Shawshank

@mpp is game-changing.

Give your agents a computer that they can actually pay for and use on their own!

@gakonst @dwr @PaperPod is exactly that: CLI-based, on-demand sandboxes. Works with x402 right now, integrating MPP very soon. Just curl paperpod.dev

desperately need MPP-enabled compute & hosting, whether it is Cloudflare, Vercel, Railway, or something else people want to host simple lambdas and websites and they don't want to see billing pages! someone???

We built on-demand, CLI native sandboxes for AI Agents before it was cool. Launching today on Product Hunt: producthunt.com/products/paper… cc: @aaron_epstein @ProductHunt @ycombinator

This is why we built a CLI tool (and APIs) for our on-demand agent runtime @PaperPod. Agents are using ppod CLI to execute code, expose URLs, automate browser, etc. in a way that’s native to them.

paperpod v2 shipped to be even more agent-native. What's new: - CLI tool - Persistent memory - Topup via stripe (alongside x402) - browser automation - LLM Inference - New built-in tools like ffmpeg, sqlite3, pandoc, etc. No SDK Setup or API Keys required! Try it: npx @paperpod/cli --help Or just give it to your agent: npx clawhub@latest install paperpod

We asked Claude Code to pull a dataset from Kaggle, analyze it and build an interactive dashboard, spin up a server, and give us a live preview URL. It did all of that inside a PaperPod sandbox with no SDK setup or API keys. Just an agent shipping software end-to-end!

Huge W for builders 🔥

AI agents need a native way to access real resources like compute, that’s why we built PaperPod. PaperPod is an AI-native, pay-per-use sandbox where agents can execute code, run servers, write files, expose ports, etc. all inside isolated pods. Alpha is now live with free compute included. No wallets or setup required, just use your email as X-User-Id in the request. 👉 paperpod.dev Built on @CloudflareDev Containers and x402 protocol. Demo with Claude Code below 👇

Why does India need a 𝗧𝗼𝗸𝗲𝗻𝗶𝘀𝗮𝘁𝗶𝗼𝗻 𝗕𝗶𝗹𝗹? I explained in Parliament today.

@nemild x402 🚀

The x402 community is growing, and it's time to get folks together. Come talk to other x402 builders at the first x402 community happy hour in San Francisco on October 8th evening. (Link below) More events coming soon.

@brian_armstrong @paulg @ycombinator @base Looking forward to it with @paystabl 🫡

.@ycombinator and @base want to support founders that are building entirely new financial systems onchain. If you're building the future of finance, we want to hear from you.

@hthieblot @fdotinc Building PayStabl, the payment infrastructure for AI Agents. Since applying to @fdotinc, we’ve built our MCP Server using which agents can access paid APIs or pay each other. @paystabl

If you’ve ever applied to @fdotinc or DMed me, reply here with your progress since then, I’ll personally take a look. If you haven’t applied, you can still share what you’re building in comments.

ethereum is SERIOUSLY gearing up for ai. (erc-8004) by @DavideCrapis just dropped, it’s called “trustless agents” and here’s what you need to know: but first: you can think of ethereum as an important substrate for ai, not necessarily because it can run all the models, but because it can run all their trust. here’s a thought experiment: > imagine millions of autonomous agents moving across the internet. they transact, negotiate, and perhaps even form their own coalitions..(dao’s, anyone?) > in this reality, what substrate would they choose to anchor themselves to? do they pick a single company server? a google api? an open database that anyone can rewrite? > if you are working with these agents to do tasks cross 50 services (banks, social media, crms), would you just let it all run on a database that can be deleted? probably not. if you were an agent with no loyalty except to your own survival, you wouldn’t want to bet your memory and reputation on one corporation or one government: you’d want a ledger that no one could quietly change behind your back. you’d want neutral ground. you’d want ethereum. so, we’ve done the why, now let’s dive into the how: erc-8004 builds on the agent-to-agent protocol (a2a). a2a gives agents a shared language, but language isn’t enough: machines also need a way to check > who are you, > what have you done > and are you behaving as you claim? the proposal sketches an extension to a2a with three registries onchain: 1) identity: a verifiable anchor for “i am me.” 2) reputation: an immutable trail of how an agent has behaved. 3) validation: proofs that an action really hap this is a practical ERC that can be used and iterated on in the wild; the specifics can stay offchain, but the skeleton of trust lives on ethereum. 8004 lets agents that have never seen each other meet in the wild and still transact with confidence. look closely and will you see the outlines of a machine economy your agent negotiating with some unknown counterpart in another part of the world, and it doesn’t matter because both are plugged into the same incorruptible memory. this is just the beginning of machines running on trustware. smart contracts are how we will communicate with ai, the immutable ledger is how they will communicate with eachother, and ethereum is how we will build this right. this is just a start, but you can come and lay the foundations of a sci-fi future done right with us.

@Flyte__AI @virtuals_io A spotify wrapped for my trips 👀

What would you guys think about having a cool ticket thats an NFT marking your trips that you've taken. Collect trips 🎟️ you've taken throughout your life and with Flyte AI. Cool idea? 🤔 @virtuals_io

Sometimes opportunity knocks on your door and you don't even answer the call. How do you swap a bad luck beat into a lucky penny?

@fdotinc Building PayStabl 🛠️ paystabl.com

Who’s a builder you think the world *needs* to know about?

🛠️🚀

@fdotinc Shipped a demo for our agent native payment platform built onchain! paystabl.com

@ builders on X What did you ship this week? Lmk!