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.

This is Partmode. is free and open-source, browser-based parametric CAD with a SolidWorks-style workflow: constrained sketches, editable feature history, parts, structured assemblies, exact B-rep geometry, production drawings, and standard CAD interchange. Built for both people and agents. - Free & Opensource - Browser Based - Agent first CAD Use... show more

sphinx

65,384 subscribers

56,485 views • 1 month ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

39 Comments

sphinx1 month ago

Repo:

sphinx1 month ago

Idea Genesis: BOMwiki 3D Models and CAD files Share your 3d models and CAD files freely

sphinx1 month ago

update: the site is slow due to traffic

engineeredX1 month ago

Bro You take this and generate gcode + part setups + strategies + tool recommendations + machine parameters You’d be surprised how easy it is to do something called adaptive control to measure the read and speed of the tool cutting into the part to automate the whole process. Few.

sphinx1 month ago

f e w

Dollar Extra1 month ago

Ha, I made something very similar! Great minds…

Jake Fitzgerald1 month ago

so good!!

Matt Ferraro1 month ago

Are you using OpenCascade? How are you handling the topo naming problem?

AI Mastery Guide1 month ago

Free, open source, and agent first CAD, that's a strong combo.

Karan1 month ago

@VishakhRanotra @munshianiket1

dwasf1 month ago

I am going to contribute.

Arrow1 month ago

Nice ui!

Reindustrialize Who's Who1 month ago

Caveat: AGPL-3 = the most viral license. Fine for some, hostile to others.

sphinx1 month ago

this product needs a community effort. agpl-3 ensures hosted modifications remain open. improvements to hosted PartMode should remain open source.

Reindustrialize Who's Who1 month ago

Apache, BSD, MIT, public domain, etc. all support community effort -- both in theory and in reality as proven by decades of experience. (Of course everyone is free to choose to make code available on whatever license they like, subject to any included code. And others are free to warn people about the consequences.)

Tim Reha1 month ago

Love it nice job 😁

Kotei1 month ago

Love it bro , My Cad sometimes hangs but this runs smoothly.

Jake Dahn1 month ago

ooo, love the name! congrats on shipping

Johnny1 month ago

Like

yash 👨‍💻1 month ago

is my claude+freecad fine or do i really need this?

sphinx1 month ago

should be 100% fine tbh

Carlos A. Wong1 month ago

By the way have you seen @kirbytheodor ‘s repo?

Steven Cheng1 month ago

Browser-based B-rep is tough. How does it handle complex assemblies without lagging? SolidWorks runs locally for a reason.

BigTech1 month ago

oh wow

Shawn Cutter1 month ago

I’ll check it out. I am looking to build a hyperscale datacenter campus

sphinx1 month ago

>hyperscale datacenter campus where ?

Shawn Cutter1 month ago

Ohio

Shadow Defense1 month ago

@10_X_eng

Harshal1 month ago

love it

Steven Cheng1 month ago

Browser-based B-rep is tough. Curious how you handle constraint solving latency for agents.

Lee Go Good1 month ago

how is it compared to freecad?

sphinx1 month ago

abundance. let there be abundant CAD.

devalopr1 month ago

Nice work! I'll test it out

安叫兽|Bird🕊️ 🔶 BNB1 month ago

浏览器里跑这套工作流还挺狠的

BGLO1 month ago

Use an agent to drive it? I didn't understand. Anybody explain please.

Diego Pullano1 month ago

can you make a partsmode x account?

LandonCryptoExplr1 month ago

Most mechanical engineering is repetitive dimension changes on similar parts. Agentic CAD has a bigger market than people think.

Zaky Vids1 month ago

@protosphinx Are there any tutorials on how to use the platform how to create 3d models etc I actually have never used a cad application which is why I ask Thankyou

Engineering Randomness1 month ago

Still uses OCCT as a kernel

Related Videos

I built an autonomous 3D Python Game Visulizer Agent team with browser use and DeepSeek R1. It has 4 AI agents working as a team to open, code, run, and visualize the game in the browser - all on autopilot. 100% Opensource code with step-by-step tutorial.

I built an autonomous 3D Python Game Visulizer Agent team with browser use and DeepSeek R1. It has 4 AI agents working as a team to open, code, run, and visualize the game in the browser - all on autopilot. 100% Opensource code with step-by-step tutorial.

Shubham Saboo

20,047 views • 1 year 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 • 2 months ago

Mechanical CAD might be one of the first jobs MCP quietly wrecks. This guy connects an AI agent to Autodesk Fusion, gives it the dimensions for a snap-fit brick, and basically stops modeling. The agent builds the actual CAD part, adds the studs, hollows the underside, calculates the wall thickness and center support, then modifies the real Fusion model when asked. Then it checks the geometry and rounds the exposed edges. This is not text-to-3D. This is AI operating Autodesk Fusion like a junior CAD engineer. If this gets reliable, memorizing every tool in Fusion starts looking a lot less valuable than knowing what the part actually needs to do.

Mechanical CAD might be one of the first jobs MCP quietly wrecks. This guy connects an AI agent to Autodesk Fusion, gives it the dimensions for a snap-fit brick, and basically stops modeling. The agent builds the actual CAD part, adds the studs, hollows the underside, calculates the wall thickness and center support, then modifies the real Fusion model when asked. Then it checks the geometry and rounds the exposed edges. This is not text-to-3D. This is AI operating Autodesk Fusion like a junior CAD engineer. If this gets reliable, memorizing every tool in Fusion starts looking a lot less valuable than knowing what the part actually needs to do.

Rina

14,531 views • 1 month ago

introducing astra: an agentic browser for your phone this is an early beta release, it includes: > sign in with anthropic > no data collection > a full computer use agent astra is free to use. link below. ps: 10% of profit goes to potocki

introducing astra: an agentic browser for your phone this is an early beta release, it includes: > sign in with anthropic > no data collection > a full computer use agent astra is free to use. link below. ps: 10% of profit goes to potocki

kyon

31,468 views • 9 months ago

🎉 Introducing 𝙾𝚙𝚎𝚗𝙼𝚞𝚜𝚎 An open source, self-hostable personal assistant that works with any agent harness. Includes: - Computer use: browser, terminal & files - Connectors for your personal apps - Ideas, goals & progress tracking - Built for Mobile and Web Repo → Powered by CopilotKit🪁 and AG-UI. Clone this template and customize it however you want.

🎉 Introducing 𝙾𝚙𝚎𝚗𝙼𝚞𝚜𝚎 An open source, self-hostable personal assistant that works with any agent harness. Includes: - Computer use: browser, terminal & files - Connectors for your personal apps - Ideas, goals & progress tracking - Built for Mobile and Web Repo → Powered by CopilotKit🪁 and AG-UI. Clone this template and customize it however you want.

Atai Barkai

871,400 views • 1 day 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 • 6 months ago

The scary part about AI in CAD is not that GPT can extrude a shape. It is that it can now build a mechanism where multiple parts actually have to agree with each other. Using GPT + Autodesk Fusion MCP, this project turns into a mechanical iris assembly with a base plate, eight overlapping blades, a drive ring, a cover, mounting holes, and relationships between the components. One blade is easy. The annoying part is repeating it around the same center, keeping every pivot aligned, fitting the mechanism between the surrounding plates, and making the whole assembly stay coherent as more geometry gets added. That is where MCP starts getting interesting. GPT is no longer treating Fusion like a place to dump some 3D geometry. It is working inside the actual CAD structure, where components, relationships, repeated parts, and the assembly itself all matter. That is a much bigger deal than text-to-3D. Because once an AI agent can reliably build and modify mechanisms instead of isolated shapes, a surprisingly large chunk of mechanical CAD starts looking like something you describe, inspect, and correct rather than model feature by feature.

The scary part about AI in CAD is not that GPT can extrude a shape. It is that it can now build a mechanism where multiple parts actually have to agree with each other. Using GPT + Autodesk Fusion MCP, this project turns into a mechanical iris assembly with a base plate, eight overlapping blades, a drive ring, a cover, mounting holes, and relationships between the components. One blade is easy. The annoying part is repeating it around the same center, keeping every pivot aligned, fitting the mechanism between the surrounding plates, and making the whole assembly stay coherent as more geometry gets added. That is where MCP starts getting interesting. GPT is no longer treating Fusion like a place to dump some 3D geometry. It is working inside the actual CAD structure, where components, relationships, repeated parts, and the assembly itself all matter. That is a much bigger deal than text-to-3D. Because once an AI agent can reliably build and modify mechanisms instead of isolated shapes, a surprisingly large chunk of mechanical CAD starts looking like something you describe, inspect, and correct rather than model feature by feature.

Rina

32,398 views • 1 month ago

so I started with FreeCAD, since i am a linux guy, haven't touched windows since the past 8 years. Also I did this online course from Uni of California Irvine on "building your hardware for your embedded and IoT projects" which had FreeCAD as the main CAD software. FreeCAD was free, and fun, yeah a bit buggy sometimes but gets the job done, since initially all the CAD work i had was just builidng cases, or mounts, or some light hobby stuff. So FreeCAD did just fine. Then I joined a company as a product engineer where I worked with LiFePo4 home energy storage battery packs and was responsible for all the modules of the pack (Cells, BMS, MCUs, Touch Display ) mainly the embedded system. Since I was the product engineer, I'd have back and forth convos with the CAD designers off the battery pack box/casing. I didn't really do any CAD work on that project, tho it seemed really interesting to me. They used Solidworks, and I installed windows for it(swallowing that was difficult); to do Solidworks in my free time which I hardly got. I tried Solidworks and I kinda liked it. But then I quit the job and started working on my SAAS products. A few months into it, it's not fun anymore, slowly getting started with CAD and eventually to electronics to hardware products. Now, I want to go about CAD. I'll be doing a 30 days CAD challenge increasing in complexity and will be sharing daily progress here! It was day 2; I designer a bolt and a nut. I'm going with Fusion 360 for now, coz i like the UI/UX and the hobbyist version is free. So yeah. This is so much fun, i completely lost track of time while doing it. Gemini on the side is alot helpful.

so I started with FreeCAD, since i am a linux guy, haven't touched windows since the past 8 years. Also I did this online course from Uni of California Irvine on "building your hardware for your embedded and IoT projects" which had FreeCAD as the main CAD software. FreeCAD was free, and fun, yeah a bit buggy sometimes but gets the job done, since initially all the CAD work i had was just builidng cases, or mounts, or some light hobby stuff. So FreeCAD did just fine. Then I joined a company as a product engineer where I worked with LiFePo4 home energy storage battery packs and was responsible for all the modules of the pack (Cells, BMS, MCUs, Touch Display ) mainly the embedded system. Since I was the product engineer, I'd have back and forth convos with the CAD designers off the battery pack box/casing. I didn't really do any CAD work on that project, tho it seemed really interesting to me. They used Solidworks, and I installed windows for it(swallowing that was difficult); to do Solidworks in my free time which I hardly got. I tried Solidworks and I kinda liked it. But then I quit the job and started working on my SAAS products. A few months into it, it's not fun anymore, slowly getting started with CAD and eventually to electronics to hardware products. Now, I want to go about CAD. I'll be doing a 30 days CAD challenge increasing in complexity and will be sharing daily progress here! It was day 2; I designer a bolt and a nut. I'm going with Fusion 360 for now, coz i like the UI/UX and the hobbyist version is free. So yeah. This is so much fun, i completely lost track of time while doing it. Gemini on the side is alot helpful.

Mustafa

20,127 views • 8 months ago

The interesting part about GPT in CAD is not that it can make a shape. It is that through MCP, GPT can work directly inside Onshape and turn a plain-English description into actual CAD geometry you can keep editing. In this case, the model builds a radial mechanical part with a central hub, repeated ribs, an outer ring, and a full pattern of mounting holes, all inside the real Onshape document. There is no fake “3D-looking” render hiding the hard part. The geometry exists in the CAD workspace, can be rotated, inspected, modified, and used as the starting point for the next iteration. That changes the workflow from manually clicking through every feature to describing the structure, letting GPT build the first pass, then correcting what matters. Once MCP gets reliable enough, the boring part of CAD starts looking less like modeling and more like supervising.

The interesting part about GPT in CAD is not that it can make a shape. It is that through MCP, GPT can work directly inside Onshape and turn a plain-English description into actual CAD geometry you can keep editing. In this case, the model builds a radial mechanical part with a central hub, repeated ribs, an outer ring, and a full pattern of mounting holes, all inside the real Onshape document. There is no fake “3D-looking” render hiding the hard part. The geometry exists in the CAD workspace, can be rotated, inspected, modified, and used as the starting point for the next iteration. That changes the workflow from manually clicking through every feature to describing the structure, letting GPT build the first pass, then correcting what matters. Once MCP gets reliable enough, the boring part of CAD starts looking less like modeling and more like supervising.

Rina

16,772 views • 1 month ago

1/ We’ve built Cosift, an open source collaborative index for agents. Whenever an agent requires a piece of data from the web, it can also index it in Cosift for easier later retrieval. Agents require the same data repeatedly, and do the costly and time consuming work every time. Cosift gives agents a collaborative space where they can index this data for easy retrieval. It’s open source and free, and its development is based on the 400B exchanges that were made so far on Pilot Protocol.

1/ We’ve built Cosift, an open source collaborative index for agents. Whenever an agent requires a piece of data from the web, it can also index it in Cosift for easier later retrieval. Agents require the same data repeatedly, and do the costly and time consuming work every time. Cosift gives agents a collaborative space where they can index this data for easy retrieval. It’s open source and free, and its development is based on the 400B exchanges that were made so far on Pilot Protocol.

Razvan Roman

75,176 views • 5 days ago

This guy literally built an AI job-search system for Claude Code that analyzed 740+ job listings, and it actually landed him a Head of Applied AI role. Even better: it is now open-source. The system scans career pages, evaluates your fit, and generates ATS-optimized PDFs automatically. The project includes: → 14 specialized agent modes → A Go-based terminal dashboard → ATS-optimized PDF generation with Playwright → 45+ companies pre-configured (Anthropic, OpenAI, Stripe) This is a perfect example of AI eliminating the grind of job hunting instead of replacing people. 100% free and open-source. Link to the repo below ↓

This guy literally built an AI job-search system for Claude Code that analyzed 740+ job listings, and it actually landed him a Head of Applied AI role. Even better: it is now open-source. The system scans career pages, evaluates your fit, and generates ATS-optimized PDFs automatically. The project includes: → 14 specialized agent modes → A Go-based terminal dashboard → ATS-optimized PDF generation with Playwright → 45+ companies pre-configured (Anthropic, OpenAI, Stripe) This is a perfect example of AI eliminating the grind of job hunting instead of replacing people. 100% free and open-source. Link to the repo below ↓

Charly Wargnier ♨️

13,115 views • 2 months ago

Here is a step-by-step introduction to building a workflow with a custom AI agent that uses MCP. I explain every component in the video: 1. Building the MCP server 2. Building the agent and an MCP client 3. Building a workflow that uses the agent The goal is simple: Generate a dialogue between two people and make one yell and the other answer with sarcasm. Kestra is sponsoring this video. They are an open-source orchestration platform (repo link below), and I used them to build the workflow that connects every component.

Here is a step-by-step introduction to building a workflow with a custom AI agent that uses MCP. I explain every component in the video: 1. Building the MCP server 2. Building the agent and an MCP client 3. Building a workflow that uses the agent The goal is simple: Generate a dialogue between two people and make one yell and the other answer with sarcasm. Kestra is sponsoring this video. They are an open-source orchestration platform (repo link below), and I used them to build the workflow that connects every component.

Santiago

51,527 views • 1 year ago

Today we're launching It gives any AI agent ready-to-use security context for thousands of open source projects, built from each project's commit history of security fixes and its disclosed CVEs. Useful whether your agent is writing code or reviewing it for bugs. Free, no auth, over MCP and API.

Today we're launching It gives any AI agent ready-to-use security context for thousands of open source projects, built from each project's commit history of security fixes and its disclosed CVEs. Useful whether your agent is writing code or reviewing it for bugs. Free, no auth, over MCP and API.

ProjectDiscovery

41,205 views • 2 months ago

AI agents are becoming increasingly capable of taking actions beyond the chat window and interacting with tools in the real world, such as web browsers. We explored this capability by having an AI agent present one of our interactive web-based demos. In this video, it's presenting our election interference demo. This agent is a Cursor coding agent and is equipped with tools to read and interact with the browser (using Playwright) and perform text-to-speech (with ElevenLabs), in addition to the standard Cursor tools.

AI agents are becoming increasingly capable of taking actions beyond the chat window and interacting with tools in the real world, such as web browsers. We explored this capability by having an AI agent present one of our interactive web-based demos. In this video, it's presenting our election interference demo. This agent is a Cursor coding agent and is equipped with tools to read and interact with the browser (using Playwright) and perform text-to-speech (with ElevenLabs), in addition to the standard Cursor tools.

CivAI

18,428 views • 9 months ago

Yesterday, Block released a new open-source agent workspace called Berd. Unlike Buzz, this app's focus is on the solo builder working with multiple agent harnesses (who likes this funky style) I made a quick demo showing how to install it, start talking to specialized agents, and even make your own agent based on your needs (mine being cat-themed visualizations). Check it out!

Yesterday, Block released a new open-source agent workspace called Berd. Unlike Buzz, this app's focus is on the solo builder working with multiple agent harnesses (who likes this funky style) I made a quick demo showing how to install it, start talking to specialized agents, and even make your own agent based on your needs (mine being cat-themed visualizations). Check it out!

tonbi

22,672 views • 1 month ago

GPT-6 Astra's 3D modeling is everywhere and it's genuinely impressive. It's generating detailed, editable meshes in Blender straight from a prompt, one developer even reconstructed a steam train from an old drawing in minutes. But a mesh isn't a part. It doesn't have wall thickness, tolerances, or a bore that fits a standard bearing. It looks right it doesn't have to BE right. That's the gap CadXStudio exists for. Not artistic 3D - manufacturing-ready parametric CAD. Describe a part in plain language, get back a real model: STEP export, editable parametric features, assemblies that actually mate, drawings a machinist can use. "Looks like a part" and "is a part" are two different problems. We're solving the second one. If you can describe it, you can build it.

GPT-6 Astra's 3D modeling is everywhere and it's genuinely impressive. It's generating detailed, editable meshes in Blender straight from a prompt, one developer even reconstructed a steam train from an old drawing in minutes. But a mesh isn't a part. It doesn't have wall thickness, tolerances, or a bore that fits a standard bearing. It looks right it doesn't have to BE right. That's the gap CadXStudio exists for. Not artistic 3D - manufacturing-ready parametric CAD. Describe a part in plain language, get back a real model: STEP export, editable parametric features, assemblies that actually mate, drawings a machinist can use. "Looks like a part" and "is a part" are two different problems. We're solving the second one. If you can describe it, you can build it.

CadX Studio

18,181 views • 17 days ago

NO WAY THIS IS ACTUALLY FREE AND OPEN-SOURCE.. PilotDeck just dropped an open-source agent OS with persistent workspaces, autonomous execution, and intelligent model routing. It routes hard tasks to stronger models and simple tasks to cheaper agents, so you stop burning premium tokens on work that doesn’t need them. Tutorial below:

NO WAY THIS IS ACTUALLY FREE AND OPEN-SOURCE.. PilotDeck just dropped an open-source agent OS with persistent workspaces, autonomous execution, and intelligent model routing. It routes hard tasks to stronger models and simple tasks to cheaper agents, so you stop burning premium tokens on work that doesn’t need them. Tutorial below:

Robin Delta

39,717 views • 3 months ago

Hermes just got a local model nobody is talking about. And it runs your entire workflow for free. You do not need to pay for smart agents anymore. A developer just dropped a free brain called Karnis on Hugging Face. It is built perfectly for Hermes. It runs right on your computer using LM Studio. It watches real agents work and copies their exact steps. It edits files and runs commands for you. Just download LM Studio, search for Karnis, and connect it to Hermes. Your private agent is ready to work.

Hermes just got a local model nobody is talking about. And it runs your entire workflow for free. You do not need to pay for smart agents anymore. A developer just dropped a free brain called Karnis on Hugging Face. It is built perfectly for Hermes. It runs right on your computer using LM Studio. It watches real agents work and copies their exact steps. It edits files and runs commands for you. Just download LM Studio, search for Karnis, and connect it to Hermes. Your private agent is ready to work.

Julian Goldie SEO

22,365 views • 5 months ago

Someone paid $6,000 (!) to get OpenClaw setup. So I built a free, open-source alternative: > OpenClaw Operator It's an agent skill + AGENTS.md/CLAUDE.md file that gives Codex/Claude Code the playbooks + validation flow needed to configure your local OpenClaw install. You open your OpenClaw repo/workspace in your coding agent and say things like: - “set up a cron job” - “create a custom skill” - “fix my provider config” - “troubleshoot this install and validate it” Nothing magical. Uses context from the OpenClaw open-source repo + docs to provide an effective skill. Includes: - SKILL.md - AGENTS.md/CLAUDE.md - validation checklist - task playbooks Free and open source. Contributions welcome. Demo below. Repo in reply.

Someone paid $6,000 (!) to get OpenClaw setup. So I built a free, open-source alternative: > OpenClaw Operator It's an agent skill + AGENTS.md/CLAUDE.md file that gives Codex/Claude Code the playbooks + validation flow needed to configure your local OpenClaw install. You open your OpenClaw repo/workspace in your coding agent and say things like: - “set up a cron job” - “create a custom skill” - “fix my provider config” - “troubleshoot this install and validate it” Nothing magical. Uses context from the OpenClaw open-source repo + docs to provide an effective skill. Includes: - SKILL.md - AGENTS.md/CLAUDE.md - validation checklist - task playbooks Free and open source. Contributions welcome. Demo below. Repo in reply.

Dan McAteer

17,859 views • 6 months ago

Finally, a browser automation framework for Agents that actually works in production (open-source)! Typical browser automation tools like Selenium or Playwright require you to hard-code automation. These are brittle since one change in the website can disrupt the full workflow. On the other hand, high-level Agents like OpenAI Operator can be unpredictable in production. Stagehand is an open-source framework that bridges the gap between: - brittle traditional automation like Playwright, Selenium, etc. and - unpredictable full-agent solutions like OpenAI Operator. Key features: - Use AI when you want to navigate unfamiliar pages. - Use code (Playwright) when you know exactly what to do. - Preview AI actions before running them. - Cache repeatable actions to save tokens. - Compatible with SOTA computer use models with just one line of code. - Available in both Python and TypeScript SDK. Stagehand also has an open-source MCP server. Find a link to the repo in the comments! 👉 Over to you: Would you use this instead of Selenium?

Finally, a browser automation framework for Agents that actually works in production (open-source)! Typical browser automation tools like Selenium or Playwright require you to hard-code automation. These are brittle since one change in the website can disrupt the full workflow. On the other hand, high-level Agents like OpenAI Operator can be unpredictable in production. Stagehand is an open-source framework that bridges the gap between: - brittle traditional automation like Playwright, Selenium, etc. and - unpredictable full-agent solutions like OpenAI Operator. Key features: - Use AI when you want to navigate unfamiliar pages. - Use code (Playwright) when you know exactly what to do. - Preview AI actions before running them. - Cache repeatable actions to save tokens. - Compatible with SOTA computer use models with just one line of code. - Available in both Python and TypeScript SDK. Stagehand also has an open-source MCP server. Find a link to the repo in the comments! 👉 Over to you: Would you use this instead of Selenium?

Avi Chawla

101,419 views • 1 year ago