Moe Saleh

ai, adventure, art, investing. Making a better tomorrow, today. $btc

[Linus ✦ Ekenstam @LinusEkenstam]

Been following Divesh since day zero.
This is really ground breaking technology.

I’m so stoked to see what people will create with this.

[Cursor @cursor_ai]

New in Cursor design mode: Annotate.

Give agents visual prompts: edit elements, draw on the page, and review your designs at different screen sizes.

[Stripe @stripe]

Introducing 'stripe pay', for instant business-to-business transfers. Find companies using their Stripe profile handle and send funds for free. Available in the Dashboard and CLI.

[Larsen Cundric @larsencc]

Alex is one of the smartest people I know when it comes to agents.

He is the kind of guy who would rather build the whole thing himself than accept how everyone else does it.

So he did.

A full agent, from scratch, in Go, open source. It lives on your own server and drives all your computers.

Very early and extremely ambitious. Give it a try and give him good feedback!

I really recommend keeping a close eye on Alex.

[Charles Maddock @charles_maddock]

You've never seen AI agents this powerful and delightful

[Aaron Epstein @aaron_epstein]

Next-gen browser use is here.

Pomerado builds APIs for any website that are faster (2-4x), cheaper (10-1000x), and more reliable (+30%) than browser agents (including Astra, Muse, and Instinct). Open source too.

Congrats on the launch @akshay_manglik @Alanmrsa1!

[Shiva @BinaryScriptar]

Why pay $29 when you can get it for free?

https://t.co/lCh6wuWqqH

Traks is MIT licensed and runs in your own Cloudflare account. Sign in with Cloudflare and it installs in one click: no terminal, no Node. Updates are one click too.

Already used by 100+ Cloudflare users.

It scales because your history goes to Iceberg tables on R2 object storage, not a database that fills up.

• realtime visitors on a live map
• funnels, goals, page paths
• ChatGPT/Claude/Perplexity traffic as its own channel
• bots classified, not just dropped
• MCP server so your coding agent can query your analytics

What it doesn't do yet: Stripe revenue by source. Which is on the roadmap.

Want something else? PRs are welcome.

[Elaya @elayadesigns]

I designed all of these landing pages in the last two months, using @higgsfield , Claude, and Cursor with my custom AI designer skill.

The skill is open source: https://t.co/Gs1RT1BZxi

[Garry Tan @garrytan]

Grep open sourcing big parts of their harness is a big deal

[David Im @davidim]

As a builder in the AI video space, I was terrified about how much markup API providers charge for simply routing the models.

Higgsfield API adds a 40% markup even with its maximum advertised discount. Fal adds 100%. Runway adds 414% (Seedance 2 480p)

I might be hated by the industry, but : 


Today, we’re launching Sume API, the first image & video model provider with 0% markup.

For example with Seedance 2.5 1080p
• 50% cheaper than fal
• 50% cheaper than higgsfield api (29% even with biggest discount)
• 28.02% cheaper than kie ai

The routing infrastructure layer is never the moat. We believe that APIs should be commoditized, and the moats will be built at the application layer.

Check the pricing comparisons below, and see how the broken industry is saved.

[jack @jack]

We believe voice is the most natural way to interact with intelligence, so we created Dessa, the most authentic full-duplex speech model ever built. Talking with it feels like talking with a person…full of emotion, nuance, pauses, and a natural cadence.

https://t.co/r0qFLdvd6c

[Abdulla Ababakre @abdullababakre]

defining a new category: phone-use

an mcp/api that gives ai agents their own phones

cloud phones. real androids. real iphones.

tell your agent what to do, and it can operate a phone just like you do.

today, ai agents face three fundamental problems and phoneuse solves them 🧵

[Dilum Sanjaya @DilumSanjaya]

Hardware looks scary until you break it down into small steps. So I built an app that takes you through Arduino one circuit at a time.

Made with Opus 5.5
https://t.co/1AL82geKtQ

[Guillermo Rauch @rauchg]

Vercel now has all the pieces in place to host at-scale backends.

WebSockets, Queues, Workflows, Cron, Services, Containers, Python, Daemons, Long-duration Functions, Blob, Drives, Sandbox…

Any guesses what comes next?

[Vercel Developers @vercel_dev]

WebSocket support in Vercel Functions is now generally available.

Vercel now serves 15 million WebSocket connections a day across AI chat, streaming, and realtime multiplayer apps.

https://t.co/VoeignmMOX

[Akshay 🚀 @akshay_pachaar]

Google just open-sourced Harness².

(turn any harness into a self-improving system)

a harness is everything wrapped around the model, like the system prompt, tools, memory, skills, and subagents. today a person designs it once, and the agent runs every new task with that same fixed setup.

Harness² lets the agent refine that setup for each new task on its own, with the model weights left untouched.

on every task, the agent proposes edits to its harness, runs a few candidate versions, and composes a better harness by comparing how those runs behaved.

because it learns from the differences between runs, it needs no correct answer or grader for the task.

that covers a single task. Harness² also carries what it learns from one task into the next.

after each task, it saves the harness it settled on along with the lessons that held up across the runs. the next time it refines a harness, it starts from those notes instead of from scratch.

this means every finished task makes the next round of edits more informed.

Google tested this with Gemini 3.5 Flash and GLM-5 on legal, office, and professional work benchmarks. one round of edits was enough to beat their original harnesses, and giving the agent more rounds pushed scores higher.

those extra rounds can go wide or deep. the agent either tries several candidate harnesses at once or keeps refining a single one step by step, using OpenCode or Codex to carry out the work.

you can find the Harness² repo here: https://t.co/i00WLeeFpw

I wrote about a similar idea for agents already running in production, where the harness should repair itself after a failure instead of waiting for someone to debug the trace by hand.

that piece walks through how @Cometml's Opik (open-source) closes this loop, going from a failing trace to a proposed fix to a regression test that stops the same failure from coming back. it's quoted below.

[JosephZhou @openmys]

We plugged Google Research’s Harness² into JEV 1.14.

Zero weights touched, yet driving massive gains on vision benchmarks round after round.

Under the hood, the system:
⚡️ Rewrites its own prompts
🛠️ Builds its own tools
🧠 Distills its own experience

JEV-Harness² repo drops soon. Stay tuned.

[Guillermo Rauch @rauchg]

We open sourced a *really fast* HTML artifact builder. It's powered by libfx, making the agent durable.

Building the low-level plumbing for v0 to survive server crashes, flaky LLMs, function limits was a huge pain.

Now it's easy, free, and OSS: https://t.co/aUP1vKeIsP.

PS: I built this floating container in a few minutes… it's delightful, and it's just HTML!

[morluto @morluto]

rea v6.7 is now live
120+ contributors, 236 merged PRs (many more in commits)

should be much more stable & faster now
we fixed a lot of bugs together!
https://t.co/90MqUOB1nW

[Rabi Shanker Guha @rabi_guha]

For 30 years, technology has moved in one direction: turning information into intuitive interfaces

Somehow, the smartest software we’ve ever built took us back to a textbox

We’ve spent the last 2 years at @openuidev trying to fix that. 6 months ago we open-sourced it: 10K+ GitHub stars, 6M+ downloads

ChatGPT shipped Intelligent UI and showed everyone what it looks like

Today we’re releasing OpenUI 1.0 bringing it to every other agent