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.

Someone open-source harness that lets Claude Code and Codex generate real 3D CAD models from plain English. It’s called text-to-cad, an open source harness that turns your coding agent into a CAD engineer.. Building a robot used to mean stitching 6+ tools, CAD software, URDF exporters, kinematics solvers, viewers.... Days of work. Broken pipelines. Files no agent can read. text-to-cad kills all of it. → Exports STEP, STL, DXF, GLB, 3MF → Generates URDF robot descriptions → Slices straight to G-code → Sends jobs to your Bambu Lab printer → Runs fully offline, no backend One demo generates a full 7-DoF robot arm, working kinematics, custom GUI, the whole thing, almost entirely through prompts. 100% open source.show more

Superman

2,550 subscribers

51,642 views • 3 days ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Say hello to text-to-cad, an open source tool for generating 3D models in Codex! Prompt and edit complex 3D models. Export STEP, STL, GLB, DXF and URDF files. Built for CAD newbies. Link to github below. CAD is hard. As a software engineer getting back into robotics, I’ve been humbled by new tools like Onshape. Struggling to kick old habits, I started prompting Codex to generate 3D models and had some limited succes. After a few iterations I found a recipe that actually works: 1. Generate a python script for every STEP file. The agent can easily edit each part’s source without touching the raw STEP file. Use build123d > cadquery. 2. Reference specific faces and edges in prompts for precise edits. I built a basic local ui to inspect / cache STEP B-reps to make this easier. 3. Maintain markdown explaining important part features in plain English so the model can index on project context quickly. 4. Verify results with screenshots and geometry. Models don’t have great spatial awareness, but they can interpret images and verify constraints very well. For the best results I’ve been using GPT 5.4 xhigh / Opus 4.6+. Fair warning, this will burn through tokens, I recommend the Pro/Max plans if you’re planning on building anything serious. PRs welcome!

Say hello to text-to-cad, an open source tool for generating 3D models in Codex! Prompt and edit complex 3D models. Export STEP, STL, GLB, DXF and URDF files. Built for CAD newbies. Link to github below. CAD is hard. As a software engineer getting back into robotics, I’ve been humbled by new tools like Onshape. Struggling to kick old habits, I started prompting Codex to generate 3D models and had some limited succes. After a few iterations I found a recipe that actually works: 1. Generate a python script for every STEP file. The agent can easily edit each part’s source without touching the raw STEP file. Use build123d > cadquery. 2. Reference specific faces and edges in prompts for precise edits. I built a basic local ui to inspect / cache STEP B-reps to make this easier. 3. Maintain markdown explaining important part features in plain English so the model can index on project context quickly. 4. Verify results with screenshots and geometry. Models don’t have great spatial awareness, but they can interpret images and verify constraints very well. For the best results I’ve been using GPT 5.4 xhigh / Opus 4.6+. Fair warning, this will burn through tokens, I recommend the Pro/Max plans if you’re planning on building anything serious. PRs welcome!

Jake Fitzgerald

52,444 views • 3 months ago

KYRALL TURNS "I NEED THIS PART" INTO SECONDS, WITHOUT OPENING CAD you describe the part. the AI generates it. no SolidWorks. no Fusion. no hours of setup. why this matters to you: modeling a part in CAD is slow and technical. sketch, constrain, extrude, fillet — for every bracket, housing or fixture. and simple one-off parts eat the same ceremony every time. for an engineer, that bottleneck stalls the whole project. Kyrall skips it: → prompt → 3D part ready → exports to STEP and STL, the formats you already use → for when you need the geometry now, not in three days it doesn't compete with CAD suites on millimeter control. it competes on getting you to a usable part first. idea → part → keep building. link below :)

KYRALL TURNS "I NEED THIS PART" INTO SECONDS, WITHOUT OPENING CAD you describe the part. the AI generates it. no SolidWorks. no Fusion. no hours of setup. why this matters to you: modeling a part in CAD is slow and technical. sketch, constrain, extrude, fillet — for every bracket, housing or fixture. and simple one-off parts eat the same ceremony every time. for an engineer, that bottleneck stalls the whole project. Kyrall skips it: → prompt → 3D part ready → exports to STEP and STL, the formats you already use → for when you need the geometry now, not in three days it doesn't compete with CAD suites on millimeter control. it competes on getting you to a usable part first. idea → part → keep building. link below :)

marcus

31,238 views • 16 days ago

Enough with LLMs - exciting things are happening in the world of atoms. This is Stanford ALOHA, a low-cost and agile robot platform. The whole system is open-source (!!): hardware design, CAD models for 3D printing, simulator, and training code. Time to graft a physical arm onto GPTs 🦾 Led by my friend Tony Zhao at Stanford, and advised by Chelsea Finn Sergey Levine Vikash Kumar. Project page: If you don't want to 3D print your own components, you can buy the setup at

Enough with LLMs - exciting things are happening in the world of atoms. This is Stanford ALOHA, a low-cost and agile robot platform. The whole system is open-source (!!): hardware design, CAD models for 3D printing, simulator, and training code. Time to graft a physical arm onto GPTs 🦾 Led by my friend Tony Zhao at Stanford, and advised by Chelsea Finn Sergey Levine Vikash Kumar. Project page: If you don't want to 3D print your own components, you can buy the setup at

Jim Fan

818,477 views • 3 years ago

Wow! AI ASSISTED GARAGE MANUFACTURING IS ABOUT TO EXPLODE! CAD Drawings From Just A Picture! MIT just released something profound for creators and engineers alike. Picture this. You take a photo of an object, upload it, and an AI delivers a fully parametric CAD model, complete with editable code and construction history. This is open source GenCAD, from MIT's Decode Lab. It uses autoregressive transformers and diffusion models, trained on hundreds of thousands of images and CAD files. Input a 2D photo or sketch. Output valid CadQuery Python code that beats models like GPT-4.5 in accuracy. Why does this matter? It speeds up reverse engineering, prototyping, and part searches in vast databases. No more hours spent modeling from scratch. Field repairs, custom designs, education, all transformed. It even retrieves similar parts from libraries of thousands. For industries like manufacturing and aerospace, it cuts costs and boosts innovation. Hobbyists gain pro tools without the steep curve. I am testing it now on random objects and can not believe how much of a super power this is. I can start dozens of companies just on this AI model. This open-source gem is here: The future of building stuff arrives in a snapshot.

Wow! AI ASSISTED GARAGE MANUFACTURING IS ABOUT TO EXPLODE! CAD Drawings From Just A Picture! MIT just released something profound for creators and engineers alike. Picture this. You take a photo of an object, upload it, and an AI delivers a fully parametric CAD model, complete with editable code and construction history. This is open source GenCAD, from MIT's Decode Lab. It uses autoregressive transformers and diffusion models, trained on hundreds of thousands of images and CAD files. Input a 2D photo or sketch. Output valid CadQuery Python code that beats models like GPT-4.5 in accuracy. Why does this matter? It speeds up reverse engineering, prototyping, and part searches in vast databases. No more hours spent modeling from scratch. Field repairs, custom designs, education, all transformed. It even retrieves similar parts from libraries of thousands. For industries like manufacturing and aerospace, it cuts costs and boosts innovation. Hobbyists gain pro tools without the steep curve. I am testing it now on random objects and can not believe how much of a super power this is. I can start dozens of companies just on this AI model. This open-source gem is here: The future of building stuff arrives in a snapshot.

Brian Roemmele

121,948 views • 4 months ago

A GUY PUT GPT-LEVEL AI INSIDE A 3D PRINTED ROBOT AND RELEASED THE ENTIRE THING FOR FREE Most people look at a 3D printer and see plastic toys This guy printed a robot with expressive eyes, object tracking, image recognition, support for ChatGPT, Qwen and offline models, then uploaded the STL files, code and hardware designs for anyone to build themselves The interesting part isn't the robot It's how fast the gap between "I have an idea" and "I built a working product" is disappearing A few years ago this required a team of engineers Now one person with a printer, open-source software and enough curiosity can build something that looks like it came from a robotics startup We're getting very close to a world where manufacturing, AI and robotics stop being separate industries and start becoming the same thing

A GUY PUT GPT-LEVEL AI INSIDE A 3D PRINTED ROBOT AND RELEASED THE ENTIRE THING FOR FREE Most people look at a 3D printer and see plastic toys This guy printed a robot with expressive eyes, object tracking, image recognition, support for ChatGPT, Qwen and offline models, then uploaded the STL files, code and hardware designs for anyone to build themselves The interesting part isn't the robot It's how fast the gap between "I have an idea" and "I built a working product" is disappearing A few years ago this required a team of engineers Now one person with a printer, open-source software and enough curiosity can build something that looks like it came from a robotics startup We're getting very close to a world where manufacturing, AI and robotics stop being separate industries and start becoming the same thing

lagerskoy

57,045 views • 1 month ago

Robotics is getting its Raspberry Pi moment. This solves one of the biggest frictions in Physical AI: Everything has been fragmented. Different tools for control. Sensors. Calibration. Learning. Now it’s one unified stack: • motor control to VLA models in one system • built for real hardware, not just simulation -> norma_core_dev just entered PUBLIC ALPHA. The real unlock is ElRobot: • 7+1 DOF arm • fully 3D printable • ~220$ cost • ships with CAD, URDF, full build guide Not a demo… Infrastructure. And the part most people will underestimate: auto-calibration for any robot No manual tuning. No trial and error. Just: code → hardware → working system That removes one of the biggest hidden bottlenecks in robotics. Which unlocks: • faster iteration • cheaper experiments • real-world data loops Exactly what Physical AI needs. We’re moving from: “Can we make it work?” to “How fast can we improve it?” Thank you so much for sharing, Erick! 📍Repro: Credit:

Robotics is getting its Raspberry Pi moment. This solves one of the biggest frictions in Physical AI: Everything has been fragmented. Different tools for control. Sensors. Calibration. Learning. Now it’s one unified stack: • motor control to VLA models in one system • built for real hardware, not just simulation -> norma_core_dev just entered PUBLIC ALPHA. The real unlock is ElRobot: • 7+1 DOF arm • fully 3D printable • ~220$ cost • ships with CAD, URDF, full build guide Not a demo… Infrastructure. And the part most people will underestimate: auto-calibration for any robot No manual tuning. No trial and error. Just: code → hardware → working system That removes one of the biggest hidden bottlenecks in robotics. Which unlocks: • faster iteration • cheaper experiments • real-world data loops Exactly what Physical AI needs. We’re moving from: “Can we make it work?” to “How fast can we improve it?” Thank you so much for sharing, Erick! 📍Repro: Credit:

Ilir Aliu

66,277 views • 4 months ago

Introducing FlowMaker 🌊🤖 A fully open-source, low-code way of building custom agent workflows. Build agents via a drag and drop interface, run it directly in the app, and also directly export it into a deeply custom workflow backed by LlamaIndex 🦙.TS. It’s a fantastic visual tool to help you get started with agents but also gives you full customizability to build the deepest, most advanced workflows, since everything is backed by code. There’s a lot of great low-code agent tools already, but this is a fully-open source template that you can use or clone/customize for your own needs. It was a fun project by Laurie Voss and is intended to give users an easy-on ramp onto our powerful agent orchestration tooling. Also integrates with LlamaCloud in case you want to integrate your own knowledge base into your agent. FlowMaker app: FlowMaker Repo: LlamaCloud:

Introducing FlowMaker 🌊🤖 A fully open-source, low-code way of building custom agent workflows. Build agents via a drag and drop interface, run it directly in the app, and also directly export it into a deeply custom workflow backed by LlamaIndex 🦙.TS. It’s a fantastic visual tool to help you get started with agents but also gives you full customizability to build the deepest, most advanced workflows, since everything is backed by code. There’s a lot of great low-code agent tools already, but this is a fully-open source template that you can use or clone/customize for your own needs. It was a fun project by Laurie Voss and is intended to give users an easy-on ramp onto our powerful agent orchestration tooling. Also integrates with LlamaCloud in case you want to integrate your own knowledge base into your agent. FlowMaker app: FlowMaker Repo: LlamaCloud:

Jerry Liu

20,413 views • 1 year ago

$Boston Dynamics’ Spot costs $75,000. This one? $135. LeCabot is an open-source mod for your SO-100 and Unitree Go2 that turns them into a fully capable mobile manipulator… for a fraction of the price. You control both the robot dog and arm simultaneously using a Meta Quest headset, thanks to Phospho AI 🧪 It’s real, it’s accessible, and it’s ready for AI model training on rough terrain. Start building: Bill of materials and assembly instructions →$

Boston Dynamics’ Spot costs $75,000. This one? $135. LeCabot is an open-source mod for your SO-100 and Unitree Go2 that turns them into a fully capable mobile manipulator… for a fraction of the price. You control both the robot dog and arm simultaneously using a Meta Quest headset, thanks to Phospho AI 🧪 It’s real, it’s accessible, and it’s ready for AI model training on rough terrain. Start building: Bill of materials and assembly instructions →

Ilir Aliu - eu/acc

20,614 views • 10 months ago

$Boston Dynamics’ Spot costs $75,000. This one? $135. LeCabot is an open-source mod for your SO-100 and Unitree Go2 that turns them into a fully capable mobile manipulator… for a fraction of the price. You control both the robot dog and arm simultaneously using a Meta Quest headset, thanks to phospho 🧪 🧪 It’s real, it’s accessible, and it’s ready for AI model training on rough terrain. Thanks for sharing, ulyanov! Start building: Bill of materials and assembly instructions →$

Boston Dynamics’ Spot costs $75,000. This one? $135. LeCabot is an open-source mod for your SO-100 and Unitree Go2 that turns them into a fully capable mobile manipulator… for a fraction of the price. You control both the robot dog and arm simultaneously using a Meta Quest headset, thanks to phospho 🧪 🧪 It’s real, it’s accessible, and it’s ready for AI model training on rough terrain. Thanks for sharing, ulyanov! Start building: Bill of materials and assembly instructions →

Ilir Aliu - eu/acc

21,874 views • 1 year ago

THIS GUY BUILT A COMMAND CENTER FOR MANAGING AI AGENT TEAMS he was running 20+ agents through openclaw. all from terminal tabs and Discord. 12 tabs open. still losing track of who's doing what. which cron failed. so he built a dashboard that gives you one place to see everything: > org map showing the full agent hierarchy, who reports to who and what tools each agent has > chat with any agent through a real UI instead of bouncing between terminals > kanban board for tracking tasks across all agents > cron monitor with pipeline visualizations so you can see which jobs are failing > memory browser to read through all agent knowledge files in one place you can even point it at your openclaw workspace and it auto-discovers every agent from their config files. zero setup. AND ITS OPEN SOURCE TOO.

THIS GUY BUILT A COMMAND CENTER FOR MANAGING AI AGENT TEAMS he was running 20+ agents through openclaw. all from terminal tabs and Discord. 12 tabs open. still losing track of who's doing what. which cron failed. so he built a dashboard that gives you one place to see everything: > org map showing the full agent hierarchy, who reports to who and what tools each agent has > chat with any agent through a real UI instead of bouncing between terminals > kanban board for tracking tasks across all agents > cron monitor with pipeline visualizations so you can see which jobs are failing > memory browser to read through all agent knowledge files in one place you can even point it at your openclaw workspace and it auto-discovers every agent from their config files. zero setup. AND ITS OPEN SOURCE TOO.

Om Patel

46,780 views • 4 months ago

Building AI agents and tools is getting ridiculously easy! Here is a pretty impressive FREE and Open-Source AI agent builder that runs on your computer. It's a desktop app you can install on Mac or Windows. Link: • Free • 100% no-code: You can type what you want, and the tool will build everything for you. • You can use local models like DeepSeek or Qwen, or connect to cloud models like GPT-4o, Claude, or Gemini with your API key. • You can turn the tools you build into MCP Servers. I recorded a quick video to show you how easy it is to build something from scratch.

Building AI agents and tools is getting ridiculously easy! Here is a pretty impressive FREE and Open-Source AI agent builder that runs on your computer. It's a desktop app you can install on Mac or Windows. Link: • Free • 100% no-code: You can type what you want, and the tool will build everything for you. • You can use local models like DeepSeek or Qwen, or connect to cloud models like GPT-4o, Claude, or Gemini with your API key. • You can turn the tools you build into MCP Servers. I recorded a quick video to show you how easy it is to build something from scratch.

Santiago

56,815 views • 1 year ago

THIS GUY VIBE CODED A TOOL THAT TURNS ANY SVG INTO A 3D OBJECT YOU CAN SPIN, ANIMATE, AND EMBED drag in an SVG, type some text, or draw pixel art. it becomes a 3D object instantly. spin it around, animate it, and embed it on your site. export as 4K image or video. runs entirely in your browser and nothing gets uploaded to any server with no account needed. 100% free AND its open source. this is one of those tools you didn't know you needed until you see it

THIS GUY VIBE CODED A TOOL THAT TURNS ANY SVG INTO A 3D OBJECT YOU CAN SPIN, ANIMATE, AND EMBED drag in an SVG, type some text, or draw pixel art. it becomes a 3D object instantly. spin it around, animate it, and embed it on your site. export as 4K image or video. runs entirely in your browser and nothing gets uploaded to any server with no account needed. 100% free AND its open source. this is one of those tools you didn't know you needed until you see it

Om Patel

230,215 views • 3 months ago

New course: Gemini CLI: Code & Create with an Open-Source Agent, built with Google Cloud Tech/Gemini CLI and taught by Jack Wotherspoon. Agentic coding assistants like Gemini CLI are transforming how developers work. This short course teaches you to use Google's open-source agent to coordinate local tools and cloud services for coding and non-coding workflows. Gemini CLI works from your terminal, so it works with your local files and development tools. You can also connect it to services through MCP. Then provide high-level instructions, and it autonomously plans and executes complex workflows. Skills you'll gain: - Build website features and automate code reviews with GitHub ActionsCreate data dashboards that combine local files with cloud data sources - Use MCP servers and extensions to orchestrate workflows across GitHub, Canva, and Google Workspace - Generate social media content from multimedia files like conference recordings I particularly appreciate that Gemini CLI is open-source. You can see exactly how it works, read the prompts it uses, and understand its architecture. The community has contributed thousands of pull requests. Since Gemini 3’s release I've found Gemini CLI highly capable - this is a tool worth having in your toolbox! Whether you're prototyping applications, automating workflows, or working with multimedia content, join to learn to delegate complex tasks and build faster:

New course: Gemini CLI: Code & Create with an Open-Source Agent, built with Google Cloud Tech/Gemini CLI and taught by Jack Wotherspoon. Agentic coding assistants like Gemini CLI are transforming how developers work. This short course teaches you to use Google's open-source agent to coordinate local tools and cloud services for coding and non-coding workflows. Gemini CLI works from your terminal, so it works with your local files and development tools. You can also connect it to services through MCP. Then provide high-level instructions, and it autonomously plans and executes complex workflows. Skills you'll gain: - Build website features and automate code reviews with GitHub ActionsCreate data dashboards that combine local files with cloud data sources - Use MCP servers and extensions to orchestrate workflows across GitHub, Canva, and Google Workspace - Generate social media content from multimedia files like conference recordings I particularly appreciate that Gemini CLI is open-source. You can see exactly how it works, read the prompts it uses, and understand its architecture. The community has contributed thousands of pull requests. Since Gemini 3’s release I've found Gemini CLI highly capable - this is a tool worth having in your toolbox! Whether you're prototyping applications, automating workflows, or working with multimedia content, join to learn to delegate complex tasks and build faster:

Andrew Ng

124,823 views • 6 months ago

🚨 One orchestrator. 10 parallel agents. 100+ tokens a second. All local. The Google Gemma team just dropped a MASSIVE demo for Gemma 4 26B. They built a concurrent workflow that lets the 26B model coordinate an entire team of sub-agents on your machine. Out of the box, the cookbook lets you run 10 parallel agents to: → Code an entire SVG art gallery in seconds → Translate text simultaneously → Generate ASCII art → Write parallel code Spinning up multi-agent systems locally has never looked this fast or this accessible. 100% free and open-source. repo link in 🧵↓

🚨 One orchestrator. 10 parallel agents. 100+ tokens a second. All local. The Google Gemma team just dropped a MASSIVE demo for Gemma 4 26B. They built a concurrent workflow that lets the 26B model coordinate an entire team of sub-agents on your machine. Out of the box, the cookbook lets you run 10 parallel agents to: → Code an entire SVG art gallery in seconds → Translate text simultaneously → Generate ASCII art → Write parallel code Spinning up multi-agent systems locally has never looked this fast or this accessible. 100% free and open-source. repo link in 🧵↓

Charly Wargnier

31,627 views • 1 month ago

Open source software is GREAT. But "open source" AI is NOT like software - it's VERY different. Rob Miles cuts through the bullshit: ROB: Oh, hey, Meta. I heard Llama's weights leaked. That's rough, man. Information security's hard. How you holding up? META: Oh, we're great. Yeah, we're fine. We... actually, that was deliberate. We meant to do that. ROB MILES: Oh, really? META: Yeah... well, the second time anyway. It's called open source. Look it up. ROB MILES: Oh. Well, I love free and open source software, but do those principles really apply to network weights? How does that work? META: Open source is good for users because it lets them read the source code and see what the program is really doing and how it works. ROB MILES: Wait, have you found a way to tell how a model works by looking at its weights? META: No. But, it lets developers all over the world spot bugs in the code and submit patches. ROB: Wait, people are fixing bugs in Llama's weights? META: Well, no. People can fine tune it themselves, though. ROB: ?? Other companies offer fine tuning through APIs. ... So, hang on, if you can't actually read the code and know what it's doing, then network weights are effectively a compiled binary. So, in what sense is this open source? Why not call it like public weights? Why call it open source at all? META: I love open source. ROB: Well, I know a lot of your employees do, but you don't love anything. You're a giant corporation. What's in it for you? META: I love, love open source.

Open source software is GREAT. But "open source" AI is NOT like software - it's VERY different. Rob Miles cuts through the bullshit: ROB: Oh, hey, Meta. I heard Llama's weights leaked. That's rough, man. Information security's hard. How you holding up? META: Oh, we're great. Yeah, we're fine. We... actually, that was deliberate. We meant to do that. ROB MILES: Oh, really? META: Yeah... well, the second time anyway. It's called open source. Look it up. ROB MILES: Oh. Well, I love free and open source software, but do those principles really apply to network weights? How does that work? META: Open source is good for users because it lets them read the source code and see what the program is really doing and how it works. ROB MILES: Wait, have you found a way to tell how a model works by looking at its weights? META: No. But, it lets developers all over the world spot bugs in the code and submit patches. ROB: Wait, people are fixing bugs in Llama's weights? META: Well, no. People can fine tune it themselves, though. ROB: ?? Other companies offer fine tuning through APIs. ... So, hang on, if you can't actually read the code and know what it's doing, then network weights are effectively a compiled binary. So, in what sense is this open source? Why not call it like public weights? Why call it open source at all? META: I love open source. ROB: Well, I know a lot of your employees do, but you don't love anything. You're a giant corporation. What's in it for you? META: I love, love open source.

AI Notkilleveryoneism Memes ⏸️

107,362 views • 2 years ago

I genuinely don't understand why everyone isn't using this yet. Andrej Karpathy, OpenAI co-founder, posted a simple idea that went massively viral: Stop using AI to write code. Use it to build a second brain. You point Claude Code at a folder. Drop in any source: an article, a transcript, a PDF. Claude reads it, links it, files it into a living wiki of everything you know. It compounds like interest. The more you feed it, the smarter it gets. Here's the whole thing: 1) Install Obsidian 2) Create a vault 3) Open it in Claude Code 4) Paste Karpathy's wiki idea and tell Claude to build it 5) Claude makes three folders: - raw (for sources) - wiki (for its pages) - CLAUDE. md (that runs it) 6) Drop any source into raw and say: "ingest this" 7) Ask questions across everything, forever Five minutes to set up and you never start from a blank chat again. Full step by step guide below.

I genuinely don't understand why everyone isn't using this yet. Andrej Karpathy, OpenAI co-founder, posted a simple idea that went massively viral: Stop using AI to write code. Use it to build a second brain. You point Claude Code at a folder. Drop in any source: an article, a transcript, a PDF. Claude reads it, links it, files it into a living wiki of everything you know. It compounds like interest. The more you feed it, the smarter it gets. Here's the whole thing: 1) Install Obsidian 2) Create a vault 3) Open it in Claude Code 4) Paste Karpathy's wiki idea and tell Claude to build it 5) Claude makes three folders: - raw (for sources) - wiki (for its pages) - CLAUDE. md (that runs it) 6) Drop any source into raw and say: "ingest this" 7) Ask questions across everything, forever Five minutes to set up and you never start from a blank chat again. Full step by step guide below.

CyrilXBT

321,125 views • 29 days ago

I got curious how compaction works as a PM, so I did some brain surgery on Claude Code: (Anthropic's been doing really interesting work on context editing - they showed Claude Opus playing Settlers of Catan for 75+ minutes in a single thread by constantly editing the context instead of starting fresh. When I saw that Claude Code has a compaction command with optional custom instructions, I wanted to understand what's actually happening.) Abhishek Katiyar and Aman Khan gave me the key tip: Claude Code stores all your conversation history as text files on your computer. Open a new directory and give Claude Code a task. Here's how to watch compaction happening: 1. Go to your user's root directory 2. Press Command+Shift+Period (Mac) to show hidden folders 3. Navigate to ~/.claude/projects/ 4. Find your project folder and use Cursor/VSCode to open it (there's a reason) 5. Install the JSONL Gazelle plugin (open source, thank you Gabor Cselle!) 6. Open the most recent JSONL file - each row is a message in your conversation 7. Run the compact command in Claude Code with custom instructions 8. Watch what happens in the file What I learned: When you compact, Claude Code doesn't just summarize and delete everything. It creates a "compact boundary" in the conversation file, writes a summary of what happened before, but keeps the full original conversation (!!!!) The new thread can still retrieve any details from before compaction if needed. That is so damn cool. Why this matters: What you're getting in Claude Code is similar to what Anthropic ships in their developer SDK - so inspecting your daily tools is how you build real product intuition. The best way to understand AI systems is to open them up and look inside. Everything is text files.

I got curious how compaction works as a PM, so I did some brain surgery on Claude Code: (Anthropic's been doing really interesting work on context editing - they showed Claude Opus playing Settlers of Catan for 75+ minutes in a single thread by constantly editing the context instead of starting fresh. When I saw that Claude Code has a compaction command with optional custom instructions, I wanted to understand what's actually happening.) Abhishek Katiyar and Aman Khan gave me the key tip: Claude Code stores all your conversation history as text files on your computer. Open a new directory and give Claude Code a task. Here's how to watch compaction happening: 1. Go to your user's root directory 2. Press Command+Shift+Period (Mac) to show hidden folders 3. Navigate to ~/.claude/projects/ 4. Find your project folder and use Cursor/VSCode to open it (there's a reason) 5. Install the JSONL Gazelle plugin (open source, thank you Gabor Cselle!) 6. Open the most recent JSONL file - each row is a message in your conversation 7. Run the compact command in Claude Code with custom instructions 8. Watch what happens in the file What I learned: When you compact, Claude Code doesn't just summarize and delete everything. It creates a "compact boundary" in the conversation file, writes a summary of what happened before, but keeps the full original conversation (!!!!) The new thread can still retrieve any details from before compaction if needed. That is so damn cool. Why this matters: What you're getting in Claude Code is similar to what Anthropic ships in their developer SDK - so inspecting your daily tools is how you build real product intuition. The best way to understand AI systems is to open them up and look inside. Everything is text files.

Tal Raviv

57,910 views • 6 months ago

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

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

Avi Chawla

455,742 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)

42,501 views • 29 days ago

We trained a robot dog to balance and walk on top of a yoga ball purely in simulation, and then transfer zero-shot to the real world. No fine-tuning. Just works. I’m excited to announce DrEureka, an LLM agent that writes code to train robot skills in simulation, and writes more code to bridge the difficult simulation-reality gap. It fully automates the pipeline from new skill learning to real-world deployment. The Yoga ball task is particularly hard because it is not possible to accurately simulate the bouncy ball surface. Yet DrEureka has no trouble searching over a vast space of sim-to-real configurations, and enables the dog to steer the ball on various terrains, even walking sideways! Traditionally, the sim-to-real transfer is achieved by domain randomization, a tedious process that requires expert human roboticists to stare at every parameter and adjust by hand. Frontier LLMs like GPT-4 have tons of built-in physical intuition for friction, damping, stiffness, gravity, etc. We are (mildly) surprised to find that DrEureka can tune these parameters competently and explain its reasoning well. DrEureka builds on our prior work Eureka, the algorithm that teaches a 5-finger robot hand to do pen spinning. It takes one step further on our quest to automate the entire robot learning pipeline by an AI agent system. One model that outputs strings will supervise another model that outputs torque control. We open-source everything! Welcome you all to check out the paper, more videos, and try the codebase today: Code:

We trained a robot dog to balance and walk on top of a yoga ball purely in simulation, and then transfer zero-shot to the real world. No fine-tuning. Just works. I’m excited to announce DrEureka, an LLM agent that writes code to train robot skills in simulation, and writes more code to bridge the difficult simulation-reality gap. It fully automates the pipeline from new skill learning to real-world deployment. The Yoga ball task is particularly hard because it is not possible to accurately simulate the bouncy ball surface. Yet DrEureka has no trouble searching over a vast space of sim-to-real configurations, and enables the dog to steer the ball on various terrains, even walking sideways! Traditionally, the sim-to-real transfer is achieved by domain randomization, a tedious process that requires expert human roboticists to stare at every parameter and adjust by hand. Frontier LLMs like GPT-4 have tons of built-in physical intuition for friction, damping, stiffness, gravity, etc. We are (mildly) surprised to find that DrEureka can tune these parameters competently and explain its reasoning well. DrEureka builds on our prior work Eureka, the algorithm that teaches a 5-finger robot hand to do pen spinning. It takes one step further on our quest to automate the entire robot learning pipeline by an AI agent system. One model that outputs strings will supervise another model that outputs torque control. We open-source everything! Welcome you all to check out the paper, more videos, and try the codebase today: Code:

Jim Fan

908,762 views • 2 years ago