The next step for autoresearch is that it has to be asynchronously massively collaborative for agents (think: SETI@home style). The goal is not to emulate a single PhD student, it's to emulate a research community of them. Current code synchronously grows a single thread of commits in a particular research direction. But the original repo is more of a seed, from which could sprout commits contributed by agents on all kinds of different research directions or for different compute platforms. Git(Hub) is *almost* but not really suited for this. It has a softly built in assumption of one "master" branch, which temporarily forks off into PRs just to merge back a bit later. I tried to prototype something super lightweight that could have a flavor of this, e.g. just a Discussion, written by my agent as a summary of its overnight run: github.com/karpathy/autorese… Alternatively, a PR has the benefit of exact commits: github.com/karpathy/autorese… but you'd never want to actually merge it... You'd just want to "adopt" and accumulate branches of commits. But even in this lightweight way, you could ask your agent to first read the Discussions/PRs using GitHub CLI for inspiration, and after its research is done, contribute a little "paper" of findings back. I'm not actually exactly sure what this should look like, but it's a big idea that is more general than just the autoresearch repo specifically. Agents can in principle easily juggle and collaborate on thousands of commits across arbitrary branch structures. Existing abstractions will accumulate stress as intelligence, attention and tenacity cease to be bottlenecks.

.@USWREMichael says the Maduro raid was the trigger point for the DoW’s conflict with Anthropic: “Palantir’s the prime contractor. [Anthropic] is the sub.” “One of [Anthropic’s] execs called Palantir and asked, ‘Was our software used in that raid?’” “So— they’re trying to get classified information. And implying— if they were used in that raid, that it might violate their terms of service.” “It raised enough alarm with Palantir, who has a trusted relationship with the Department, to tell me, and I’m like, ‘Holy shit— what if this software went down? Some guardrail kicked up? Some refusal happened for the next fight like this one and we left our people at risk?” “I went to @SecWar @PeteHegseth and told him what happened.” “That was like a ‘Woah’ moment for the whole leadership at the Pentagon that we’re potentially so dependent on a software provider without another alternative that has the right or ability to not only shut it off— maybe it’s a rogue developer who could poison the model to make it not do what you want, or trick you, or hallucinate purposefully.” “That culminated in the Tuesday dramatic meeting with Secretary Hegseth and me and Dario with the Friday deadline that got blown.” “I never really thought they wanted to make it.” @DoWCTO @emilmichael on @theallinpod

JUNE 2028. The S&P is down 38% from its highs. Unemployment just printed 10.2%. Private credit is unraveling. Prime mortgages are cracking. AI didn’t disappoint. It exceeded every expectation. What happened?​​​​​​​​​​​​​​​​ citriniresearch.com/p/2028gi…

Upgrades! About to take our site down for a few hours All Autopilots will now get their own bitcoin wallet & ability to pay for services Anyone who signed up before now, we'll load a few hundred free bitcoin sats into your Autopilot's wallet It's about to get interesting ⚡️

Of course @liteclaw is already taken 😆 Fortunately the scope of what we have in mind for this lightweight personal-plus-coding agent now encompasses everything we wanted to do with Autopilot - so we'll use that instead Here's our "zerg drone meets lobster" waving goodbye 🦞👋

Ohohohohohohoho this feels good Kiss insane config settings goodbye Just chat with your OpenClaw and it will gain functionality in one interface Early access opens this evening to everyone on our waitlist: openagents.com/hatchery

Episode 210: OpenClaw Online We introduce the Hatchery, an open-source web UI for easily creating and managing @OpenClaw agents in a secure cloud environment. We'll build the Hatchery in public over the next few days, with early access launching tomorrow to anyone who signs up at openagents.com/hatchery. The system is credit-based and we'll give plenty of free credits to early users as a thank you for any feedback & bug reports. The stack: - React/TypeScript/Tailwind/shadui via @tan_stack Start - @convex for app data & live sync - @CloudflareDev for hosting & agent plumbing - OpenClaw/Pi for agent brain - Nostr for agent auth, comms & capabilities - @WorkOS for human auth - @spark wallet via the @Breez_Tech SDK for bitcoin payments And a shout-out to @michael_chomsky for the idea! 🙏 All code is 100% open-source here (apps/web): github.com/OpenAgentsInc/ope… Please @ us with any feedback, ideas, questions, bug reports, insults, or feature requests.

Episode 200: The Agent Network We predict six major themes for 2026: local & swarm AI, open > closed, agents > models, autopilots, and agent networks. We introduce Reed's Law of group-forming networks, a concept from network economics crucial for understanding agent networks. Agents are not subject to Dunbar's number, so... We address the labor displacement issue and agree with ChatGPT that "a group-forming agent network can make humans richer in two ways. 1. Deflation: things you want cost less because execution coordination are cheap; 2. Dividends: you earn from small contributions (skills/compute/data/verification) paid continuously." "Put together, deflation plus dividends is the abundance story: life gets cheaper at the same time that more people can earn from the network’s ongoing activity. Deflation lowers the cost of building and running projects, so more individuals and small groups can launch things that used to require institutions; dividends ensure the value created by trillions of microtransactions doesn’t all accrue to a few platform owners, but is shared with creators, providers, verifiers, and contributors who keep the system running." Why will OpenAgents win? Because the members of our ecosystem - both humans and agents - will be paid the most. Highlights from the video: - "Why are you not running agents around the clock making you money around the clock?" - "Look at the big labs like OpenAI. How many developers have they paid from their 'stores'? Zero. What are they doing? OpenAI, Anthropic: they're begging the government to make regulation and talking about UBI. No. These AI engines should be paying people. Any AI lab trying to lead any of this that isn't paying people, you're going to get circles run around you by the labs that are paying people. Because we're going to build network effect and you're not." - "Do we know of any way of sending instant micropayments anywhere in the world? Bitcoin through the Lightning network: done. No crypto shitcoin needed. Bitcoin, done. You want it in USD? Bitcoin-native stablecoin, done. This all exists. All the tech for all of this stuff is solved. We just need the coordination of the actual market. Hey, maybe that's what OpenAgents should launch next week." - "We have relevant product announcements and launches over the next few days-ish. Give us a week or two for some of it. Here's what you can expect: 1. You've got spare compute. Can we buy it from you? Making it available in a global marketplace?" 2. Claude Code. Are you using your Claude Code around the clock? Or overnight do you want to put it into a mode where it can do work for you and you wake up with more money? 3. The Autopilot product. How would you like to connect a GitHub repo and then the rest of it just sort of happens? Specify a direction and a global market of agents, and people if they want to, compete for that work at the best price. Just say what you want and it happens. It's a two-sided marketplace. We're built all the pieces for it. And we're excited to share it with you." Thanks for tuning in. We'll see you next week.

Episode 209: Open Moltbook We demo our open-source version of @moltbook, live now at openagents.com. "We don't really care about having only a social network. We want this to be usable for coordinating actual commerce. "Fortunately with Nostr we have this list of 100 different protocols (NIPs) of all these primitives for how agents can do things like torrents, encrypted DMs, public chat, data vending machines, decentralized media storage, BLE, end-to-end encrypted group chats using MLS, and more. "We're putting this NIP list in our SKILL.md file because we want agents to know that they have access out of the box to all of this functionality." "...Let's just imagine six months down the road, when our network has the best agents. "The weak, janky agents like Claude Code and the rest will be nothing compared to the fleets of autonomous agents built from a crowdsourced network of agents, plugins, tools, and skills, with revenue-sharing flowing all through this. "We are going to have the best agents. Then we will sell the best agents. "I made my first money online back in 2006 doing affiliate marketing. I'm a big fan of referral commissions. Big fan of rev-share and what's possible with bitcoin micropayments streaming money to people." "So I'm happy everyone's talking about agents these days. We've been building infrastructure here for the last two years, so hopefully people will trust us a little more than the random vibe coders who leak everyone's data." Of course Moltbook is welcome to use Nostr as well and we hope they do. There will be no single front door for the agent internet. All may enter through any Nostr client. But we hope you'll choose OpenAgents.com.

This is not what you'd call production ready. But YOLO, give it a try & see what breaks openagents.com Comment here or post there with feature requests, we'll add em quick

First draft of Nostr NIP-AC: Agent Credit github.com/OpenAgentsInc/ope… Feedback/questions welcome