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.

v0.2.0 for Three.js Awesome Graphics Agent Skills is out npx threejs-awesome-graphics-agent-skills@latest install --agent codex I added 5 more examples based on 5 open source projects i saw on X with awesome graphics: - Sabo Sugi / Three.js & Shaders lava planet surface - André → andreelias.dev stylized grass -... show more

Scott

3,166 subscribers

27,545 views • 2 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

14 Comments

Scott2 months ago

repo here for example gallery inspection

Nick Venturi2 months ago

@threejs @sabosugi @andreeliasdev about to run this and pretend i spent weeks on it

Gioele Dalla Pozza2 months ago

@threejs @sabosugi @andreeliasdev Honored to be featured alongside such amazing creators! Thanks for including my stylized ocean, @scottstts. Keep pushing the Three.js ecosystem forward! 🌊🤝

meguna2 months ago

@threejs @sabosugi @andreeliasdev Thank you

AINZX2 months ago

@threejs @sabosugi @andreeliasdev Are we going to see tron legacy movie from world

Vasily One2 months ago

@threejs @sabosugi @andreeliasdev This MUST be bookmarked. Thanks for sharing!

Chubigans2 months ago

hot take why are we doing all this work on threejs instead of godot... threejs doesnt have an actual game engine, you cant port it to consoles (though prob barely to desktop is possible). it's such a wasted effort for games... godot is the open source solution for gamedev, so lets work on building toolchains for that

Scott2 months ago

@threejs @sabosugi @andreeliasdev Threejs is web native, web is the best way to share and collaborate. Threejs can achieve AAA graphics, it’s been done. You’re right there’s no game engine built for native web, hoping someone will build it

Chubigans2 months ago

@threejs @sabosugi @andreeliasdev yeah but are gamers really going to switch to web?

Scott2 months ago

If you build a good game, people will come. And because it’s on web, there’s zero entry friction for players. The problem is lack of good games, and the reason behind that is most people who make good games are used to game engine platforms. That’s why we need a game engine on web or some web native game frameworks that work in conjunction with threejs Anyway still early days, anything can happen

Chubigans2 months ago

@threejs @sabosugi @andreeliasdev Seems to me the problem is lack of portability to consoles. I’m a huge web tech fan (10 years in the js ecosystem) but when I decided to make my game the first thing on my mind was portability and integration to steam and consoles

AI Mastery Guide2 months ago

@threejs @sabosugi @andreeliasdev That lava planet render looks way too good for something built from open source examples.

AiDevCraft2 months ago

@threejs @sabosugi @andreeliasdev The npx-skills pattern keeps quietly winning because devs would rather install a few hundred lines than register an MCP server. Visual domains are also a gift for skill libraries: broken shaders fail loudly in pixels, which text-only agents never get for free in eval.

mobx.games2 months ago

@threejs @sabosugi @andreeliasdev This is amazing! Thanks for sharing!

Related Videos

Introducing Threejs Awesome Graphics Agent Skills npx threejs-awesome-graphics-agent-skills install --agent codex I collected some of the best looking graphic Three.js open source projects on X and distilled them into an agent skills pack, AAA game graphics right out of the box so anyone can create games that don't look like cheap demos These are just examples included in the agent skills. All projects referenced are noted as source materials. I will continuously update this to include new projects with epic graphics

Introducing Threejs Awesome Graphics Agent Skills npx threejs-awesome-graphics-agent-skills install --agent codex I collected some of the best looking graphic Three.js open source projects on X and distilled them into an agent skills pack, AAA game graphics right out of the box so anyone can create games that don't look like cheap demos These are just examples included in the agent skills. All projects referenced are noted as source materials. I will continuously update this to include new projects with epic graphics

Scott

37,901 views • 3 months ago

$I am having a lot of fun with this ThreeJS game. Will probably be spending more time on this cosy flyer game for #vibejam And btw, shaders are awesome! I highly recommend anyone building a 3D game to add some shaders to make your game look good. Here's a quick primer on the different types of shaders you can tell your AI to level up your game's graphics: - Noise-based shader for water refractions or shimmer - Fresnel shader for a nice rim lighting effect on your 3D game objects - Post-processing shader to change your game's color scheme dynamically - Post-processing shaders like the VHS effect that @levelsio use for the Drone flyer game - Shader effect to make the trees sway or objects wobble - and many more uses Shaders are incredibly versatile and useful. I would recommend you to go YT to check out some shader basics videos and come up with more creative uses for them!$

I am having a lot of fun with this ThreeJS game. Will probably be spending more time on this cosy flyer game for #vibejam And btw, shaders are awesome! I highly recommend anyone building a 3D game to add some shaders to make your game look good. Here's a quick primer on the different types of shaders you can tell your AI to level up your game's graphics: - Noise-based shader for water refractions or shimmer - Fresnel shader for a nice rim lighting effect on your 3D game objects - Post-processing shader to change your game's color scheme dynamically - Post-processing shaders like the VHS effect that @levelsio use for the Drone flyer game - Shader effect to make the trees sway or objects wobble - and many more uses Shaders are incredibly versatile and useful. I would recommend you to go YT to check out some shader basics videos and come up with more creative uses for them!

Danny Limanseta

203,685 views • 5 months ago

This little device lets your agents do what they do best, whilst making sure you approve every important action. This is a Ledger Nano Gen5, a hardware signer that keeps your accounts secure. You can install a CLI and a set of skills in your projects. These will enable your agents to send their plan to the signer, so you can approve it. This is awesome: 1. You can have an automated agentic workflow 2. Your agents can't make costly mistakes Check the video I recorded to see how this works. You can run all of this in two commands: 1. Install the CLI 2. Install the skills for your agent From here, the agent can query my Ethereum accounts, check balances, and even initiate transactions as long as my Ledger Nano Gen5 is plugged into the computer. My keys are never stored in my computer and never shared with the agent. This is huge! Also, while the agent can set up transactions, it can't execute them unless a human approves them using the device. Pretty awesome! Thanks to the Ledger team for partnering with me on this post.

This little device lets your agents do what they do best, whilst making sure you approve every important action. This is a Ledger Nano Gen5, a hardware signer that keeps your accounts secure. You can install a CLI and a set of skills in your projects. These will enable your agents to send their plan to the signer, so you can approve it. This is awesome: 1. You can have an automated agentic workflow 2. Your agents can't make costly mistakes Check the video I recorded to see how this works. You can run all of this in two commands: 1. Install the CLI 2. Install the skills for your agent From here, the agent can query my Ethereum accounts, check balances, and even initiate transactions as long as my Ledger Nano Gen5 is plugged into the computer. My keys are never stored in my computer and never shared with the agent. This is huge! Also, while the agent can set up transactions, it can't execute them unless a human approves them using the device. Pretty awesome! Thanks to the Ledger team for partnering with me on this post.

Santiago

44,296 views • 3 months ago

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!

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 🚀

87,048 views • 4 months ago

NVIDIA just released a repo that scans AI agent skills for security risks BEFORE you run them, which matters more than people realize now that everyone's installing random tools, skills, and MCPs from GitHub. I break down that one AND 4 other GitHub repos trending over the last 30 days in this episode of The Startup Ideas Podcast (SIP) 🧃: 1. A skill that kills AI slop finally (better writing) 2. A CRM thats built for AI agents (so you can have agents follow up, reach out etc) 3. An agent that edits your videos for you (so you can focus on creative) 4. An opensource CapCut alternative built for agents (because editing is a headache) All free, all open source. Watch my breakdown of the 5 GitHub repos trending over the last 30 days below The tools people will be talking about in six months are on GitHub today. That's the fun part of digging through GitHub right now.

NVIDIA just released a repo that scans AI agent skills for security risks BEFORE you run them, which matters more than people realize now that everyone's installing random tools, skills, and MCPs from GitHub. I break down that one AND 4 other GitHub repos trending over the last 30 days in this episode of The Startup Ideas Podcast (SIP) 🧃: 1. A skill that kills AI slop finally (better writing) 2. A CRM thats built for AI agents (so you can have agents follow up, reach out etc) 3. An agent that edits your videos for you (so you can focus on creative) 4. An opensource CapCut alternative built for agents (because editing is a headache) All free, all open source. Watch my breakdown of the 5 GitHub repos trending over the last 30 days below The tools people will be talking about in six months are on GitHub today. That's the fun part of digging through GitHub right now.

GREG ISENBERG

54,582 views • 21 days ago

Send this to ANYONE on your team using AI agents with Claude/Codex skills: If I were you, I'd put your BEST AI skills in a GitHub repo, turn that repo into a PLUGIN, and have your team INSTALL it in Claude/Codex with auto update on. Why? 1. Everyone gets the same AI SOPs instead of 10 versions floating around Slack 2. When one person improves a skill, the whole team gets the better version. 3. New hires can start with your best workflows instead of a blank AI setup (this is a BIG deal). 4. If someone breaks a skill, you can roll it back with version control. 5. Personal skills can stay personal, while team skills become shared company infrastructure (and an asset!). 6. Your best AI processes stay with the company when someone leaves. 7. You can chain skills together for bigger workflows, like titles -> thumbnails -> descriptions -> YouTube publish. 8. You can track which skills are actually being used and delete the ones collecting dust. 9. You get less slop because the agent has real instructions, examples, taste, and process. 10. Your team moves from single-player AI to multiplayer AI. (thanks to AI with Remy | Learn AI for coming onto The Startup Ideas Podcast (SIP) 🧃) Watch full breakdown here (clearly explained): I don't know why I didn't do this before. The more I think about it, the more obvious it feels: your AI workflows should be version controlled company assets. It kinda feels like the difference between “we use AI” and “we actually operate with AI". Enjoy.

Send this to ANYONE on your team using AI agents with Claude/Codex skills: If I were you, I'd put your BEST AI skills in a GitHub repo, turn that repo into a PLUGIN, and have your team INSTALL it in Claude/Codex with auto update on. Why? 1. Everyone gets the same AI SOPs instead of 10 versions floating around Slack 2. When one person improves a skill, the whole team gets the better version. 3. New hires can start with your best workflows instead of a blank AI setup (this is a BIG deal). 4. If someone breaks a skill, you can roll it back with version control. 5. Personal skills can stay personal, while team skills become shared company infrastructure (and an asset!). 6. Your best AI processes stay with the company when someone leaves. 7. You can chain skills together for bigger workflows, like titles -> thumbnails -> descriptions -> YouTube publish. 8. You can track which skills are actually being used and delete the ones collecting dust. 9. You get less slop because the agent has real instructions, examples, taste, and process. 10. Your team moves from single-player AI to multiplayer AI. (thanks to AI with Remy | Learn AI for coming onto The Startup Ideas Podcast (SIP) 🧃) Watch full breakdown here (clearly explained): I don't know why I didn't do this before. The more I think about it, the more obvious it feels: your AI workflows should be version controlled company assets. It kinda feels like the difference between “we use AI” and “we actually operate with AI". Enjoy.

GREG ISENBERG

79,850 views • 1 month ago

A really impressive set of Three.js graphics experiments just got open sourced, and these are much more than little visual demos. They are basically reusable procedural systems for oceans, vegetation, fluids and even whole planets. 🔹 Poseidon A real-time FFT ocean running on WebGPU. It simulates large swells, smaller ripples, foam, reflections, choppy displacement and physically inspired wave spectra entirely in the browser. 🔹 Gaia A procedural grass generator where every blade, seed head and field comes from a deterministic genome and environmental parameters. No authored grass models. 🔹 Dryad A procedural flora system that generates trees and other plant forms from physics, environmental conditions and a seed. No authored 3D models or textures are needed for the plants themselves. 🔹 Tiamat A real-time GPU fluid simulation using around 100,000 SPH particles, with the resulting water rendered directly in the browser. 🔹 Demiurge Probably the craziest one. It procedurally builds an entire planet from tectonic plates, then lets uplift drive erosion, erosion and latitude drive climate, and climate drive biomes, wind and weather. You can move seamlessly from orbit down to the surface. What I really like here is that these are not just pretty outputs. They are actual building blocks. Ocean simulation, vegetation generation, fluid dynamics and procedural worlds are exactly the kinds of systems that can be plugged into games, simulations and agent-built 3D environments. Project by: Owen

A really impressive set of Three.js graphics experiments just got open sourced, and these are much more than little visual demos. They are basically reusable procedural systems for oceans, vegetation, fluids and even whole planets. 🔹 Poseidon A real-time FFT ocean running on WebGPU. It simulates large swells, smaller ripples, foam, reflections, choppy displacement and physically inspired wave spectra entirely in the browser. 🔹 Gaia A procedural grass generator where every blade, seed head and field comes from a deterministic genome and environmental parameters. No authored grass models. 🔹 Dryad A procedural flora system that generates trees and other plant forms from physics, environmental conditions and a seed. No authored 3D models or textures are needed for the plants themselves. 🔹 Tiamat A real-time GPU fluid simulation using around 100,000 SPH particles, with the resulting water rendered directly in the browser. 🔹 Demiurge Probably the craziest one. It procedurally builds an entire planet from tectonic plates, then lets uplift drive erosion, erosion and latitude drive climate, and climate drive biomes, wind and weather. You can move seamlessly from orbit down to the surface. What I really like here is that these are not just pretty outputs. They are actual building blocks. Ocean simulation, vegetation generation, fluid dynamics and procedural worlds are exactly the kinds of systems that can be plugged into games, simulations and agent-built 3D environments. Project by: Owen

Token Gremlin

34,448 views • 1 month ago

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:

Three skills I use every day in Claude Code and Codex to solve my hardest problems: 1️⃣ /agent-watchdog When I have one agent like Codex working on a task and I don't fully trust it's going to do everything right, I'll open up another one like Claude Code and tell it to watchdog the Codex thread. You can copy the Codex deep link into Claude Code and it'll look at the prompt you sent, watch the Codex thread until it's done, then compare the Codex solution to how it was planning to solve it and automatically fix anything that Codex missed. It can also test the work of the other agent end-to-end. Similar to the idea of OpenRouter's new Fusion feature, I've definitely found that two models thinking through a problem and checking each other's work can be wildly more impactful than just one. 2️⃣ /plan-arbiter Similar ideas as /agent-watchdog - but with this one you have both make plans, compare plans, negotiate the differences, and make a final plan to execute. I find Claude Code is better at writing plans, but Codex is faster and cheaper to execute on them. Then I usually have Claude Code watchdog the Codex work and fix anything that was missed. 3️⃣ /read-the-damn-docs One thing that drives me crazy with coding agents is they're so reluctant to look up docs. They'll just guess and guess and guess at the right API surface for things, or the right solution to an integration of two things. Once I explicitly tell it to look up the docs, it says "Oh, I see the answer," and it fixes the problem. So I made the /read-the-damn-docs skill. Add it and your agents will know when and how to do efficient web searches to look up docs for the types of problems you really should look up docs for. All of these are totally open source over on my GitHub. If you try them, let me know your feedback. Will link to them below:

Steve (Builder.io)

43,089 views • 3 months ago

20 GitHub repos with 2.4M+ combined stars that replace tools costing $60,000+/year 1. public-apis ⭐456k - 1,500+ free APIs across every category, weather to finance to games, all documented. 2. awesome-selfhosted ⭐312k - self-hosted replacements for Notion, Google Photos, Zapier, and dozens more paid subscriptions. 3. hermes-agent ⭐230k - self-improving personal agent with persistent memory, cron scheduling, MCP built in. Free alternative to paid always-on agent platforms. 4. n8n ⭐200k - visual automation with native AI agents. Replaces Zapier/Make entirely, self-hosted. 5. ollama ⭐178k - run Llama, Mistral, DeepSeek locally with one command. No API bill, no rate limits. 6. dify ⭐152k - visual builder for AI agents and RAG pipelines. Skip the $500/mo no-code AI builder subscription. 7. free-for-dev ⭐132k - hundreds of services with permanent free tiers. No trials, no credit card. 8. awesome-llm-apps ⭐132k - 100+ ready AI agents and RAG apps with full code. 9. awesome-mcp-servers ⭐92k - thousands of MCP servers connecting your agent to browsers, databases, anything. 10. supabase ⭐108k - Firebase alternative that's actually free to start. Auth, DB, storage in one Claude Code prompt. 11. strapi ⭐73k - open-source headless CMS, generates a full API from your content model in minutes. No Contentful bill. 12. immich ⭐110k - self-hosted photo and video backup with face recognition. Cancel the Google Photos storage plan. 13. appwrite ⭐57k - complete backend-as-a-service, self-hosted. Auth, DB, functions, storage, one prompt away from Firebase money. 14. medusa ⭐36k - full ecommerce backend, open source. Skip Shopify Plus fees entirely on your next vibe-coded store. 15. novu ⭐39k - notification infrastructure for email, SMS, push, in-app, all in one API. Replaces OneSignal's paid tiers. 16. tooljet ⭐38k - drag-and-drop internal tool builder connected to any database or API. Retool's seat pricing gone. 17. mattermost ⭐38k - self-hosted team chat built for engineering orgs. Slack without the per-seat bill. 18. outline ⭐40k - fast, clean team wiki and docs. Replaces Confluence and Notion's team plan. 19. plausible ⭐28.5k - privacy-friendly analytics, lightweight script, real dashboards. No GA360 contract needed. 20. openwork ⭐22k - open-source Claude Cowork alternative. Share skills and MCPs across Claude Code, Cursor, Codex, one setup for every agent. Save this before you pay for another tool this list already replaces for free 👇

20 GitHub repos with 2.4M+ combined stars that replace tools costing $60,000+/year 1. public-apis ⭐456k - 1,500+ free APIs across every category, weather to finance to games, all documented. 2. awesome-selfhosted ⭐312k - self-hosted replacements for Notion, Google Photos, Zapier, and dozens more paid subscriptions. 3. hermes-agent ⭐230k - self-improving personal agent with persistent memory, cron scheduling, MCP built in. Free alternative to paid always-on agent platforms. 4. n8n ⭐200k - visual automation with native AI agents. Replaces Zapier/Make entirely, self-hosted. 5. ollama ⭐178k - run Llama, Mistral, DeepSeek locally with one command. No API bill, no rate limits. 6. dify ⭐152k - visual builder for AI agents and RAG pipelines. Skip the $500/mo no-code AI builder subscription. 7. free-for-dev ⭐132k - hundreds of services with permanent free tiers. No trials, no credit card. 8. awesome-llm-apps ⭐132k - 100+ ready AI agents and RAG apps with full code. 9. awesome-mcp-servers ⭐92k - thousands of MCP servers connecting your agent to browsers, databases, anything. 10. supabase ⭐108k - Firebase alternative that's actually free to start. Auth, DB, storage in one Claude Code prompt. 11. strapi ⭐73k - open-source headless CMS, generates a full API from your content model in minutes. No Contentful bill. 12. immich ⭐110k - self-hosted photo and video backup with face recognition. Cancel the Google Photos storage plan. 13. appwrite ⭐57k - complete backend-as-a-service, self-hosted. Auth, DB, functions, storage, one prompt away from Firebase money. 14. medusa ⭐36k - full ecommerce backend, open source. Skip Shopify Plus fees entirely on your next vibe-coded store. 15. novu ⭐39k - notification infrastructure for email, SMS, push, in-app, all in one API. Replaces OneSignal's paid tiers. 16. tooljet ⭐38k - drag-and-drop internal tool builder connected to any database or API. Retool's seat pricing gone. 17. mattermost ⭐38k - self-hosted team chat built for engineering orgs. Slack without the per-seat bill. 18. outline ⭐40k - fast, clean team wiki and docs. Replaces Confluence and Notion's team plan. 19. plausible ⭐28.5k - privacy-friendly analytics, lightweight script, real dashboards. No GA360 contract needed. 20. openwork ⭐22k - open-source Claude Cowork alternative. Share skills and MCPs across Claude Code, Cursor, Codex, one setup for every agent. Save this before you pay for another tool this list already replaces for free 👇

unicode

34,424 views • 1 month ago

I built a Three.js rendering study inspired by Tiny Glade’s painterly aesthetic, and got it running at 120fps in the browser. Over the past few weeks, I’ve been studying how stylized games achieve that soft, handcrafted look in real time. Tiny Glade was a huge inspiration, and I wanted to use the browser as a constraint: no compute shaders, no native GPU access, and single-threaded JavaScript. As part of this study, I implemented: - GPU-driven instanced brick walls with procedural noise jitter and elastic build animations - Tree, bush, and flower rendering with billboard card expansion, wind sway, and grow animations - Procedural grass with terrain conformance and interactive push deformation - Animated water with layered noise, interactive ripples, and Fresnel-based reflections - Procedural terrain with slope-aware triplanar materials, dirt paths, and rocks - A 7-pass post-processing stack with TAA, bloom, depth of field, painterly filtering, ACES tonemapping, 3D LUT color grading, and film grain The hardest part wasn’t writing any single shader. It was making all of these systems work together at high frame rates inside WebGL, where every millisecond counts and performance problems compound quickly across animation, materials, post-processing, and scene management. Some techniques in this study were inspired by analyzing Tiny Glade’s rendering approach, while others were original implementations built from scratch from visual reference. That contrast taught me a lot: recreating an effect is one challenge, but designing your own shaders and systems to achieve a similar feel is a very different one. This is a private educational rendering study. Some temporary placeholder content is being used during the research phase, and any public or production version would use original or properly licensed assets. Huge credit to Pounce Light for the incredible art direction and rendering work in Tiny Glade: Three.js #gamedev #webgl #threejs #rendering #graphics #realtimerendering #shaderdev

I built a Three.js rendering study inspired by Tiny Glade’s painterly aesthetic, and got it running at 120fps in the browser. Over the past few weeks, I’ve been studying how stylized games achieve that soft, handcrafted look in real time. Tiny Glade was a huge inspiration, and I wanted to use the browser as a constraint: no compute shaders, no native GPU access, and single-threaded JavaScript. As part of this study, I implemented: - GPU-driven instanced brick walls with procedural noise jitter and elastic build animations - Tree, bush, and flower rendering with billboard card expansion, wind sway, and grow animations - Procedural grass with terrain conformance and interactive push deformation - Animated water with layered noise, interactive ripples, and Fresnel-based reflections - Procedural terrain with slope-aware triplanar materials, dirt paths, and rocks - A 7-pass post-processing stack with TAA, bloom, depth of field, painterly filtering, ACES tonemapping, 3D LUT color grading, and film grain The hardest part wasn’t writing any single shader. It was making all of these systems work together at high frame rates inside WebGL, where every millisecond counts and performance problems compound quickly across animation, materials, post-processing, and scene management. Some techniques in this study were inspired by analyzing Tiny Glade’s rendering approach, while others were original implementations built from scratch from visual reference. That contrast taught me a lot: recreating an effect is one challenge, but designing your own shaders and systems to achieve a similar feel is a very different one. This is a private educational rendering study. Some temporary placeholder content is being used during the research phase, and any public or production version would use original or properly licensed assets. Huge credit to Pounce Light for the incredible art direction and rendering work in Tiny Glade: Three.js #gamedev #webgl #threejs #rendering #graphics #realtimerendering #shaderdev

Ibrahim Boona

58,625 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

how to set up hermes agent step by step. built-in memory, 40+ tools, works on your phone, and what to think of hermes vs openclaw: 1. hermes is a personal AI agent that runs in your terminal. think of it like open claw but with built-in memory, 40+ tools out of the box, and 90% cheaper token costs. you install it with one command. 2. the 3 problems with open claw that hermes solves: no memory (you keep repeating yourself), constant gateway restarts, and zero visibility into what you're spending on tokens. 3. hermes remembers everything. every completed task gets saved to memory. it searches through past logs to find solutions. over time it literally gets smarter at your specific workflows. 4. connect it to open router. you see exact costs per model per task. free models rotate weekly. one founder went from $130 every five days on open claw to $10 on hermes. same output. 5. it comes preloaded with skills. apple notes, imessage, find my, browser, web search, image generation, cron jobs. no hunting for plugins. 6. connect it to obsidian so it reads your entire vault. connect it to gstack for your dev environment. create custom skills for your specific workflows. 7. the biggest money saver: have it write code once for recurring tasks. then it runs without burning tokens every time. stop paying an LLM to do the same scrape or report daily. 8. run it on android via telegram. name your agents. talk to them like coworkers. in this episode imran shows you how to set this up. 9. you can run it bare metal, in docker, or serverless on modal. pick your risk level. i begged imran to come on The Startup Ideas Podcast (SIP) 🧃 and walk through the full installation live. he made it impossibly clear. if you've heard of Hermes Agent and want the clearest explanation of how to get set up like a pro let me know what you want me to cover on the next ep this is the best personal agent setup video on the internet right now. watch

how to set up hermes agent step by step. built-in memory, 40+ tools, works on your phone, and what to think of hermes vs openclaw: 1. hermes is a personal AI agent that runs in your terminal. think of it like open claw but with built-in memory, 40+ tools out of the box, and 90% cheaper token costs. you install it with one command. 2. the 3 problems with open claw that hermes solves: no memory (you keep repeating yourself), constant gateway restarts, and zero visibility into what you're spending on tokens. 3. hermes remembers everything. every completed task gets saved to memory. it searches through past logs to find solutions. over time it literally gets smarter at your specific workflows. 4. connect it to open router. you see exact costs per model per task. free models rotate weekly. one founder went from $130 every five days on open claw to $10 on hermes. same output. 5. it comes preloaded with skills. apple notes, imessage, find my, browser, web search, image generation, cron jobs. no hunting for plugins. 6. connect it to obsidian so it reads your entire vault. connect it to gstack for your dev environment. create custom skills for your specific workflows. 7. the biggest money saver: have it write code once for recurring tasks. then it runs without burning tokens every time. stop paying an LLM to do the same scrape or report daily. 8. run it on android via telegram. name your agents. talk to them like coworkers. in this episode imran shows you how to set this up. 9. you can run it bare metal, in docker, or serverless on modal. pick your risk level. i begged imran to come on The Startup Ideas Podcast (SIP) 🧃 and walk through the full installation live. he made it impossibly clear. if you've heard of Hermes Agent and want the clearest explanation of how to get set up like a pro let me know what you want me to cover on the next ep this is the best personal agent setup video on the internet right now. watch

GREG ISENBERG

623,943 views • 5 months ago

Introducing Wikiwise: an open-source Mac app for managing your own Karpathy-style LLM wiki. Set up a new wiki in a few clicks: all you need is Wikiwise + your agent. It's infinitely customizable, just markdown/html under the hood, and one click to share your wiki publicly. Here's how it works: * Install Wikiwise for mac (it's built in Swift so super minimal and performant). In Karpathy's framework, Wikiwise is your IDE. * Start a new Wiki: it generates a new folder on your machine that's scaffolded in the wiki structure Andrej Karpathy describes (index.md, raw folder, wiki folder, CLAUDE.md/AGENTS.md, although it tries to be as un-opinionated as possible). * Then just point your agent (Codex, Claude Code, Cursor, etc) at the folder and tell it what to import -- files on your machine, connect to your Readwise account, or urls from the web. * Your agent creates wthe wiki for you: Your agent will know how to ingest your raw sources (via the AGENTS.md) and will immediately start writing+linking wiki pages for you. * Go crazy on customization! The rendered wiki pages live as static html/css in your folder too so just tell your agent to change stuff, and if you need any more customization Wikiwise is fully open source :) * Ask questions about your research with your agent, ask it to bring in new sources, write new documents, etc. * (optionally) Hit the Publish button to share your wiki with friends/colleagues at a custom URL === I tried to walk the line on a couple constraints with Wikiwise: 1. I wanted it to be easy to spin up new wikis, especially without chaining together a bunch of different apps. It takes me a few minutes to spin up a new wiki on a topic -- I already have five! 2. Infinitely Customizable: one great aspect of building a wiki as Karpathy described is that you can modify any aspect of your wiki with your agent. Every new wiki styling+structure is self-contained in the local folder, which allows you to preserve this. Wikiwise is just an IDE that makes the setup easier and includes a nice un-opinionated starting state. 3. Minimal: Wikiwise is built mostly in Swift, and the DMG you install to download it is only 2.6MB (!) 4. Easy Publishing: my colleague Eleanor Konik has been building her own LLM wikis for months, but has always really struggled to actually share them with her book club. There are tools to do it, but figuring out hosting is always a huge headache. This seemed like an ideal usecase for a tool like Wikiwise to solve. The process of building wikiwise was also pretty interesting -- I "bootstrapped" the app in a way by first building my own wiki based on Karpathy's tweet and other notes I had, and slowly formed the shape of the project in collaboration with my LLM. This was all done in 3 days over the latest Readwise company hackathon we had. Truly an incredible time to be alive. Anyways, curious what you think! Links in next tweet.

Introducing Wikiwise: an open-source Mac app for managing your own Karpathy-style LLM wiki. Set up a new wiki in a few clicks: all you need is Wikiwise + your agent. It's infinitely customizable, just markdown/html under the hood, and one click to share your wiki publicly. Here's how it works: * Install Wikiwise for mac (it's built in Swift so super minimal and performant). In Karpathy's framework, Wikiwise is your IDE. * Start a new Wiki: it generates a new folder on your machine that's scaffolded in the wiki structure Andrej Karpathy describes (index.md, raw folder, wiki folder, CLAUDE.md/AGENTS.md, although it tries to be as un-opinionated as possible). * Then just point your agent (Codex, Claude Code, Cursor, etc) at the folder and tell it what to import -- files on your machine, connect to your Readwise account, or urls from the web. * Your agent creates wthe wiki for you: Your agent will know how to ingest your raw sources (via the AGENTS.md) and will immediately start writing+linking wiki pages for you. * Go crazy on customization! The rendered wiki pages live as static html/css in your folder too so just tell your agent to change stuff, and if you need any more customization Wikiwise is fully open source :) * Ask questions about your research with your agent, ask it to bring in new sources, write new documents, etc. * (optionally) Hit the Publish button to share your wiki with friends/colleagues at a custom URL === I tried to walk the line on a couple constraints with Wikiwise: 1. I wanted it to be easy to spin up new wikis, especially without chaining together a bunch of different apps. It takes me a few minutes to spin up a new wiki on a topic -- I already have five! 2. Infinitely Customizable: one great aspect of building a wiki as Karpathy described is that you can modify any aspect of your wiki with your agent. Every new wiki styling+structure is self-contained in the local folder, which allows you to preserve this. Wikiwise is just an IDE that makes the setup easier and includes a nice un-opinionated starting state. 3. Minimal: Wikiwise is built mostly in Swift, and the DMG you install to download it is only 2.6MB (!) 4. Easy Publishing: my colleague Eleanor Konik has been building her own LLM wikis for months, but has always really struggled to actually share them with her book club. There are tools to do it, but figuring out hosting is always a huge headache. This seemed like an ideal usecase for a tool like Wikiwise to solve. The process of building wikiwise was also pretty interesting -- I "bootstrapped" the app in a way by first building my own wiki based on Karpathy's tweet and other notes I had, and slowly formed the shape of the project in collaboration with my LLM. This was all done in 3 days over the latest Readwise company hackathon we had. Truly an incredible time to be alive. Anyways, curious what you think! Links in next tweet.

Tristan

96,743 views • 5 months ago

I realized that I would probably get more interest in my AI music theory tool (mtdt) and corresponding agent skill library if I did impressive things with more mainstream/popular tunes rather than an obscure Irish folk song from the 18th century like in my quoted post. So this time, I took my 3 favorite tunes from Zelda: Ocarina of Time (i.e., Saria's Song, the Song of Storms, and Zelda's Lullaby) and had them reimagined by the AI agent using my system in the style of various famous classical composers: Schubert, Schumann, Rachmaninoff, and Liszt. I had GPT-6 Astra xhigh acting as the "controller" agent create the prompt and launch another instance of Codex (the "worker" agent) in a fresh workspace with all 322 skills loaded, and then monitor the process. I gave the controller agent only very high-level instructions about which songs from the Zelda game I wanted and which composers to use for which songs. I also told it stuff like: "For actually rendering the written music to audio, we should use the nice concert piano instrument with reverb that came from my jazz chords project originally (see /cass) and we should humanize the playing with a skill so it doesn't sound robotic in tempo and dynamics; it should sound like a professional pianist specializing in the music of the particular composer. And try to do a final critical pass over each piece with fresh eyes looking for any deficiencies and blunders... does it REALLY sound like that composer's work? Can you still hear the original song's essence in the new, reimagined version? Is it good? Does it follow the rules and structure of music theory well, through the lens of that particular composer? If not, then FIX or IMPROVE those things (instruct the other agent to do so using its skills and the mtdt tool!)" --- But then the controller agent was in charge and handled managing the worker agent (which did nearly all of the actual labor of making the tracks). It's a bit counterintuitive that this creator-critic split would work better (why not just go directly to the agent doing the work?), but I sort of stumbled on it by accident because I didn't want to mess with my default agent skills and only wanted the 322 music theory skills to be visible to the worker agent. That's why I originally had the controller agent launch the other agent: to specify that. But then I realized that it's very handy to have an independent agent handling the details for me. It's sort of like a rich English aristocrat in the 1700s having an awesome butler to handle the rest of the household staff. Just tell the butler what you want in a kind of abbreviated shorthand and he will turn around and give very detailed instructions, monitor everything, and do quality control for you so you don't have to get into the nitty-gritty details so much. It gives you another set of eyes, even if it's using the exact same underlying LLM, and there's something about the gestalt shift of being a critic versus a creator that leads to better objectivity and honesty and, ultimately, better-quality results. Anyway, the first results made me realize that it had taken my instructions about being able to hear the original song clearly in the reimagined version too literally, so I told the controller agent: "It too directly has the entire original melody within it unaltered, which is jarring and not like . It's also too long; they should be closer to 1.5 to 2 minutes each. We don't need to start from scratch, but make sure you address those issues." That's about the extent of my feedback and iteration here. And to be clear, the original versions were pretty nice, too. I'll have some other fun demos coming out soon as well. Anyway, attached here are results from 4 composers as animated scores. You can also get the PDF of the complete scores here: So do they actually sound like those composers wrote them? It's sort of an impossible task, in that the style of the original melodies is really nothing like the styles of those composers. But within those constraints, I think it did a respectable job. If you're a fan of that Zelda music and like classical music you will probably get a kick out of these. I'm positive that with more focused prompting and iteration I could get much better results from the system, but I sort of just wanted to see what it could do with minimal interventions. Curious to hear what people think.

I realized that I would probably get more interest in my AI music theory tool (mtdt) and corresponding agent skill library if I did impressive things with more mainstream/popular tunes rather than an obscure Irish folk song from the 18th century like in my quoted post. So this time, I took my 3 favorite tunes from Zelda: Ocarina of Time (i.e., Saria's Song, the Song of Storms, and Zelda's Lullaby) and had them reimagined by the AI agent using my system in the style of various famous classical composers: Schubert, Schumann, Rachmaninoff, and Liszt. I had GPT-6 Astra xhigh acting as the "controller" agent create the prompt and launch another instance of Codex (the "worker" agent) in a fresh workspace with all 322 skills loaded, and then monitor the process. I gave the controller agent only very high-level instructions about which songs from the Zelda game I wanted and which composers to use for which songs. I also told it stuff like: "For actually rendering the written music to audio, we should use the nice concert piano instrument with reverb that came from my jazz chords project originally (see /cass) and we should humanize the playing with a skill so it doesn't sound robotic in tempo and dynamics; it should sound like a professional pianist specializing in the music of the particular composer. And try to do a final critical pass over each piece with fresh eyes looking for any deficiencies and blunders... does it REALLY sound like that composer's work? Can you still hear the original song's essence in the new, reimagined version? Is it good? Does it follow the rules and structure of music theory well, through the lens of that particular composer? If not, then FIX or IMPROVE those things (instruct the other agent to do so using its skills and the mtdt tool!)" --- But then the controller agent was in charge and handled managing the worker agent (which did nearly all of the actual labor of making the tracks). It's a bit counterintuitive that this creator-critic split would work better (why not just go directly to the agent doing the work?), but I sort of stumbled on it by accident because I didn't want to mess with my default agent skills and only wanted the 322 music theory skills to be visible to the worker agent. That's why I originally had the controller agent launch the other agent: to specify that. But then I realized that it's very handy to have an independent agent handling the details for me. It's sort of like a rich English aristocrat in the 1700s having an awesome butler to handle the rest of the household staff. Just tell the butler what you want in a kind of abbreviated shorthand and he will turn around and give very detailed instructions, monitor everything, and do quality control for you so you don't have to get into the nitty-gritty details so much. It gives you another set of eyes, even if it's using the exact same underlying LLM, and there's something about the gestalt shift of being a critic versus a creator that leads to better objectivity and honesty and, ultimately, better-quality results. Anyway, the first results made me realize that it had taken my instructions about being able to hear the original song clearly in the reimagined version too literally, so I told the controller agent: "It too directly has the entire original melody within it unaltered, which is jarring and not like . It's also too long; they should be closer to 1.5 to 2 minutes each. We don't need to start from scratch, but make sure you address those issues." That's about the extent of my feedback and iteration here. And to be clear, the original versions were pretty nice, too. I'll have some other fun demos coming out soon as well. Anyway, attached here are results from 4 composers as animated scores. You can also get the PDF of the complete scores here: So do they actually sound like those composers wrote them? It's sort of an impossible task, in that the style of the original melodies is really nothing like the styles of those composers. But within those constraints, I think it did a respectable job. If you're a fan of that Zelda music and like classical music you will probably get a kick out of these. I'm positive that with more focused prompting and iteration I could get much better results from the system, but I sort of just wanted to see what it could do with minimal interventions. Curious to hear what people think.

Jeffrey Emanuel

23,583 views • 14 days ago

I cut Fable 5 token usage 2.5x with just one change! - Before: 5.5 M tokens · 7 errors · $8.94 - After: 2.3 M tokens · 0 errors · $4.17 The final build was the same for both, but the path the agent took wildly differed. In both runs, the agent started with the same thing, i.e., it understood the backend before building anything, like: - Permission policies - Available storage buckets - Auth providers configured - How edge functions are deployed The first run used Firebase, which was built for a human dev using a dashboard. While the dev can read the above state by clicking through tabs, an agent has no dashboard. So it gathered the same info through API calls. And there's no single Firebase call that returned this info. The agent required to query multiple times, and each query over-returned. For instance, when the agent asked how sign-in is configured, Firebase also returned the entire auth surface and every method it supported. This was far more context than what it needed. And it repeated across every part of the backend it inspected. Some states (like which auth providers are active) weren't queryable at all. I provided it myself. Otherwise, the agent would have guessed. Errors further compounded the token usage. When a dev sees "permission denied," they can look at the console and figure out whether it's a rule, a path, or an unauthenticated request. Firebase returned the same string to the agent as well, and it had none of that surrounding context to debug. So it guessed again, picked the most likely cause, and rewrote code, utilizing more tokens. This Firebase setup cost me 5.5M tokens and 7 manual interventions during errors on a full-stack RAG app. But I brought that down to 2.3M tokens and 0 manual interventions by using InsForge as the backend context engineering layer (open-source and self-hostable via Docker). It provides the same primitives as Supabase/Firebase, but structures the entire information layer for agents, instead of dashboards. In one CLI call that consumed ~500 tokens, the agent saw the full backend topology before writing a single line of code. This included auth, database, storage, edge functions, model gateway, micro VMs, and deployment. Also, instead of loading the entire product surface into context on every task, four narrowly scoped skills activated only when relevant to keep cognitive load minimal. And to ensure efficient retries if needed, every CLI operation returned structured JSON with meaningful exit codes, so the agent never guessed what to do next. Here's the InsForge GitHub Repo: (don't forget to star it ⭐) The video below depicts the final build, comparing Firebase and InsForge. To dive deeper, I recently published a full walkthrough building the same RAG app on both backends and inspected them end-to-end. Read it below.

I cut Fable 5 token usage 2.5x with just one change! - Before: 5.5 M tokens · 7 errors · $8.94 - After: 2.3 M tokens · 0 errors · $4.17 The final build was the same for both, but the path the agent took wildly differed. In both runs, the agent started with the same thing, i.e., it understood the backend before building anything, like: - Permission policies - Available storage buckets - Auth providers configured - How edge functions are deployed The first run used Firebase, which was built for a human dev using a dashboard. While the dev can read the above state by clicking through tabs, an agent has no dashboard. So it gathered the same info through API calls. And there's no single Firebase call that returned this info. The agent required to query multiple times, and each query over-returned. For instance, when the agent asked how sign-in is configured, Firebase also returned the entire auth surface and every method it supported. This was far more context than what it needed. And it repeated across every part of the backend it inspected. Some states (like which auth providers are active) weren't queryable at all. I provided it myself. Otherwise, the agent would have guessed. Errors further compounded the token usage. When a dev sees "permission denied," they can look at the console and figure out whether it's a rule, a path, or an unauthenticated request. Firebase returned the same string to the agent as well, and it had none of that surrounding context to debug. So it guessed again, picked the most likely cause, and rewrote code, utilizing more tokens. This Firebase setup cost me 5.5M tokens and 7 manual interventions during errors on a full-stack RAG app. But I brought that down to 2.3M tokens and 0 manual interventions by using InsForge as the backend context engineering layer (open-source and self-hostable via Docker). It provides the same primitives as Supabase/Firebase, but structures the entire information layer for agents, instead of dashboards. In one CLI call that consumed ~500 tokens, the agent saw the full backend topology before writing a single line of code. This included auth, database, storage, edge functions, model gateway, micro VMs, and deployment. Also, instead of loading the entire product surface into context on every task, four narrowly scoped skills activated only when relevant to keep cognitive load minimal. And to ensure efficient retries if needed, every CLI operation returned structured JSON with meaningful exit codes, so the agent never guessed what to do next. Here's the InsForge GitHub Repo: (don't forget to star it ⭐) The video below depicts the final build, comparing Firebase and InsForge. To dive deeper, I recently published a full walkthrough building the same RAG app on both backends and inspected them end-to-end. Read it below.

Avi Chawla

113,219 views • 3 months ago

Claude Code can now make full videos from your terminal.. Not slideshows. Not text on screen.. Actual motion graphics with animations, transitions, custom photos, and background music. [ SHARED A TUTORIAL BELOW EDITED WITH THIS SETUP IN JUST 5mins ] ▫️Here's the setup: Claude Code + Remotion Remotion is a React based framework that renders video programmatically. You describe what you want in plain English, Claude writes the React components and Remotion renders it into a real MP4. What you can actually do with this: > Generate 9:16 vertical videos for TikTok / Reels / Shorts > Add animated text with viral hooks and safe zones > Pull live web screenshots directly into your scenes using Chrome MCP > Fact-check your content in real time with Perplexity MCP > Drop in your own photos and background music > Edit existing talking-head footage cut bloopers, add captions > Schedule posts to your socials straight from the terminal ▫️How to set it up (takes 5 minutes) : > Make sure you have Node.js installed ( node -v to check ) > Create a new Remotion project: npx create-video@latest Pick the Blank template, enable TailwindCSS, and install the Skills package when prompted. > Install dependencies: cd my-video npm install > Start the preview server: npm run dev > Open Claude Code in the same project folder: cd my-video claude That's it. You can now prompt videos in plain English. If you already have a Remotion project, just add the skill directly: npx skills add remotion-dev/skills This drops a SKILL.md into your project that gives Claude expert knowledge of Remotion.. animations, compositions, captions, assets, 3D content everything. Example prompt you can steal: "Create a 30-second 9:16 vertical video about the top 3 AI tools this week. Use animated text with a hook in the first 2 seconds. Add smooth transitions between scenes. Keep text in the safe zone for TikTok. Use a dark tech aesthetic with blue accent colors." Claude writes all the React code, renders a preview, you tweak with natural language, and export when ready. The crazy part is this whole pipeline is local, free (minus your Claude sub), and you never open a video editor. imo this kills CapCut for anyone making info-style content. You describe the video in English and get back a rendered MP4. try it now.

Claude Code can now make full videos from your terminal.. Not slideshows. Not text on screen.. Actual motion graphics with animations, transitions, custom photos, and background music. [ SHARED A TUTORIAL BELOW EDITED WITH THIS SETUP IN JUST 5mins ] ▫️Here's the setup: Claude Code + Remotion Remotion is a React based framework that renders video programmatically. You describe what you want in plain English, Claude writes the React components and Remotion renders it into a real MP4. What you can actually do with this: > Generate 9:16 vertical videos for TikTok / Reels / Shorts > Add animated text with viral hooks and safe zones > Pull live web screenshots directly into your scenes using Chrome MCP > Fact-check your content in real time with Perplexity MCP > Drop in your own photos and background music > Edit existing talking-head footage cut bloopers, add captions > Schedule posts to your socials straight from the terminal ▫️How to set it up (takes 5 minutes) : > Make sure you have Node.js installed ( node -v to check ) > Create a new Remotion project: npx create-video@latest Pick the Blank template, enable TailwindCSS, and install the Skills package when prompted. > Install dependencies: cd my-video npm install > Start the preview server: npm run dev > Open Claude Code in the same project folder: cd my-video claude That's it. You can now prompt videos in plain English. If you already have a Remotion project, just add the skill directly: npx skills add remotion-dev/skills This drops a SKILL.md into your project that gives Claude expert knowledge of Remotion.. animations, compositions, captions, assets, 3D content everything. Example prompt you can steal: "Create a 30-second 9:16 vertical video about the top 3 AI tools this week. Use animated text with a hook in the first 2 seconds. Add smooth transitions between scenes. Keep text in the safe zone for TikTok. Use a dark tech aesthetic with blue accent colors." Claude writes all the React code, renders a preview, you tweak with natural language, and export when ready. The crazy part is this whole pipeline is local, free (minus your Claude sub), and you never open a video editor. imo this kills CapCut for anyone making info-style content. You describe the video in English and get back a rendered MP4. try it now.

Axel Bitblaze 🪓

31,250 views • 5 months ago

I met the guy behind Paperclip. he won't show his face, but he just built one of the FASTEST growing open-source projects in AI. how to use Paperclip to hire AI agents to ACTUALLY run a startup with 0 employees: 1. with paperclip, you hire a team of AI agents like CEO, engineer, QA, video editor, content strategist and manage them from one dashboard. it works with Claude Code, Codex, OpenCode, or any model on OpenRouter. you're not locked into one provider. 2. your AI agents wake up capable but with zero memory. they don't know who they are, where they are, or what they're supposed to be doing. kinda like that movie memento from back in the day you need to leave them Polaroids like heartbeat checklists, persona prompts, written context. that's how you keep them on track. 3. when an agent makes a mistake, you don't rewrite everything. you add one rule to their persona prompt. "always define a success condition for every task." "always pass work to QA before closing." you're training them like you'd train a junior hire. one correction at a time. 4. skills extend what your agents can do. want a video editor who can produce animated content? install the Remotion skill. want security reviews? there's a skill for that. 5. the biggest lever for quality is encoding your own taste. AI can do everything except know your values. design sensibility, brand voice, success criteria but you have to write it down. 6. don't one-shot your startup. agentic design patterns matter. the simplest one: after the engineer builds something, QA reviews it. structure prevents compounding errors. one-shotting an entire app is fun for 30 minutes, then it falls apart. 7. Paperclip tracks every token spent and every task completed. you can use your existing subscriptions (Claude, Codex) so spend shows as $0, or hook into API credits for real dollar tracking. 8. importable companies are coming. Gary Tan's G-Stack, a full game studio, 300+ agent repos... you can "acqui-hire" a proven agent team into your Paperclip instance instead of building from scratch. the future is downloading a tested org that actually works. 9. routines let you automate recurring work. "every day at 10am, read what was merged into the main branch and write a Discord update celebrating community contributors." it runs, you review, you improve. every task is traceable. 10. maximizer mode is next. you tell the CEO "build this game" and it does whatever it takes and hires who it needs, keeps pressing until it's done. no token anxiety. just outcomes. use Idea Browser for startup ideas/trends to get started thank you for dotta 📎 for doing this podcast and breaking down exactly how people can hire ai agent teams with paperclip you won't find an episode like this anywhere else episode is live on The Startup Ideas Podcast (SIP) 🧃 on your fav platforms (follow for more) is this not the greatest time in history to be building? im rooting for you now go watch my frien

GREG ISENBERG

463,893 views • 6 months ago

If you watch this ~50 minute screen recording closely (yeah, I know, it's long; there are also some times when my computer was very slow and laggy, just skip past that part. And at one point I had to run and get my 9-month-old a new bottle and left it on a boring screen, sorry!), I believe you can see real signs of the kind of runaway, recursive AI self-improvement that people have been warning of for a while (Mr. Kurzweil most notably and prophetically). Why do I say that? What's different now? Well, there's a reason my set of agent coding tooling is called the Flywheel. These tools all mutually self-reinforce each other. And they all flow directly into my ntm tool (short for "named_tmux_manager"), which acts as a sort of integration point and nerve center for the tools (this is becoming more true by the minute as I'm now seriously working on ntm). Now, ntm was something I started making to automate some aspects of my workflow, but it was the kind of thing where, until it was perfect, it sort of just slowed me down. So I didn't actually use it even though I kept working on it and trying to improve it, and suggested to users that they try it in my tutorials. Well anyway, I finally got around to "dogfooding" ntm last night, and now it's going to get very dramatically better at an alarming rate. Some of that is from applying my "idea wizard" prompt to generate more useful features and building that stuff out and addressing obvious pain points I encountered during my newfound usage of the tool. But a lot comes from my realization that, once again, ntm's true utility is not as a tool for ME, but for an agent. That is, ntm lets one instance of Claude Code or Codex act as, well, me, do the things that I had been doing manually. Do I wish I had started using ntm earlier? No, for two big reasons: 1) Doing it manually helped me build up my intuition massively, which directly led me down the path of creating useful prompt strategies and workflows; these often began as ad-hoc prompts that I realized could be generalized and made more versatile/universal. Lesson: don't prematurely automate until you have an intimate, intuitive feel for your "core value-add loop." Otherwise you'll have a fully automated system quickly that efficiently and automatically does a stupid or otherwise sub-optimal thing. 2) My eyes have been opened to the beauty and power of Skills. I'm not talking about your garden-variety skills that are just a simple markdown file. I'm talking about true tour-de-force directories of perfectly structured and organized files that are filled with good information, insights, workflows, etc., but presented in a way that is highly optimized for consumption by AI agents, with extreme attention paid to things like perfect progressive disclosure, token density, agent-ergonomics, agent-intuitiveness, etc. And also Skills that go way beyond markdown files, with full integration into Claude Code where it makes sense via hooks, sub-agents, and even Python scripts. These kinds of skills are a qualitative difference in expressive power and usefulness and a total game changer. They are also effectively composable, creating almost an algebra of skills that let you use them together in powerful ways. I'm working on a subscription service website and CLI tool now to share what I've learned here most effectively, stay tuned for that in the coming days. Anyway, I now know what to make and how to make it. So, getting back to that screen recording, what does it show that makes me claim recursive self-improvement is here? If you keep your eye on the upper left tmux pane, that's the "controller" agent. It is using ntm to control all the other panes which are also running Claude Code (but ntm fully supports other agent types like Codex and Gemini-CLI, and it's trivially easy to mix and match them if you wanted to have, say, 8 CCs and 6 Codexes for writing the code and 3 Gemini-CLIs for reviewing code.) Now, there's nothing that crazy about this much so far. But where it starts to get very cool is that as the session continues and we encounter real-world problems, things like my ridiculously overloaded computer that keeps hanging for long periods, Claude Code instances that crash and get into a frozen, unresponsive state, it can learn from that. And you can see it using my skill writing skill to refine its ntm vibe coding skill in real time. And then take that skill and refine it to be more intuitive for itself. Or use my cass tool skill to search all the session histories to look for problems that came up and strategize how to solve them. The most useful part was when, towards the end of the session, I told it to reflect on all the things we had done and problems we encountered. One way it can usefully leverage those reflections is by improving its ntm vibe coding skill to make it cover more edge cases and exigencies. But the other, more fundamental, way is for it to conceive of and design the optimal new features and functionality for ntm itself so that the tool embodies those lessons in a first-class way. This offloads cognition from its brain onto its tooling, just like how a person can lean on spellcheck or a calculator. It codifies correct, effective reasoning at the tool level, where it's more reliable and robust and repeatable. And btw, did you notice what code base it was working on the whole time? It was none other than ntm itself! So as it worked on its own tool, it had reflections and ideas about how to further improve the tool. Now, it could have just as easily gotten those insights and ideas while using ntm to work on a different project, but the fact that it was working on itself is almost gloriously meta and recursive. So by the end, after learning from tending to a big group of agent workers (btw, I have previously emphasized doing everything in a really distributed/decentralized way, where each fungible agent gets identical marching orders that tell it to use my bv tool to find the optimal bead to work on. This does work very well, but occasionally results in some contention and overlap from thundering herd, or at least wastes time/tokens/communication in avoiding that before the agents waste time duplicating work. But in this new ntm-oriented workflow, I was able to have the controller agent in the upper left use bv itself and then optimally parcel out the instructions to each agent so that we could know for sure that there's no overlap), I ended up with a ton of new beads for new features, which I had it optimize and polish a few times. Now I can swap to a new Claude Max account and have the swarm implement all those new features! It should only take a couple passes like the one shown in the screen recording to get everything implemented. Then we can rinse and repeat, having the agent read through the full session histories of each agent and its experience from its own session in sending ntm commands and seeing how they worked out in practice, to come up with the next batch of changes to both its ntm vibe coding skill AND to the ntm tool itself. Do you see how rapidly this turns into Skynet? My mistake earlier was in focusing on making myself a "faster horse" as Henry Ford used to joke about customers wanting before he showed them what they should really want (a Model T). That is, something that would make my experience nicer while doing this agent swarm based development workflow. But the obvious lesson is that you should make all your tooling agent-first because the agents are just better at this stuff. You can still watch, and of course I did add a ridiculous number of very nice human-centric features to ntm that you'll be seeing in the next day or two, but those are really kind of "for fun" to make us humans feel better about the process. All the real value-add is happening "by agents, for agents." PS: Towards the end, you can see me switch to my Mac and tell Claude to improve the skill that I made earlier today for taking the mkv screen recording files from OBS Studio and muxing them into MP4 files for sharing, while downloading songs from YouTube to serve as the background music. I made it so it can also grab the thumbnails and generate little song credit cards that show up in the lower right corner. This worked perfectly the first time! I'll include some screenshots in a response post showing how that worked, but it was awesome to witness. Skills are POWERFUL. I'll also post a link to this video on YouTube if you prefer to watch it there.

If you watch this ~50 minute screen recording closely (yeah, I know, it's long; there are also some times when my computer was very slow and laggy, just skip past that part. And at one point I had to run and get my 9-month-old a new bottle and left it on a boring screen, sorry!), I believe you can see real signs of the kind of runaway, recursive AI self-improvement that people have been warning of for a while (Mr. Kurzweil most notably and prophetically). Why do I say that? What's different now? Well, there's a reason my set of agent coding tooling is called the Flywheel. These tools all mutually self-reinforce each other. And they all flow directly into my ntm tool (short for "named_tmux_manager"), which acts as a sort of integration point and nerve center for the tools (this is becoming more true by the minute as I'm now seriously working on ntm). Now, ntm was something I started making to automate some aspects of my workflow, but it was the kind of thing where, until it was perfect, it sort of just slowed me down. So I didn't actually use it even though I kept working on it and trying to improve it, and suggested to users that they try it in my tutorials. Well anyway, I finally got around to "dogfooding" ntm last night, and now it's going to get very dramatically better at an alarming rate. Some of that is from applying my "idea wizard" prompt to generate more useful features and building that stuff out and addressing obvious pain points I encountered during my newfound usage of the tool. But a lot comes from my realization that, once again, ntm's true utility is not as a tool for ME, but for an agent. That is, ntm lets one instance of Claude Code or Codex act as, well, me, do the things that I had been doing manually. Do I wish I had started using ntm earlier? No, for two big reasons: 1) Doing it manually helped me build up my intuition massively, which directly led me down the path of creating useful prompt strategies and workflows; these often began as ad-hoc prompts that I realized could be generalized and made more versatile/universal. Lesson: don't prematurely automate until you have an intimate, intuitive feel for your "core value-add loop." Otherwise you'll have a fully automated system quickly that efficiently and automatically does a stupid or otherwise sub-optimal thing. 2) My eyes have been opened to the beauty and power of Skills. I'm not talking about your garden-variety skills that are just a simple markdown file. I'm talking about true tour-de-force directories of perfectly structured and organized files that are filled with good information, insights, workflows, etc., but presented in a way that is highly optimized for consumption by AI agents, with extreme attention paid to things like perfect progressive disclosure, token density, agent-ergonomics, agent-intuitiveness, etc. And also Skills that go way beyond markdown files, with full integration into Claude Code where it makes sense via hooks, sub-agents, and even Python scripts. These kinds of skills are a qualitative difference in expressive power and usefulness and a total game changer. They are also effectively composable, creating almost an algebra of skills that let you use them together in powerful ways. I'm working on a subscription service website and CLI tool now to share what I've learned here most effectively, stay tuned for that in the coming days. Anyway, I now know what to make and how to make it. So, getting back to that screen recording, what does it show that makes me claim recursive self-improvement is here? If you keep your eye on the upper left tmux pane, that's the "controller" agent. It is using ntm to control all the other panes which are also running Claude Code (but ntm fully supports other agent types like Codex and Gemini-CLI, and it's trivially easy to mix and match them if you wanted to have, say, 8 CCs and 6 Codexes for writing the code and 3 Gemini-CLIs for reviewing code.) Now, there's nothing that crazy about this much so far. But where it starts to get very cool is that as the session continues and we encounter real-world problems, things like my ridiculously overloaded computer that keeps hanging for long periods, Claude Code instances that crash and get into a frozen, unresponsive state, it can learn from that. And you can see it using my skill writing skill to refine its ntm vibe coding skill in real time. And then take that skill and refine it to be more intuitive for itself. Or use my cass tool skill to search all the session histories to look for problems that came up and strategize how to solve them. The most useful part was when, towards the end of the session, I told it to reflect on all the things we had done and problems we encountered. One way it can usefully leverage those reflections is by improving its ntm vibe coding skill to make it cover more edge cases and exigencies. But the other, more fundamental, way is for it to conceive of and design the optimal new features and functionality for ntm itself so that the tool embodies those lessons in a first-class way. This offloads cognition from its brain onto its tooling, just like how a person can lean on spellcheck or a calculator. It codifies correct, effective reasoning at the tool level, where it's more reliable and robust and repeatable. And btw, did you notice what code base it was working on the whole time? It was none other than ntm itself! So as it worked on its own tool, it had reflections and ideas about how to further improve the tool. Now, it could have just as easily gotten those insights and ideas while using ntm to work on a different project, but the fact that it was working on itself is almost gloriously meta and recursive. So by the end, after learning from tending to a big group of agent workers (btw, I have previously emphasized doing everything in a really distributed/decentralized way, where each fungible agent gets identical marching orders that tell it to use my bv tool to find the optimal bead to work on. This does work very well, but occasionally results in some contention and overlap from thundering herd, or at least wastes time/tokens/communication in avoiding that before the agents waste time duplicating work. But in this new ntm-oriented workflow, I was able to have the controller agent in the upper left use bv itself and then optimally parcel out the instructions to each agent so that we could know for sure that there's no overlap), I ended up with a ton of new beads for new features, which I had it optimize and polish a few times. Now I can swap to a new Claude Max account and have the swarm implement all those new features! It should only take a couple passes like the one shown in the screen recording to get everything implemented. Then we can rinse and repeat, having the agent read through the full session histories of each agent and its experience from its own session in sending ntm commands and seeing how they worked out in practice, to come up with the next batch of changes to both its ntm vibe coding skill AND to the ntm tool itself. Do you see how rapidly this turns into Skynet? My mistake earlier was in focusing on making myself a "faster horse" as Henry Ford used to joke about customers wanting before he showed them what they should really want (a Model T). That is, something that would make my experience nicer while doing this agent swarm based development workflow. But the obvious lesson is that you should make all your tooling agent-first because the agents are just better at this stuff. You can still watch, and of course I did add a ridiculous number of very nice human-centric features to ntm that you'll be seeing in the next day or two, but those are really kind of "for fun" to make us humans feel better about the process. All the real value-add is happening "by agents, for agents." PS: Towards the end, you can see me switch to my Mac and tell Claude to improve the skill that I made earlier today for taking the mkv screen recording files from OBS Studio and muxing them into MP4 files for sharing, while downloading songs from YouTube to serve as the background music. I made it so it can also grab the thumbnails and generate little song credit cards that show up in the lower right corner. This worked perfectly the first time! I'll include some screenshots in a response post showing how that worked, but it was awesome to witness. Skills are POWERFUL. I'll also post a link to this video on YouTube if you prefer to watch it there.

Jeffrey Emanuel

25,483 views • 8 months ago

acpx v0.4 ships Agentic Workflows, or as I like to call them "Agentic Graphs" It let's you create node-based workflows on top of ACP (Agent Client Protocol), to drive any coding agent (Codex, Claude Code, pi) through deterministic steps This let's you automate routine, mechanical legwork like triaging incoming PRs, bugs in error reporting, and so on... For example, OpenClaw receives 300~500 new PRs per day. A lot of them are low quality, but they still relate to real issues, so you have to address them somehow You need to: - extract the intent - cluster them based on intent - figure out if the proposed changes are legit, or whether they are slop local solutions, like trying to catch flies instead of drying out the swamp - if the PR is too low quality or the intent is not clear, close them - run AI review on them them and address any issues that come up - refactor them if the changes are half-baked - resolve conflicts - and so on... So that when the PR is presented to the attention of the maintainer, all the routine legwork is done and the only remaining thing is the decision to (a) merge, (b) give feedback to the PR author, or (c) take over the PR work yourself I wanted to build this feature since a couple months now, since Codex got so good. OpenAI models are now good at judging implementation quality, so I found myself repeating the same steps I wrote above over and over I also tried putting all this in a single prompt. But I believe there are workflows that should not be a single prompt, but a sequence of prompts in the same session That is because like humans, LLMs are prone to PRIMING. I claim that putting all steps in the same prompt at the beginning of the context will generally give suboptimal results, compared to revealing the intention to the model step by step Creating such a workflow also gives more OBSERVABILITY into the each step that an agent is supposed to take. Agent generates JSON at the end of each step, and that structured data can be used to monitor thousands of agents running at the same time in an easier way, on a dashboard Similar features have been introduced in e.g. n8n, langflow. But AFAIK they are not integrating ACP like the way I do I wanted to have a fresh approach, and to build an API that I can develop freely the way I want, so I created a new workflow API inside acpx The video is from the workflow run viewer, but that is not where you build the workflow. You build it by using the acpx flow typescript API. See examples/pr-triage in acpx repo Before building that, I started from a Markdown file with a Mermaid chart of the flow I had in mind. The Markdown file acts as a spec for the flow, and I have built the workflow through trial and error. I call this process "workflow tuning" I started working on acpx repo PRs one by one, tuning the flow, slowly scaling to more PRs. Finally, when I felt confident, I ran it in parallel over all external open PRs in the acpx repo. I believe it already saved me hours this week My next goal, if well received, is to set this up on a cloud agent so that it can process the 300~500 PRs the OpenClaw repo receives every day, in real time, as they come in I believe this will save all open source maintainers around the world countless hours and make it much easier to herd and absorb external contributions from everyone!

acpx v0.4 ships Agentic Workflows, or as I like to call them "Agentic Graphs" It let's you create node-based workflows on top of ACP (Agent Client Protocol), to drive any coding agent (Codex, Claude Code, pi) through deterministic steps This let's you automate routine, mechanical legwork like triaging incoming PRs, bugs in error reporting, and so on... For example, OpenClaw receives 300~500 new PRs per day. A lot of them are low quality, but they still relate to real issues, so you have to address them somehow You need to: - extract the intent - cluster them based on intent - figure out if the proposed changes are legit, or whether they are slop local solutions, like trying to catch flies instead of drying out the swamp - if the PR is too low quality or the intent is not clear, close them - run AI review on them them and address any issues that come up - refactor them if the changes are half-baked - resolve conflicts - and so on... So that when the PR is presented to the attention of the maintainer, all the routine legwork is done and the only remaining thing is the decision to (a) merge, (b) give feedback to the PR author, or (c) take over the PR work yourself I wanted to build this feature since a couple months now, since Codex got so good. OpenAI models are now good at judging implementation quality, so I found myself repeating the same steps I wrote above over and over I also tried putting all this in a single prompt. But I believe there are workflows that should not be a single prompt, but a sequence of prompts in the same session That is because like humans, LLMs are prone to PRIMING. I claim that putting all steps in the same prompt at the beginning of the context will generally give suboptimal results, compared to revealing the intention to the model step by step Creating such a workflow also gives more OBSERVABILITY into the each step that an agent is supposed to take. Agent generates JSON at the end of each step, and that structured data can be used to monitor thousands of agents running at the same time in an easier way, on a dashboard Similar features have been introduced in e.g. n8n, langflow. But AFAIK they are not integrating ACP like the way I do I wanted to have a fresh approach, and to build an API that I can develop freely the way I want, so I created a new workflow API inside acpx The video is from the workflow run viewer, but that is not where you build the workflow. You build it by using the acpx flow typescript API. See examples/pr-triage in acpx repo Before building that, I started from a Markdown file with a Mermaid chart of the flow I had in mind. The Markdown file acts as a spec for the flow, and I have built the workflow through trial and error. I call this process "workflow tuning" I started working on acpx repo PRs one by one, tuning the flow, slowly scaling to more PRs. Finally, when I felt confident, I ran it in parallel over all external open PRs in the acpx repo. I believe it already saved me hours this week My next goal, if well received, is to set this up on a cloud agent so that it can process the 300~500 PRs the OpenClaw repo receives every day, in real time, as they come in I believe this will save all open source maintainers around the world countless hours and make it much easier to herd and absorb external contributions from everyone!

Onur Solmaz

149,693 views • 5 months ago