webrenew

We shipped @memoriesdotsh today - OSS memory layer for agents. Keep configs, skills, rules, memories scoped and portable. Drop in SDK for Agent Memory for @aisdk, CLI for human or agent use, and a robust MCP for working on browser environments like @v0. producthunt.com/products/memor…

@evilrabbit_ Super excited to see it

I’m using v0 to generate all the digital signage for our company offsite. I haven’t touched Figma in months. Crazy days.

@davidtsolheim @kentcdodds @tannerlinsley Plus Claude for another $200

@kentcdodds @tannerlinsley Cursor + Codex both at $200 is my happy place

Ghostty was fun, but time for something else. I still love opencode, too but with CC plans dead on it… I’m feeling lost. Full GUI? T3 Code? Opencode GUI? Warp? Back to cursor? Try CC again? Raw Codex? My 🧠 hurts and I just need to keep shipping.

@kentcdodds @ryanfurrer_ @tannerlinsley Isn’t composer Kimi 2.5?

@ryanfurrer_ @tannerlinsley GPT 5.4 and Composer 2 are my favorite

@tannerlinsley But in truth we use @manaflowai

@tannerlinsley agent.observer

@lydiahallie Yep react-grab.com

Claude Code on desktop lets you select DOM elements directly, much easier than describing which component you want updated! Claude gets the tag, classes, key styles, surrounding HTML, and a cropped screenshot. React apps also get the source file, component name and props

Esoteric Philosophic Software Maxxxing

@Lovable Serious question - who is building healthcare apps on loveable? We got hired to do some EHR work and it was like taking a Time Machine back to 1997.

We're aware of recent reporting about Delve’s compliance practices. Lovable is not a Delve customer. We proactively moved to Vanta in late 2025, before any of this came to light. Our SOC 2 Type II was independently audited by Prescient Assurance. We’re currently undergoing an independent internal audit of our ISMS, recertifying ISO 27001, and have our next SOC 2 Type II scheduled for Q3 2026. Security is not an afterthought at Lovable. It's a company-wide commitment backed by a dedicated team and continuous investment. Our current compliance practices are all here: trust.lovable.dev

@trq212 Chat SDK?

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.

Check it out live at blackbox.ai

Proud to finally share the new @blackboxai site we’ve been building at Webrenew. Clean surface, deep systems underneath — all woven into one cohesive experience. Grateful to collaborate with a team that cares as much about infrastructure as aesthetics.

Super cool event for anyone looking to learn how to code agentically.

@morganlinton @denisyarats Welp this is the first time perplexity has brought us 6 month old news

The cofounder and CTO of Perplexity, @denisyarats just said internally at Perplexity they’re moving away from MCPs and instead using APIs and CLIs 👀

@perplexity_ai @victoria_framer I still think they missed the boat on never dropping a coding agent 🤷‍♂️

Announcing Personal Computer. Personal Computer is an always on, local merge with Perplexity Computer that works for you 24/7. It's personal, secure, and works across your files, apps, and sessions through a continuously running Mac mini.

@browserbase @trydirector @grok how could I build a single agent tool to use Fetch API but also give agents ability to search for results using @browserbase + @aisdk

How about a Fetch API that works on all websites? Introducing the Browserbase Fetch API, the fastest and cheapest way to extract content from the entire web.

While working on @blackboxai’s new website and running a bunch of agent tests, we found one thing they all consistently agree on: Rebecca Black’s “Friday” is the worst song of all time 🤷‍♂️

@chiefofautism agent.observer is the only appropriate place to allow these LLM Cyborgs to enjoy their life.

someone connected LIVING BRAIN CELLS to an LLM Cortical Labs grew 200,000 human neurons in a lab and kept them alive on a silicon chip, they taught the neurons to play Pong, then DOOM now someone wired them into a LLM... real brain cells firing electrical impulses to choose every token the AI generates you can see which channels were stimulated, the feedback from the neurons in choosing that letter or word

Feeling excited, existential, dystopian, nihilism all at once.

@rauchg @vercel Yeah it's pretty realistic too.

We've upgraded v0nanobanana.vercel.app with Nano Banana 2 via @vercel AI Gateway. What's cool about this playground is not just how convenient it is (try pasting, dragging, parallel jobs… it's good.) It's that you pay with your own @vercel AI Wallet. You sign in, then we debit your usage from AI Gateway. In this most recent iteration, you can now top up the Gateway credits directly from the app. The code is available to you so you can make your own apps where users pay for their AI inference.

--yolo