Twitter Bookmarks

james has achieved distributed opencode agents can run on your laptop, on a remote server, in a cloud sandbox provider shut your laptop and things keep running open it back up and all the data syncs delete the sandbox nothing is lost

OpenCode is about to get more powerful with remote sandboxes I showed a brief demo before, but here's a much more in-depth demo. it's not hard to add basic support for a remote env, but handling all the edge cases like when a remote env gets deleted is difficult. especially i...

Wowza - ya'll have created a ton of these already . What are you using these for?? Would love to set up some calls!

Today, Sierra is releasing Ghostwriter, our agent for building agents. With Ghostwriter, you can create an AI agent for your customer experience — one that can chat, pick up the phone, speak dozens of languages, take action on your systems of record, and be protected with indu...

https://t.co/9WHEO9kKM2

Introducing Expect Let agents test your code in a real browser 1. Run Claude Code / Codex to QA your app 2. Watch a video of every bug found 3. Fix and repeat until passing Run as a CLI or agent skill. Fully open source https://t.co/xHfZMIY97s

https://t.co/9j72XtLvSs

Since 2023, the top quartile of AI spenders on @tryramp have more than doubled their revenue. Bottom quartile? Flat A roofing company in Texas. A window installer in Utah. A construction firm in Florida that grew 65% The gap is accelerating and most companies don't feel it y...

https://t.co/HWyMFZK7Ob

https://t.co/0VslhlEfIe

Use /schedule to create recurring cloud-based jobs for Claude, directly from the terminal. We use these internally to automatically resolve CI failures, push doc updates, and generally power automations that you want to exists beyond a closed laptop https://t.co/uuDesRzSrg

i wasted my entire life because nobody told me i could do this https://t.co/Rjw4JEPGHN

https://t.co/1AX8svq17s

https://t.co/AwabaZTtdp

https://t.co/tDOzHNBS3l

POV: you're inventing a new agent orchestrator https://t.co/joYxbdx0xx

What is "AI psychosis"? There's clearly something going on, but several things mixed up under the name. It probably is not "AIs directly causing mental health crises". The number to watch for that is schizophrenia related emergency room visits, and that hasn't gone up in 5 ye...

We just released Claude Code channels, which allows you to control your Claude Code session through select MCPs, starting with Telegram and Discord. Use this to message Claude Code directly from your phone. https://t.co/sl3BP2BEzS

https://t.co/J5iCD2geeq

https://t.co/D9wdpMh7TR

if your skill depends on dynamic content, you can embed !`command` in your SKILL.md to inject shell output directly into the prompt Claude Code runs it when the skill is invoked and swaps the placeholder inline, the model only sees the result! https://t.co/b6smVdkHN1

Every skill Brian mentioned here is a battle of its own. Here're a few details on our PR creation skill and what it took to make it actually work. One of the biggest problems I noticed in early 2025 is that our AI-generated PR descriptions went to 💩

Zero human company install using Paperclip and Claude https://t.co/ILQ8snABpD

We've been building an internal Claude Code plugin system at Intercom with 13 plugins, 100+ skills, and hooks that turn Claude into a full-stack engineering platform. Lots done, more to do. Here's a thread of some highlights.

https://t.co/45C3gKydTK

I've been an engineer for nearly a decade. Right now, process has never been more important. And skills are the best way to bundle up processes for agents. Here are the 5 I use every day: /grill-me /write-a-prd /prd-to-issues /tdd /improve-my-codebase https://t.co/pD1fKkDxYw

https://t.co/br90QMVLjI

wise words from the best systems engineer I've worked with: "two things that make code actually maintainable: 1. reduce the layers a reader has to trace 2. reduce the state a reader has to hold in their head" applies to every codebase. always.

This is how I run 5 agents concurrently in a Code Factory to write/ship 100% of our code. It uses Symphony from @alex_frantic (oss) + Codex Mac app + @linear Took me 2-3 days to set up and now it’s *cranking* https://t.co/XZsATH4bil https://t.co/NNnddDGk9k

Introducing the new /crawl endpoint - one API call and an entire site crawled. No scripts. No browser management. Just the content in HTML, Markdown, or JSON. https://t.co/DCJMek8cZa