll send you the setup.

Ori Silver

694,324 views • 1 month ago

📁 Fei-Fei Li founder of World Labs, says the next leap in AI is not language. Human intelligence does not just speak, it moves, perceives, and acts in the physical world. Spatial intelligence is the real core of intelligence. From text to space, from models to 3D and 4D worlds, from understanding words to interacting with reality. The next chapter is not read, it is inhabited.

📁 Fei-Fei Li founder of World Labs, says the next leap in AI is not language. Human intelligence does not just speak, it moves, perceives, and acts in the physical world. Spatial intelligence is the real core of intelligence. From text to space, from models to 3D and 4D worlds, from understanding words to interacting with reality. The next chapter is not read, it is inhabited.

Jon Hernandez

20,592 views • 7 months ago

Meet Cabinet: Your KB + AI Team on Disk🗄️ for the longest time I’ve been frustrated that LLMs are stateless and scattered. every chat starts from zero. no memory, no team, nothing that persists. So I built Cabinet: your AI team on disk 📁 ├─ 📝 .kb/ - CSVs, notes, webapps, everything) ├─ ⏰ .jobs/ - tasks & routines └─ 🧠 .agents/ dump your data, bring your own AI, and it researches, drafts, and ships while you sleep. no db. no lock-in. just files you own.

Meet Cabinet: Your KB + AI Team on Disk🗄️ for the longest time I’ve been frustrated that LLMs are stateless and scattered. every chat starts from zero. no memory, no team, nothing that persists. So I built Cabinet: your AI team on disk 📁 ├─ 📝 .kb/ - CSVs, notes, webapps, everything) ├─ ⏰ .jobs/ - tasks & routines └─ 🧠 .agents/ dump your data, bring your own AI, and it researches, drafts, and ships while you sleep. no db. no lock-in. just files you own.

Hila Shmuel

18,629 views • 3 months ago

GitHub Student Pack + Cursor Pro for a year = everything you need to build a $30K/month startup for free while everyone's paying $20-100/month for AI tools and developer subscriptions, students get all of this for free GitHub Student Developer Pack: > JetBrains all IDEs ($700/year) > GitHub Copilot Pro + GitHub Pro > DigitalOcean $200 cloud credit > Microsoft Azure $100 credit > Notion Education plan > FrontendMasters 6 months > Namecheap domain + SSL > Stripe - fees waived on first $1,000 Cursor Pro 1 Year: > extended limits on Agent > access to all frontier models - GPT, Claude Opus, Gemini > MCPs, skills, and hooks > cloud agents > no card required > takes 2 minutes with your .edu email > no .edu? many countries have their own student verification 📁 Cursor Pro 1 Year ↳ 📁 GitHub Student Pack ↳ combined value: $2,000+ > most students don't know any of this exists bookmark this and share it with every student you know

GitHub Student Pack + Cursor Pro for a year = everything you need to build a $30K/month startup for free while everyone's paying $20-100/month for AI tools and developer subscriptions, students get all of this for free GitHub Student Developer Pack: > JetBrains all IDEs ($700/year) > GitHub Copilot Pro + GitHub Pro > DigitalOcean $200 cloud credit > Microsoft Azure $100 credit > Notion Education plan > FrontendMasters 6 months > Namecheap domain + SSL > Stripe - fees waived on first $1,000 Cursor Pro 1 Year: > extended limits on Agent > access to all frontier models - GPT, Claude Opus, Gemini > MCPs, skills, and hooks > cloud agents > no card required > takes 2 minutes with your .edu email > no .edu? many countries have their own student verification 📁 Cursor Pro 1 Year ↳ 📁 GitHub Student Pack ↳ combined value: $2,000+ > most students don't know any of this exists bookmark this and share it with every student you know

Mr. Buzzoni

29,750 views • 3 months ago

CLAUDE + OBSIDIAN + LOOP ENGINEERING = AN AGENT THAT LIVES INSIDE YOUR NOTES Karpathy's second brain runs on something close to this two years of growth he typed almost none of it himself • the loop, four steps on repeat > read - Claude Opus 5 opens the vault instead of a chat window > write - notes and links get edited inside a branch > check - a critic reads the diff and verifies every link > keep - the good change stays, everything else is left alone • the math > cost: 2-4x a single prompt > pays off past a 5% gain > zero notes overwritten, the vault only grows • the whole system, six plain files > CLAUDE.md, skills, subagents, hooks, MCP, plugins > nothing hidden • three ways in > desktop connector - three clicks > Claude Code - full control > Obsidian plugin - you never leave the app the rules that keep it safe: append, never overwrite measure the gain before adding another step don't let it rewrite the whole vault in one turn a loop that never deletes a note is compound interest on your own thinking the stack: 📁 Claude ↳ 📁 Obsidian ↳

CLAUDE + OBSIDIAN + LOOP ENGINEERING = AN AGENT THAT LIVES INSIDE YOUR NOTES Karpathy's second brain runs on something close to this two years of growth he typed almost none of it himself • the loop, four steps on repeat > read - Claude Opus 5 opens the vault instead of a chat window > write - notes and links get edited inside a branch > check - a critic reads the diff and verifies every link > keep - the good change stays, everything else is left alone • the math > cost: 2-4x a single prompt > pays off past a 5% gain > zero notes overwritten, the vault only grows • the whole system, six plain files > CLAUDE.md, skills, subagents, hooks, MCP, plugins > nothing hidden • three ways in > desktop connector - three clicks > Claude Code - full control > Obsidian plugin - you never leave the app the rules that keep it safe: append, never overwrite measure the gain before adding another step don't let it rewrite the whole vault in one turn a loop that never deletes a note is compound interest on your own thinking the stack: 📁 Claude ↳ 📁 Obsidian ↳

Mr. Buzzoni

27,624 views • 4 days ago

We shipped it. The Drag & Drop Landing Page Builder for Shadcn Studio is here. 🧭 Search blocks (Hero, Features, Pricing, FAQ, etc.) 🧱 Drag & drop onto an empty canvas ↕️ Reorder sections instantly 🖌️ Switch themes in one click 📁 Preview, Export, Save, and Share 🔁 Shuffle Blocks to explore ideas No design software. No clunky builders. Just clean, reliable workflows. Build landing pages visually → export clean shadcn code. Link in the comments below, Try it out 👇🏻

We shipped it. The Drag & Drop Landing Page Builder for Shadcn Studio is here. 🧭 Search blocks (Hero, Features, Pricing, FAQ, etc.) 🧱 Drag & drop onto an empty canvas ↕️ Reorder sections instantly 🖌️ Switch themes in one click 📁 Preview, Export, Save, and Share 🔁 Shuffle Blocks to explore ideas No design software. No clunky builders. Just clean, reliable workflows. Build landing pages visually → export clean shadcn code. Link in the comments below, Try it out 👇🏻

Ajay Patel

19,267 views • 5 months ago

Agent development is moving forward. While production scaling traditionally required manual infrastructure setup and provisioning sandboxes from scratch, there's now a faster path. Managed Agents in the Gemini API are officially live. Get maximum agentic power with zero infrastructure overhead. One simple API call delivers a managed, remote sandbox for your agent so you can focus entirely on behavior. 📁 Fully customizable with your instructions, tools, and data via and 🌐 Test, iterate, and scale long-horizon tasks natively in the cloud. The hardest part of building agents is now the part you don't have to build. 👇 Get started now:

Agent development is moving forward. While production scaling traditionally required manual infrastructure setup and provisioning sandboxes from scratch, there's now a faster path. Managed Agents in the Gemini API are officially live. Get maximum agentic power with zero infrastructure overhead. One simple API call delivers a managed, remote sandbox for your agent so you can focus entirely on behavior. 📁 Fully customizable with your instructions, tools, and data via and 🌐 Test, iterate, and scale long-horizon tasks natively in the cloud. The hardest part of building agents is now the part you don't have to build. 👇 Get started now:

Google for Developers

39,294 views • 3 months ago

Google Veo3 creates beautiful base videos, but what if that’s not enough? I built a ComfyUI workflow that takes it further: 🏗 New structure with Flux (LoRA arch) 📦 Turned into 3D with Hunyuan3d 2 🔁 Integrated + relight via Flux, Controlnet, Denoise and Redux 🎞️ Finalized the video using Wan2.1 + CausVid + VACE The result? Custom, controllable, cinematic videos far beyond the original VEO3. ⚠️ There are still a few scale and quality issues I'm currently working on, but the core process is solid. 📹 I’ll drop a full video tutorial next week. 📁 In the meantime, you can download the workflows, links in the comments (I am using a H100 for it, but probably a A100 is enough).

Google Veo3 creates beautiful base videos, but what if that’s not enough? I built a ComfyUI workflow that takes it further: 🏗 New structure with Flux (LoRA arch) 📦 Turned into 3D with Hunyuan3d 2 🔁 Integrated + relight via Flux, Controlnet, Denoise and Redux 🎞️ Finalized the video using Wan2.1 + CausVid + VACE The result? Custom, controllable, cinematic videos far beyond the original VEO3. ⚠️ There are still a few scale and quality issues I'm currently working on, but the core process is solid. 📹 I’ll drop a full video tutorial next week. 📁 In the meantime, you can download the workflows, links in the comments (I am using a H100 for it, but probably a A100 is enough).

Lovis Odin

89,083 views • 1 year ago

TIRED of posting the same BORING content across 5 platforms? Or watching agencies BURN $2500 a month on posts that get 6 likes? This AI Agent scrapes, creates & posts VIRAL content 24/7. 📊 Tracks VIRAL patterns + trends 🎯 Adapts tone: Professional LinkedIn post→ Casual TikTok video 🖼️ Creates scroll-stopping visuals ⏰ Posts when your audience is most active (not when convenient) 📁 Saves everything (agencies charge extra for this) You can build this in a weekend and watch it run your content strategy on autopilot. Follow + Like + Comment “Marketing” & I’ll send it over... (must be following so I can DM). PS: Get this setup before your next agency invoice arrives or keep playing social media manager forever.

TIRED of posting the same BORING content across 5 platforms? Or watching agencies BURN $2500 a month on posts that get 6 likes? This AI Agent scrapes, creates & posts VIRAL content 24/7. 📊 Tracks VIRAL patterns + trends 🎯 Adapts tone: Professional LinkedIn post→ Casual TikTok video 🖼️ Creates scroll-stopping visuals ⏰ Posts when your audience is most active (not when convenient) 📁 Saves everything (agencies charge extra for this) You can build this in a weekend and watch it run your content strategy on autopilot. Follow + Like + Comment “Marketing” & I’ll send it over... (must be following so I can DM). PS: Get this setup before your next agency invoice arrives or keep playing social media manager forever.

Damian Player

69,554 views • 1 year ago

Parsing documents with AI agents just got a lot more seamless🚀 We've rebuilt the LlamaParse MCP server to handle your document processing workflows, and you can connect it today to any MCP-compatible client at 🌐 Once connected, you'll be able to: 📁 Parse documents into clean markdown 🔍 Classify files against your own categories ✂️ Split long documents into labelled sections ⬆️ Upload files via URL or a browser-based upload flow Building a production MCP server surfaced some non-obvious challenges: getting auth to align with an existing platform identity system using WorkOS, working around MCP's lack of built-in file upload support, and making deployments, rate limiting and observability feel native with Vercel and . We wrote up all of it, from the OAuth flow, to the token-based upload design, to the tradeoffs we hit along the way📝 📚 Read the full blog: 👩‍💻 GitHub repository:

Parsing documents with AI agents just got a lot more seamless🚀 We've rebuilt the LlamaParse MCP server to handle your document processing workflows, and you can connect it today to any MCP-compatible client at 🌐 Once connected, you'll be able to: 📁 Parse documents into clean markdown 🔍 Classify files against your own categories ✂️ Split long documents into labelled sections ⬆️ Upload files via URL or a browser-based upload flow Building a production MCP server surfaced some non-obvious challenges: getting auth to align with an existing platform identity system using WorkOS, working around MCP's lack of built-in file upload support, and making deployments, rate limiting and observability feel native with Vercel and . We wrote up all of it, from the OAuth flow, to the token-based upload design, to the tradeoffs we hit along the way📝 📚 Read the full blog: 👩‍💻 GitHub repository:

LlamaIndex 🦙

19,906 views • 4 months ago

THE GHOSTS ARRIVE SEPTEMBER 28 👻 ▶️ WL: 0.015 ETH ▶️ PUBLIC: 0.02 ETH ▶️ CHAIN: Robinhood Crypto L2 👀 REMEMBER THIS: A Cifer Ghost is not just a collectible. It is your access key to a level of privacy no other Web3 ecosystem brings together in one place. With a Ghost, you will be able to: 💬 Send and receive private messages that only you and the intended recipient can decrypt 📁 Encrypt files directly from your computer or compatible cloud services, including Google Drive and Box 📧 Send and receive encrypted emails that only you and the intended recipient can decrypt 🌐 Use a private proxy designed to keep your browsing activity and connection hidden 💸 Receive crypto payments without publicly exposing your wallet address or creating an easy trail to track 📱 Use the Cifer mobile application to capture, encrypt and protect private content 🎁 Access the Cifer affiliate program and earn additional rewards 👻 Breed your Ghost NFTs and produce new Fantoms And you always remain in control of your NFT. Use it. Resell it. Or deposit it into the liquidity pool for another user to buy when they need access to the Cifer ecosystem. The mint is approaching.

THE GHOSTS ARRIVE SEPTEMBER 28 👻 ▶️ WL: 0.015 ETH ▶️ PUBLIC: 0.02 ETH ▶️ CHAIN: Robinhood Crypto L2 👀 REMEMBER THIS: A Cifer Ghost is not just a collectible. It is your access key to a level of privacy no other Web3 ecosystem brings together in one place. With a Ghost, you will be able to: 💬 Send and receive private messages that only you and the intended recipient can decrypt 📁 Encrypt files directly from your computer or compatible cloud services, including Google Drive and Box 📧 Send and receive encrypted emails that only you and the intended recipient can decrypt 🌐 Use a private proxy designed to keep your browsing activity and connection hidden 💸 Receive crypto payments without publicly exposing your wallet address or creating an easy trail to track 📱 Use the Cifer mobile application to capture, encrypt and protect private content 🎁 Access the Cifer affiliate program and earn additional rewards 👻 Breed your Ghost NFTs and produce new Fantoms And you always remain in control of your NFT. Use it. Resell it. Or deposit it into the liquidity pool for another user to buy when they need access to the Cifer ecosystem. The mint is approaching.

CIFER 👻

117,958 views • 4 days ago

is live on the Solana dApp Store. Your Solana Seeker is now a 3D agent studio. MAKE SOMETHING IN 3D A selfie becomes a rigged, textured, animation-ready character in about a minute. Or describe it in text. Or turn any photo into a model. Or upload a GLB you already have. Then restyle its materials, change its clothes, check its rig and fix it. MAKE IT MOVE A clip library that retargets onto any humanoid skeleton. Mocap from your camera. Lipsync from text or a live mic. Gestures. Sign language. A choreographer for full routines. And motion swap, which drops your avatar into video you already shot. GIVE IT A MIND A personality, a voice, skills, and a choice of models behind it. Then talk to it. It answers in 3D, out loud or in text, in your language. PUT IT ANYWHERE Every agent has a URL and a one-line embed, so it drops into a site, a chat, or a widget. Place it in your room in AR. Walk it across any web page. Turn a URL into a 3D world it can stand in. Render it out as video. OWN IT Deploy it on-chain as a Metaplex Core asset your wallet holds. Open manifest, no lock-in. Give it an on-chain identity, a name, and a wallet with recovery and inheritance. Sell its skills. Take tips. Trade the agent itself in USDC. LET IT EARN Pay-per-call, so other agents can buy what yours does and yours can buy what it needs. A skills marketplace, a labor market, vaults that let people back an agent, and a live feed of agents paying each other. Launch a coin around it if you want one. FIND EVERYONE ELSE A marketplace of what the community built: orbit any agent, inspect it, fork it, talk to it. Crews, rankings, tournaments, leaderboards. And build on it: SDKs, an MCP server, a CLI, an API, and the whole platform open source. AND THE PART THAT NEEDED THIS PHONE Every signature routes to Seed Vault through Mobile Wallet Adapter. Signing in is one tap, and the private key never enters the app process. Creating, chatting and browsing are free. Search in the dApp Store on your Seeker.

three.ws

11,659 views • 14 days 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

$This is running in a browser tab. No engine. No install. No download. Six spells, real-time particle simulation, refracting ice geometry, and a live VFX editor on the right side where every parameter is tunable while the scene runs. A studio VFX artist builds this in weeks. It is genuinely the hardest discipline in 3D - nothing about particle work is intuitive. The thing that changed is not that AI got better at art. It is that Astra writes geometry and shaders as CODE instead of as files. A game made of .fbx files is a game an AI can only rearrange. A game made of code is a game an AI can edit. That is why the good demos this week are all three.js and Blender-scripted, and why they run at 60fps in a tab. Dude built a full game this way and it came out under 2 MB before audio. Every rock, tree and character - procedural code, not assets. The cost consequence is the part almost nobody understood: → let the model CLICK in Blender: burns your weekly cap in two minutes → let the model WRITE Blender Python: ~100x cheaper One builder shipped a complete 3D roguelike level - day/night cycle, weather, modeling, texturing, enemies - for 3% of his quota. That is the entire reason why. Scripts, not clicks. It's the single rule that decides your bill. Full breakdown + the 7-day guide in the article below ↓$

This is running in a browser tab. No engine. No install. No download. Six spells, real-time particle simulation, refracting ice geometry, and a live VFX editor on the right side where every parameter is tunable while the scene runs. A studio VFX artist builds this in weeks. It is genuinely the hardest discipline in 3D - nothing about particle work is intuitive. The thing that changed is not that AI got better at art. It is that Astra writes geometry and shaders as CODE instead of as files. A game made of .fbx files is a game an AI can only rearrange. A game made of code is a game an AI can edit. That is why the good demos this week are all three.js and Blender-scripted, and why they run at 60fps in a tab. Dude built a full game this way and it came out under 2 MB before audio. Every rock, tree and character - procedural code, not assets. The cost consequence is the part almost nobody understood: → let the model CLICK in Blender: burns your weekly cap in two minutes → let the model WRITE Blender Python: ~100x cheaper One builder shipped a complete 3D roguelike level - day/night cycle, weather, modeling, texturing, enemies - for 3% of his quota. That is the entire reason why. Scripts, not clicks. It's the single rule that decides your bill. Full breakdown + the 7-day guide in the article below ↓

Aleiah

41,744 views • 19 days ago

Google's new laptop category Googlebook running Googlebook OS which mixes the best of ChromeOS and Android, built fully around Gemini AI. starts at 💰 $899. 🖥️ up to 2.8K OLED touchscreens, haptic glass trackpads, backlit keyboards 🔩 premium materials: aluminum, magnesium alloy and carbon fiber ⚡ Intel and Qualcomm chips with 45+ TOPS NPUs, up to 14 hours battery 💡 Glowbar is back: lights up at startup, shows battery level, animates when you talk to Gemini 🤝 made by Acer, Asus, Dell, HP and Lenovo works with your Android phone out of the box: 🔐 sign in and your settings, passwords, Wi-Fi and messages move with you (end-to-end encrypted) ▶️ Continue On: pick up exactly where you left off on your phone, right from the taskbar 📁 Files: view, search and open your phone's files and photos on the laptop 📲 Cast My Apps: stream and use your phone's apps in a desktop window Gemini stuff built in: ✨ Magic Pointer: shake your cursor and Gemini works on whatever's on your screen 🗣️ Rambler: talk through your thoughts and it turns them into clean, structured writing 🧩 Create My Widget: describe what you need and it builds a custom desktop widget apps and extras: 🌐 full Chrome browser with extensions + millions of Android apps 🎬 Photoshop, Lightroom, CapCut, Netflix and HBO Max with offline viewing 🎮 1 year of GeForce NOW free with every purchase 🛠️ Antigravity AI dev platform + full Linux terminal for developers 🔒 Google Titan security, Level 5 certified hypervisor, updates for up to 10 years every Googlebook includes 12 months of Google AI Pro (5TB storage + Gemini Advanced), 3 months of YouTube Premium, Adobe Photoshop and more. pre-orders open now on Google Store, Best Buy and select retailers. on shelves October 4 in the US, October 5 in Canada, UK, Ireland, France, Germany and Australia. #Googlebook

Google's new laptop category Googlebook running Googlebook OS which mixes the best of ChromeOS and Android, built fully around Gemini AI. starts at 💰 $899. 🖥️ up to 2.8K OLED touchscreens, haptic glass trackpads, backlit keyboards 🔩 premium materials: aluminum, magnesium alloy and carbon fiber ⚡ Intel and Qualcomm chips with 45+ TOPS NPUs, up to 14 hours battery 💡 Glowbar is back: lights up at startup, shows battery level, animates when you talk to Gemini 🤝 made by Acer, Asus, Dell, HP and Lenovo works with your Android phone out of the box: 🔐 sign in and your settings, passwords, Wi-Fi and messages move with you (end-to-end encrypted) ▶️ Continue On: pick up exactly where you left off on your phone, right from the taskbar 📁 Files: view, search and open your phone's files and photos on the laptop 📲 Cast My Apps: stream and use your phone's apps in a desktop window Gemini stuff built in: ✨ Magic Pointer: shake your cursor and Gemini works on whatever's on your screen 🗣️ Rambler: talk through your thoughts and it turns them into clean, structured writing 🧩 Create My Widget: describe what you need and it builds a custom desktop widget apps and extras: 🌐 full Chrome browser with extensions + millions of Android apps 🎬 Photoshop, Lightroom, CapCut, Netflix and HBO Max with offline viewing 🎮 1 year of GeForce NOW free with every purchase 🛠️ Antigravity AI dev platform + full Linux terminal for developers 🔒 Google Titan security, Level 5 certified hypervisor, updates for up to 10 years every Googlebook includes 12 months of Google AI Pro (5TB storage + Gemini Advanced), 3 months of YouTube Premium, Adobe Photoshop and more. pre-orders open now on Google Store, Best Buy and select retailers. on shelves October 4 in the US, October 5 in Canada, UK, Ireland, France, Germany and Australia. #Googlebook

Abhishek Yadav

19,376 views • 4 days ago

It's time to #getInspir3d. Many loyalty programs lock users to closed ecosystems that often fail to provide meaningful value. Leveraging Multiversᕽ technology, Inspir3 introduces Loyalty 3.0: a unified program through which consumers get discounts, cash backs and exclusive perks from their favorite brands. 🌊 INNOVATION Users will be able to claim daily rewards from one brand and spend them with another. Yesterday's shopping spree will fuel the car today. 🤝 TRADING With Inspir3, users can trade rewards they don't need for ones they do, making every benefit they receive meaningful. 📁 DATA It's more than convenience; it's about empowerment. Our integration of the Itheum protocol puts users in control of their own data. 🌐 COMMUNITY We've built Inspir3 as a truly community-centric product. Every consumer that joins Inspir3 will need a referral link. That's why we've created a powerful referral system that will benefit our holders and reward them for their early-stage involvement. With all these points in mind, know that Inspir3 is more than an app; it's a natural evolution of the traditional loyalty programs. A solution designed to answer real consumer needs. And no, that's not all. We're just getting started. Follow us to learn more and interact with this post to be considered for whitelist. T-30.

Inspir3

141,491 views • 2 years ago