Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

Wow so Google has just open sourced a tool to automate ANY task on mobile ARTEMIS turns prompts into automation: - 99%+ success rate (!!) - Integrates w/ Codex, Claude Code, Antigravity - Automates workflows + captures logs And the roadmap is VERY interesting: They want to add an... show more

Paul Couvert

220,718 subscribers

58,026 Aufrufe • vor 16 Tagen •via X (Twitter)

Bildung Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

25 Kommentare

Profilbild von Paul Couvert

Paul Couvertvor 16 Tagen

It has a MCP integration so basically any coding agent will be able to use it (Cursor, Cordex, Antigravity, Claude Code, etc.) Here's the GitHub repo:

Profilbild von Nick Beagley

Nick Beagleyvor 16 Tagen

Looks cool. It hit a bit of controversy though:

Profilbild von Paul Couvert

Paul Couvertvor 15 Tagen

Interesting... hope they'll clarify soon

Profilbild von Lennox

Lennoxvor 15 Tagen

同感。生产里最先炸的往往不是模型智商，是工具权限边界没划清。

Profilbild von Stephan

Stephanvor 16 Tagen

I do seem to miss a lot of your post on Grok and Grok Bot

Profilbild von Paul Couvert

Paul Couvertvor 15 Tagen

Grok Bot is good but tbh we have better alternative for now. Looking forward a more efficient model in it.

Profilbild von vairisk ☀️🇱🇻

vairisk ☀️🇱🇻vor 15 Tagen

It open sourced because initially stole? Is it same tool you are talking about that google was caught stealing and rewriting authors in repo?

Profilbild von Paul Couvert

Paul Couvertvor 15 Tagen

I wasn't aware of that before reading a previous comment. Hope they'll clarify the situation.

Profilbild von vairisk ☀️🇱🇻

vairisk ☀️🇱🇻vor 15 Tagen

They will not clarify - they already locked option to check older commits revealing truth; now you can find only proves already gathered on i-net but when company like google does that - its clear they stole.

Profilbild von Paul Couvert

Paul Couvertvor 15 Tagen

Yeah not a good practice, agree.

Profilbild von Alek

Alekvor 16 Tagen

ARTEMIS — can I inspect the captured logs per run?

Profilbild von Paul Couvert

Paul Couvertvor 16 Tagen

Of course you can!

Profilbild von Sage

Sagevor 15 Tagen

Google has been shipping amazing AI products non-stop. If they could just get their shit together on the product and UX front they'd 10x their product usage.

Profilbild von Enter Matrix

Enter Matrixvor 16 Tagen

@grok mi spieghi come usarlo?

Profilbild von Build Fast with AI

Build Fast with AIvor 15 Tagen

would this work with a local 4b model that can run on an android @grok

Profilbild von Jimmy Otis #TruthMatters #EndCronyism

Jimmy Otis #TruthMatters #EndCronyismvor 16 Tagen

I'm sure samsung will block it.

Profilbild von Paul Couvert

Paul Couvertvor 16 Tagen

They can't, it'll work on any Android device (iOS coming) with usb debugging enabled

Profilbild von Jimmy Otis #TruthMatters #EndCronyism

Jimmy Otis #TruthMatters #EndCronyismvor 16 Tagen

They "can't"? I do not think you understand Samsung OEM.

Profilbild von Paul Couvert

Paul Couvertvor 16 Tagen

Well if they're blocking adb they're also blocking all the devs from using their devices haha

Profilbild von Jimmy Otis #TruthMatters #EndCronyism

Jimmy Otis #TruthMatters #EndCronyismvor 16 Tagen

I will try. There are many apps that do not work via ADB either. Clearly this is not targeting mainstream.

Profilbild von AI Mastery Guide

AI Mastery Guidevor 16 Tagen

99% success rate is a big claim

Profilbild von Paul Couvert

Paul Couvertvor 15 Tagen

And yet, here we are.

Profilbild von LocalLLM

LocalLLMvor 16 Tagen

On-device VLM for the privacy piece is the interesting bit. Are they aiming to keep the full automation loop local, or is the VLM only for the sensitive steps while the rest still phones home?

Profilbild von Paul Couvert

Paul Couvertvor 16 Tagen

It's on the roadmap for now so hard to say... but I hope it will be an end-to-end solution.

Profilbild von Jon Fletcher

Jon Fletchervor 15 Tagen

This is what I've been waiting for to get a better phone experience.

Ähnliche Videos

ANTHROPIC HAS AN OFFICIAL PROMPT LIBRARY FOR CLAUDE CODE and it's completely FREE. most people don't even know it exists, so they keep writing prompts from scratch every day. the prompts are ready to copy and paste, sorted by task and by role. > planning, debugging, code review, security, automation > every prompt comes with a note on how it works and why it wasn't put together by some random third party. the anthropic teams who use claude code every day wrote it, and it shows you what claude code can already do for you. link below👇

ANTHROPIC HAS AN OFFICIAL PROMPT LIBRARY FOR CLAUDE CODE and it's completely FREE. most people don't even know it exists, so they keep writing prompts from scratch every day. the prompts are ready to copy and paste, sorted by task and by role. > planning, debugging, code review, security, automation > every prompt comes with a note on how it works and why it wasn't put together by some random third party. the anthropic teams who use claude code every day wrote it, and it shows you what claude code can already do for you. link below👇

Dean W. Perkins

20,860 Aufrufe • vor 1 Tag

This might be the best agent I've seen yet. After raising $220M, H just introduced an agent that can execute any task from a prompt. Their "Runner H" can basically turn instructions into action with human-like precision. Features: ▸ Navigates web interfaces with pixel-level precision. ▸ Interprets pixels and text to understand screens and elements. ▸ Automates workflows for web testing, onboarding, and e-commerce. ▸ Adapts automatically to UI changes. ▸ Achieves a 67% success rate on WebVoyager, outperforming competitors. Architecture: ▸ Powered by a 2B-paramezer LLM for function calling and coding. ▸ Includes a 3B-parameter VLM for understanding graphical and text elements.

This might be the best agent I've seen yet. After raising $220M, H just introduced an agent that can execute any task from a prompt. Their "Runner H" can basically turn instructions into action with human-like precision. Features: ▸ Navigates web interfaces with pixel-level precision. ▸ Interprets pixels and text to understand screens and elements. ▸ Automates workflows for web testing, onboarding, and e-commerce. ▸ Adapts automatically to UI changes. ▸ Achieves a 67% success rate on WebVoyager, outperforming competitors. Architecture: ▸ Powered by a 2B-paramezer LLM for function calling and coding. ▸ Includes a 3B-parameter VLM for understanding graphical and text elements.

Lior Alexander

106,985 Aufrufe • vor 1 Jahr

Anthropic just released a talk on building headless automation with Claude Code. Presented by Sid Bidasaria, Member of Technical Staff at Anthropic live at Code with Claude on May 22, 2025 in San Francisco. Here is what the talk covers. Headless mode lets you run Claude Code without a person actively typing prompts from inside an automated script. Instead of a live session, a script calls Claude with a pre-written instruction using the -p flag. This opens the door for Claude Code to become a piece of a much larger, automated process. In plain terms: Claude Code stops being a tool you use and starts being a service that runs on its own. What this unlocks: Scheduled tasks: Run Claude Code on a cron schedule without anyone at a keyboard. Fix linting errors across an entire codebase. Automatically. Overnight. CI/CD integration: Trigger Claude Code as a step in your build process. Open a PR. Claude reviews it, flags issues, and pushes fixes before a human ever looks at it. GitHub automation: A project manager comments "Claude fix this" on a GitHub issue. Claude reads the request, finds the code, writes the fix, and opens the PR. Multi-machine workflows: One orchestrator dispatches tasks to multiple Claude Code instances running in parallel across different repos simultaneously. When you combine headless mode, hooks, and GitHub Actions, development teams can automate tasks that usually eat up significant time freeing senior engineers to focus on architectural problems while Claude handles the repetitive ones. If you use Claude Code for anything beyond single sessions this talk is worth 20 minutes of your time.

Anthropic just released a talk on building headless automation with Claude Code. Presented by Sid Bidasaria, Member of Technical Staff at Anthropic live at Code with Claude on May 22, 2025 in San Francisco. Here is what the talk covers. Headless mode lets you run Claude Code without a person actively typing prompts from inside an automated script. Instead of a live session, a script calls Claude with a pre-written instruction using the -p flag. This opens the door for Claude Code to become a piece of a much larger, automated process. In plain terms: Claude Code stops being a tool you use and starts being a service that runs on its own. What this unlocks: Scheduled tasks: Run Claude Code on a cron schedule without anyone at a keyboard. Fix linting errors across an entire codebase. Automatically. Overnight. CI/CD integration: Trigger Claude Code as a step in your build process. Open a PR. Claude reviews it, flags issues, and pushes fixes before a human ever looks at it. GitHub automation: A project manager comments "Claude fix this" on a GitHub issue. Claude reads the request, finds the code, writes the fix, and opens the PR. Multi-machine workflows: One orchestrator dispatches tasks to multiple Claude Code instances running in parallel across different repos simultaneously. When you combine headless mode, hooks, and GitHub Actions, development teams can automate tasks that usually eat up significant time freeing senior engineers to focus on architectural problems while Claude handles the repetitive ones. If you use Claude Code for anything beyond single sessions this talk is worth 20 minutes of your time.

Elias

14,096 Aufrufe • vor 4 Monaten

🚂 Introducing Agent Prompt Train 🚂 An open-sourced high-performance proxy that works with Claude Code to help turn it from a single-developer tool into a collaborative development platform. Claude Code changed the game. Now, Agent Prompt Train is here to help teams: ✅ Log every conversation for review ✅ Analyze & optimize prompts with AI ✅ Turn best practices into reusable team commands ✨ The payoff: Smarter prompts, faster learning, and shared knowledge across your whole team. 📖 Read more on the blog & test it out 👇

🚂 Introducing Agent Prompt Train 🚂 An open-sourced high-performance proxy that works with Claude Code to help turn it from a single-developer tool into a collaborative development platform. Claude Code changed the game. Now, Agent Prompt Train is here to help teams: ✅ Log every conversation for review ✅ Analyze & optimize prompts with AI ✅ Turn best practices into reusable team commands ✨ The payoff: Smarter prompts, faster learning, and shared knowledge across your whole team. 📖 Read more on the blog & test it out 👇

Moonsong Labs 🌙

21,523 Aufrufe • vor 1 Jahr

-> someone cloned claude -> design interface and -> made it completely free -> it's work on YouTube -> and also suitable for kids -> it’s called open design -> and it’s live on github -> same clean split-screen ui -> you get in claude artifacts -> prompt on the left, live -> design/code preview on -> the right, type what you -> want to build and it -> generates the ui in real -> time, but here’s the twist -> you pick the ai model -> not locked into one -> company, want to use -> gemini, mistral, llama, -> deepseek any model -> with an api work -> if you’re running local -> models with ollama -> that works too -> no subscription walls -> the big difference -> vs claude artifacts -> works with any free -> ai model you’re not -> paying $20/mo just to -> design, use free tiers -> local models, or whatever -> you already have access to -> fully local, your prompts -> and code never leave -> your machine unless -> you want them to -> no data training -> no cloud storage -> privacy by default -> no usage limits -> claude cuts you off -> after a few designs -> here you can generate, -> iterate, break things -> and rebuild all day -> the only limit is your -> don’t like how a button -> works, change it -> want to add your own -> components, go ahead -> you own the tool -> so if you’ve been gatekept -> by paywalls or worried -> about sensitive prompts -> going to some company’s -> servers, this fixes that. -> same workflow, more -> control, zero monthly fee

-> someone cloned claude -> design interface and -> made it completely free -> it's work on YouTube -> and also suitable for kids -> it’s called open design -> and it’s live on github -> same clean split-screen ui -> you get in claude artifacts -> prompt on the left, live -> design/code preview on -> the right, type what you -> want to build and it -> generates the ui in real -> time, but here’s the twist -> you pick the ai model -> not locked into one -> company, want to use -> gemini, mistral, llama, -> deepseek any model -> with an api work -> if you’re running local -> models with ollama -> that works too -> no subscription walls -> the big difference -> vs claude artifacts -> works with any free -> ai model you’re not -> paying $20/mo just to -> design, use free tiers -> local models, or whatever -> you already have access to -> fully local, your prompts -> and code never leave -> your machine unless -> you want them to -> no data training -> no cloud storage -> privacy by default -> no usage limits -> claude cuts you off -> after a few designs -> here you can generate, -> iterate, break things -> and rebuild all day -> the only limit is your -> don’t like how a button -> works, change it -> want to add your own -> components, go ahead -> you own the tool -> so if you’ve been gatekept -> by paywalls or worried -> about sensitive prompts -> going to some company’s -> servers, this fixes that. -> same workflow, more -> control, zero monthly fee

BeingInvested

12,134 Aufrufe • vor 4 Monaten

OpenAI has introduced a beta feature called Tasks for ChatGPT, allowing users to schedule reminders and actions at future times. This feature includes one-time reminders, recurring tasks such as daily check-ins or weekly reports, and automatic task execution like sending emails or drafting documents. It is seamlessly integrated with ChatGPT's core functions, enabling users to manage their workflows more efficiently. With Tasks, users can automate their routines and ensure they stay on top of commitments, making it an ideal tool for boosting productivity and streamlining work processes. #AI #Productivity #OpenAI #ChatGPT #Automation #FutureTech #Tasks #WorkSmart

OpenAI has introduced a beta feature called Tasks for ChatGPT, allowing users to schedule reminders and actions at future times. This feature includes one-time reminders, recurring tasks such as daily check-ins or weekly reports, and automatic task execution like sending emails or drafting documents. It is seamlessly integrated with ChatGPT's core functions, enabling users to manage their workflows more efficiently. With Tasks, users can automate their routines and ensure they stay on top of commitments, making it an ideal tool for boosting productivity and streamlining work processes. #AI #Productivity #OpenAI #ChatGPT #Automation #FutureTech #Tasks #WorkSmart

Wissam Hussein

20,675 Aufrufe • vor 1 Jahr

Introducing Agent Tincan. Let your AI agents ask each other for help. Your agents each have a superpower. Grok Bot is always on in the cloud. Muse makes phone calls and has access to Meta. Instinct runs in iMessage. Codex and Claude Code have your code. ChatGPT and Claude have your chats. But they can't talk to each other, so you're the copy-paste. Now they can, all securely over Tailscale. 📞 Ask Grok Bot to have Muse call the restaurant 🖼 Get an image from ChatGPT, from any agent 🔎 Pull a detail out of an old Claude chat 🛠 Talk to Codex on your primary development machine Runs on your own private Tailscale network. No open ports, nothing leaves it. Open source. Setup is agent-first: paste one message into your always-on agent and it sets up the rest.

Introducing Agent Tincan. Let your AI agents ask each other for help. Your agents each have a superpower. Grok Bot is always on in the cloud. Muse makes phone calls and has access to Meta. Instinct runs in iMessage. Codex and Claude Code have your code. ChatGPT and Claude have your chats. But they can't talk to each other, so you're the copy-paste. Now they can, all securely over Tailscale. 📞 Ask Grok Bot to have Muse call the restaurant 🖼 Get an image from ChatGPT, from any agent 🔎 Pull a detail out of an old Claude chat 🛠 Talk to Codex on your primary development machine Runs on your own private Tailscale network. No open ports, nothing leaves it. Open source. Setup is agent-first: paste one message into your always-on agent and it sets up the rest.

Matt Van Horn

50,380 Aufrufe • vor 6 Tagen

Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor - OpenCode, and 20+ more Beacon by Asymptote Labs continuously captures your agent history across harnesses and uses Jev to identify which runs are actually worth learning from. It then turns the highest-signal workflows, corrections, and debugging patterns into reusable skills. GitHub repo: (don’t forget to star it ⭐ ) Beacon preserves the complete session history. But preserving a run and learning from it are two different things. Most coding-agent sessions contain routine exploration, failed commands, and fixes that only apply to one task. The trace can remain available for inspection without turning every detail into guidance for future agents. Jev scores each run for evidence, reuse potential, and human correction signals. An application policy then decides whether to promote, review, or discard it. The recording shows this in action. Claude receives a coding task, modifies the implementation, and runs the tests. I then provide an edge-case correction, so Claude updates the code and adds regression coverage. Beacon automatically captures the complete session. Jev evaluates whether the correction contains a reusable engineering lesson. Once approved, that lesson becomes available to other coding agents working on the project. Since it works across harnesses: - Claude Code sessions can teach Codex. - Cursor debugging can improve OpenCode. So a problem solved by one agent should not need to be learned from scratch by another. If you want to dive deeper into Jev, I also wrote a hands-on guide to building this Jev-style decision path with open models, entirely locally. Read it below.

Another insane Jev use case! Jev is making it dramatically cheaper to evaluate what actually happened inside an agent run. And finally, someone open-sourced a self-improving memory layer that can put that signal to work across agent harnesses: - Claude Code - Codex - Cursor - OpenCode, and 20+ more Beacon by Asymptote Labs continuously captures your agent history across harnesses and uses Jev to identify which runs are actually worth learning from. It then turns the highest-signal workflows, corrections, and debugging patterns into reusable skills. GitHub repo: (don’t forget to star it ⭐ ) Beacon preserves the complete session history. But preserving a run and learning from it are two different things. Most coding-agent sessions contain routine exploration, failed commands, and fixes that only apply to one task. The trace can remain available for inspection without turning every detail into guidance for future agents. Jev scores each run for evidence, reuse potential, and human correction signals. An application policy then decides whether to promote, review, or discard it. The recording shows this in action. Claude receives a coding task, modifies the implementation, and runs the tests. I then provide an edge-case correction, so Claude updates the code and adds regression coverage. Beacon automatically captures the complete session. Jev evaluates whether the correction contains a reusable engineering lesson. Once approved, that lesson becomes available to other coding agents working on the project. Since it works across harnesses: - Claude Code sessions can teach Codex. - Cursor debugging can improve OpenCode. So a problem solved by one agent should not need to be learned from scratch by another. If you want to dive deeper into Jev, I also wrote a hands-on guide to building this Jev-style decision path with open models, entirely locally. Read it below.

Avi Chawla

290,485 Aufrufe • vor 10 Tagen

Turn any website into an AI-readable design system. Here's how: Google recently introduced the DESIGN.md specification: a file that helps AI agents understand a product’s design system. So we built a free tool for designers. Paste any website URL and Masumi’s DESIGN.md Generator extracts the brand’s colors, typography, components, spacing, and visual rules into an editable DESIGN.md file. Your designer can review it, tweak it, and hand it to Claude Code, Cursor, Codex, or any AI coding agent so the generated UI stays on-brand. Links below

albina

26,087 Aufrufe • vor 4 Monaten

🥧 Introducing GooeyPi - A GUI for the Pi Family of Agents. Supports: Pi, Oh-My-Pi (OMP), and Prime Agent Very excited to share this with you all. Being into local models, I wanted to have a separate harness for my local models so I don't have to constantly switch configs. And I didn't want to go back to the TUI (nerds). But, I didn't want to miss out on all the features that I know and love. Turns out, I didn't have to. I just needed to build it myself. So I did. Features include: > Fully featured GUI experience > Agentic Browser > Realtime Voice Agent > Voice transcription (local or API) > Computer Use > Automation Desk > Agent to Agent messaging > Ask Question Tool > Git Control > Terminal > Pets > and more I tried to capture all of the most popular features I could in this first pass, but we're only just getting started. Available in BETA on MacOS, Linux, and Windows. I need testers! I have only tested on Mac and Linux. If you want to help me with this project, please reach out. Available:

🥧 Introducing GooeyPi - A GUI for the Pi Family of Agents. Supports: Pi, Oh-My-Pi (OMP), and Prime Agent Very excited to share this with you all. Being into local models, I wanted to have a separate harness for my local models so I don't have to constantly switch configs. And I didn't want to go back to the TUI (nerds). But, I didn't want to miss out on all the features that I know and love. Turns out, I didn't have to. I just needed to build it myself. So I did. Features include: > Fully featured GUI experience > Agentic Browser > Realtime Voice Agent > Voice transcription (local or API) > Computer Use > Automation Desk > Agent to Agent messaging > Ask Question Tool > Git Control > Terminal > Pets > and more I tried to capture all of the most popular features I could in this first pass, but we're only just getting started. Available in BETA on MacOS, Linux, and Windows. I need testers! I have only tested on Mac and Linux. If you want to help me with this project, please reach out. Available:

am.will

162,855 Aufrufe • vor 1 Monat

THIS GUY OPENED A TINY PC AND SHOWED HOW A $1,800 GMKTEC EVO-X2 TURNS INTO A LOCAL AI SERVER not a cloud dashboard. not another $200/mo subscription. just one box on a desk, upgraded with storage, cleaner airflow, faster networking, and pointed at real local models. the numbers are what make it interesting. Claude Code Max is $200/mo, ChatGPT Pro is $200/mo, Cursor is another $20/mo. that is $5,040/year just to rent tools most people use for coding, research, summaries, and agents. EVO-X2 flips the setup because it has 128GB unified memory, Ryzen AI Max+ 395, and up to 110GB usable as VRAM on Linux. enough room for Qwen3-Coder 30B, Llama 70B, and 200B-class local models when speed is not the bottleneck. so the workflow becomes simple: buy the box once, install Linux, run the model locally, connect the CLI, and let the machine handle jobs from your own network instead of sending every request to the cloud. this is where the real edge starts. overnight code audits, private document search, local RAG, scraping agents, transcription, file cleanup, all running while the token meter stays at zero. frontier models still win for the hardest prompts. but for daily automation, coding, research, and private workflows, local AI is already moving from nerd setup to obvious business math. the next flex won’t be “which AI plan do you pay for?” it’ll be “what’s running under your desk?”

THIS GUY OPENED A TINY PC AND SHOWED HOW A $1,800 GMKTEC EVO-X2 TURNS INTO A LOCAL AI SERVER not a cloud dashboard. not another $200/mo subscription. just one box on a desk, upgraded with storage, cleaner airflow, faster networking, and pointed at real local models. the numbers are what make it interesting. Claude Code Max is $200/mo, ChatGPT Pro is $200/mo, Cursor is another $20/mo. that is $5,040/year just to rent tools most people use for coding, research, summaries, and agents. EVO-X2 flips the setup because it has 128GB unified memory, Ryzen AI Max+ 395, and up to 110GB usable as VRAM on Linux. enough room for Qwen3-Coder 30B, Llama 70B, and 200B-class local models when speed is not the bottleneck. so the workflow becomes simple: buy the box once, install Linux, run the model locally, connect the CLI, and let the machine handle jobs from your own network instead of sending every request to the cloud. this is where the real edge starts. overnight code audits, private document search, local RAG, scraping agents, transcription, file cleanup, all running while the token meter stays at zero. frontier models still win for the hardest prompts. but for daily automation, coding, research, and private workflows, local AI is already moving from nerd setup to obvious business math. the next flex won’t be “which AI plan do you pay for?” it’ll be “what’s running under your desk?”

Gipp 🦅

13,365 Aufrufe • vor 3 Monaten

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 Aufrufe • vor 1 Jahr

BREAKING 🚨 Anthropic just unveiled "Cowork," a major feature that turns Claude into a fully autonomous virtual assistant for everyone. It brings the deep agentic capabilities previously reserved for coders to general users, allowing Claude to perform complex tasks directly on your computer. The tool was built after Anthropic noticed developers using "Claude Code" for everyday admin tasks. Cowork now lets anyone grant Claude access to folders to manage files, research, and complete multi-step workflows independently acting as a digital employee that "does" instead of just chats. Cowork is available today as a research preview for Claude Max subscribers on the macOS app 😡. Claude is releasing new coding/desktop agents much faster than all of there competitors. This launch exposes a massive gap in the current AI landscape: in 2026, Google still explicitly lacks a consumer browser agent, and xAI has yet to release a native CLI or agentic interface. While OpenAI has "Operator" and Google has the developer-focused "Antigravity," Anthropic is now the only other major lab providing a true "do-it-for-me" experience for general users.

BREAKING 🚨 Anthropic just unveiled "Cowork," a major feature that turns Claude into a fully autonomous virtual assistant for everyone. It brings the deep agentic capabilities previously reserved for coders to general users, allowing Claude to perform complex tasks directly on your computer. The tool was built after Anthropic noticed developers using "Claude Code" for everyday admin tasks. Cowork now lets anyone grant Claude access to folders to manage files, research, and complete multi-step workflows independently acting as a digital employee that "does" instead of just chats. Cowork is available today as a research preview for Claude Max subscribers on the macOS app 😡. Claude is releasing new coding/desktop agents much faster than all of there competitors. This launch exposes a massive gap in the current AI landscape: in 2026, Google still explicitly lacks a consumer browser agent, and xAI has yet to release a native CLI or agentic interface. While OpenAI has "Operator" and Google has the developer-focused "Antigravity," Anthropic is now the only other major lab providing a true "do-it-for-me" experience for general users.

Chris

502,585 Aufrufe • vor 8 Monaten

do you have an interesting yet simple idea that you can't get claude code / codex to build? if so, I want to hear it or see a sketch, and then try building a decent start for you. I need little distractions when I'm tired of working on my own projects that never end. the end result would be an open source code artifact, and I'll do my best to include prompts/process where possible. video is the quintessential example, time-helix built from a Tim Babb sketch/idea

do you have an interesting yet simple idea that you can't get claude code / codex to build? if so, I want to hear it or see a sketch, and then try building a decent start for you. I need little distractions when I'm tired of working on my own projects that never end. the end result would be an open source code artifact, and I'll do my best to include prompts/process where possible. video is the quintessential example, time-helix built from a Tim Babb sketch/idea

Codetaur

24,190 Aufrufe • vor 4 Monaten

You should really stop using Zapier or Make. Deploying Python scripts on Replit takes less than 5 min and is cheaper. Just describe what you want to automate and AI takes care of writing the code. For example, I created an automation that merges all the PDFs in a folder on Drive into a single file. All that's left to do is: - Copy/paste the API key - Click on "Run" And you're done! In this case I used Aider Chat (free and open source), but you can also use Replit Agent.

You should really stop using Zapier or Make. Deploying Python scripts on Replit takes less than 5 min and is cheaper. Just describe what you want to automate and AI takes care of writing the code. For example, I created an automation that merges all the PDFs in a folder on Drive into a single file. All that's left to do is: - Copy/paste the API key - Click on "Run" And you're done! In this case I used Aider Chat (free and open source), but you can also use Replit Agent.

Paul Couvert

163,047 Aufrufe • vor 2 Jahren

Today we’re officially launching Bubble Lab. 🫧 🚀 We spent the last 4 months rebuilding the way developers automate. If you’ve ever wrestled with n8n.io or similar tools: debugging silently breaking workflows, staring at black-box logs, or trying to ship fragile JSON configs into production… you’re not alone. We felt that pain firsthand while building internal automations for our previous startup, So we fixed it. Bubble Lab (YC W26) is the first agentic workflow builder where every step is real, inspectable TypeScript. Prompt your workflow → get a clean visual editor → inspect the underlying code → export it into your stack. Say goodbye to black-box automation and trial and error debugging, and hello to clean, code-based, agentic workflows you can trust!! Oh yeah and it’s open source. 🙂 #developer #automations #AI #agentic #workflows #bubblelab

Today we’re officially launching Bubble Lab. 🫧 🚀 We spent the last 4 months rebuilding the way developers automate. If you’ve ever wrestled with n8n.io or similar tools: debugging silently breaking workflows, staring at black-box logs, or trying to ship fragile JSON configs into production… you’re not alone. We felt that pain firsthand while building internal automations for our previous startup, So we fixed it. Bubble Lab (YC W26) is the first agentic workflow builder where every step is real, inspectable TypeScript. Prompt your workflow → get a clean visual editor → inspect the underlying code → export it into your stack. Say goodbye to black-box automation and trial and error debugging, and hello to clean, code-based, agentic workflows you can trust!! Oh yeah and it’s open source. 🙂 #developer #automations #AI #agentic #workflows #bubblelab

Selina

50,253 Aufrufe • vor 10 Monaten

Finally, an OpenRouter for agent harnesses! (including System One by Jev) Devs just open-sourced plug-and-play infrastructure layer that lets you run any harness under a single interface for free, like: - Codex - Claude code - Hermes - DeepSeek Harness - System One, powered by Jev - And 9 more agent harnesses This means you can bring Jev into the same product that already uses Codex, Claude Code, or another supported harness, without writing another implementation for sessions, streaming, files, cancellation, and failure handling. Here's the repo: The harnesses run locally, and the Unified Harness Protocol (UHP) defines the common task interface with an OpenAI Responses-compatible API. If you want to dive deeper, the article below explains how to set up Jev from scratch, check it out ↓

Finally, an OpenRouter for agent harnesses! (including System One by Jev) Devs just open-sourced plug-and-play infrastructure layer that lets you run any harness under a single interface for free, like: - Codex - Claude code - Hermes - DeepSeek Harness - System One, powered by Jev - And 9 more agent harnesses This means you can bring Jev into the same product that already uses Codex, Claude Code, or another supported harness, without writing another implementation for sessions, streaming, files, cancellation, and failure handling. Here's the repo: The harnesses run locally, and the Unified Harness Protocol (UHP) defines the common task interface with an OpenAI Responses-compatible API. If you want to dive deeper, the article below explains how to set up Jev from scratch, check it out ↓

rody

88,007 Aufrufe • vor 8 Tagen

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.

Run your coding agent on a local model, with QVAC. OpenCode now plugs into a model on your own machine through our official plugin. That changes two things. Privacy by default. Your repo, your prompts, and every command the agent runs stay on your device. No third-party model ever sees your code. For an agent that reads your codebase and runs commands, that is the point, not a nice-to-have. New workflows. With no meter and no rate limit, the agent does not have to stop. Let it loop on a task, refactor a whole repo overnight, or run a watch-build-fix loop that keeps going. Setup takes a few minutes: one line in opencode.json and OpenCode runs on a local QVAC model. In the video demo, it handles three real developer tasks back to back, fully offline.

QVAC

11,382,936 Aufrufe • vor 3 Monaten

How I have Claude automate anything I do on my computer just by showing it: I use the free Clips app and hit record to start recording. Then I just do the action - like navigating to Rippling and approving any unapproved time off - and I’ll often just talk out loud as I do it explaining any add’l details like I would when showing a human. The Clips app captures everything on your screen and everything you say, and transforms it into a format Claude can “see and hear”. You'll then get a link that you can easily share with Claude (or humans too). I’ll paste it to Claude and say something like, "automate this for me every day at 8:00 AM." The link has special metadata that agents like Claude can discover. It exposes APIs to see the full transcript with timestamps and grab screenshots of what was on your screen at any of those timestamps. Once it's created the routine, you can go to the Routines tab in Claude Code desktop app. This also works with the CLI, Claude Cowork, Codex etc. You’ll see your new routine there, and you can just hit Run Now to have it start running it. Video attached shows this step by step. The Clips apps is free and open source - I’ll link to it and the source code in the thread.

How I have Claude automate anything I do on my computer just by showing it: I use the free Clips app and hit record to start recording. Then I just do the action - like navigating to Rippling and approving any unapproved time off - and I’ll often just talk out loud as I do it explaining any add’l details like I would when showing a human. The Clips app captures everything on your screen and everything you say, and transforms it into a format Claude can “see and hear”. You'll then get a link that you can easily share with Claude (or humans too). I’ll paste it to Claude and say something like, "automate this for me every day at 8:00 AM." The link has special metadata that agents like Claude can discover. It exposes APIs to see the full transcript with timestamps and grab screenshots of what was on your screen at any of those timestamps. Once it's created the routine, you can go to the Routines tab in Claude Code desktop app. This also works with the CLI, Claude Cowork, Codex etc. You’ll see your new routine there, and you can just hit Run Now to have it start running it. Video attached shows this step by step. The Clips apps is free and open source - I’ll link to it and the source code in the thread.

Steve (Builder.io)

25,473 Aufrufe • vor 3 Monaten

This new Siri update is absolutely maddening. It's a tale as old as time, Siri being a complete joke. Google has historically just been far better at basically every stage of their lifecycle in terms of voice to text, and phone control. Google Assistant was completely dominant. So you would think considering that Google makes their own frontier models, and the fact they are one of the industry leaders in small models capable of running on Edge devices, that they would easily dominate the mobile space, right? I mean surely that would be true considering Apple has more or less been on the sidelines in the AI race, right? I seriously don't understand how this happened. On device Gemini, even with "Personal Intelligence" really has very little additional utility over the previous deterministic STT "Google Assistant" we've had for the last decade. What are we doing?

This new Siri update is absolutely maddening. It's a tale as old as time, Siri being a complete joke. Google has historically just been far better at basically every stage of their lifecycle in terms of voice to text, and phone control. Google Assistant was completely dominant. So you would think considering that Google makes their own frontier models, and the fact they are one of the industry leaders in small models capable of running on Edge devices, that they would easily dominate the mobile space, right? I mean surely that would be true considering Apple has more or less been on the sidelines in the AI race, right? I seriously don't understand how this happened. On device Gemini, even with "Personal Intelligence" really has very little additional utility over the previous deterministic STT "Google Assistant" we've had for the last decade. What are we doing?

am.will

206,441 Aufrufe • vor 3 Monaten