All the AEO/SEO tools are thermometers. If you have a fever, you need a doctor.

Personal blogs are back in style. And they’re here to stay. When people write with zero expectations on their blog (website or any platform), they’re pouring their heart into it and readers feel it. See @simonw’s writings for example. Tech companies writing for SEO, aim for that quality first.

1/ Today, we're releasing the first open-source Computer History - now in early preview for Cua Driver on macOS, Windows, and Linux. It gives agents an encrypted, local record of actions they took through Cua Driver, so new sessions can recover useful context from earlier work.

We just killed Exa, Tavily, SerpAPI, and Brave. Your agent can now search & fetch any webpage for 100% FREE. Them: $7 per 1,000 searches. Us: $0. No subscriptions, no quotas. Humans search Google for free. Agents shouldn't have to pay either. Made possible by @Tiny_Fish and @MonidHQ.

there is no launch i love you launchnothing.com

I've become a documentation freak. So much so, I document life

Scale your content with AI. But don't expect paid users because you have a 100 new blog posts. In the devtools space, depth is highly valued (PS that's where Manicule wins) Developers will talk about that "one blog post" for months after they've read it and keep sending you "traffic." (To be honest, I hate to call people "traffic" because what the heck are we even measuring then?) Does this post mean I'm anti-AI? Absolutely not. But I think it's 10x faster to use AI to: - build your demo apps - explain the architecture - create architecture diagrams - write draft v1 Once I have the right amount of context and understanding about what the AI did and the storyline behind the PRs it raised throughout the building, I can voice type the article section-by-section, adding interesting analogies, nuances, and insights from my experience. That's a much more impactful piece compared to an AI written and AI edited piece. Give this workflow a shot. You'll no longer waste the time people usually spend trying to understand what the AI wrote after the article is written.

You can read a diff and still not know what it means for the person using the product. The answer is in a map you built before the change landed, or it's nowhere.

Claude Security scans now run on Claude Mythos 5, available today in public beta for all Claude Enterprise customers. Put our most capable security model to work on your codebase, no separate model access needed.

excited to partner with @UseCorgi somehow they’ve made insurance fun we got to onboard the team in person yesterday with @hyperspell swag and chocolates now they have a company brain

GitHub finally moved to serverless.

I've been the biggest fan of @herdrdev since I found it. Man I'm so thrilled to see them get into @ycombinator! It's genuinely most efficient way to manage agents after trying everything from Zed, Orchestrator, different IDEs, etc. LFG!

Introducing the Firecrawl plugin for Codex. Give Codex access to the most accurate search available (94.7% on SimpleQA) plus tools to scrape, crawl, and interact with any site. Find us on the @OpenAI plugin marketplace today!

we open sourced the fastest pdf parser engine pdf-inspector powers /parse together with our custom OCR models 0.002s per page

Once we have completed our review for security vulnerabilities, we will make the entire codebase of 𝕏 open source, with no exceptions. Moreover, we will invite third party reviewers to examine the system that is running to confirm that the open source code is what is running. Trust through total transparency is the only thing that should be believed.

Stupidly simple way to build your own claude tag for your team - now live on opencomputer.dev via durable agent sessions. We kept seeing mutiple users build background agents inside slack, and it also quickly became one of our fastest growing use cases internally. Naturally, we are trying to make this as easy as possible. Go give it a shot!

Every enterprise we talk to is building their own model agnostic internal agents (stuff like Claude Tag but homegrown and multi channel - @tryramp has inspect, @WorkOS has horizon, @coinbase has mux). It's table stakes now. Today, we shipped a simple way to build a claude tag alternative for your org. Anyone in the team (think sales, customer support, gtm, pm's etc) can @mention it in a channel to start a session and steer it from there. It runs on opencomputer durable agent sessions (docs.opencomputer.dev/agent-…). We'd love any and all feedback. We're very excited for this!