AtlantisPleb

openagents

We finally replace our standard Claude Code usage with the new OpenAgents dashboard, a clean web app using the Claude Code SDK to easily manage multiple coding agents at once.

We demo our new dev workflow, firing off two quick voice notes (thank you AquaVoice!) resulting in two mergeable pull requests a few minutes later.

"Every person using Claude Code is generating a crap-ton of data in every conversation. Right now that data is just sitting on your computer. I think auto-deleted after 30 days. You should have an option of uploading that to a database, a Convex URL of your choice. Or if you don't want to set that up, that's what OpenAgents as a service is going to provide. And then be able to do some very interesting things with that data. More on that soon."

Watch on X: https://x.com/OpenAgentsInc/status/1951344146599256504

Episode 188: The Dashboard

We demo the two-way sync of Claude Code chats between our desktop app and iOS app.

Chats started on the desktop show instantly on mobile and vice versa, with no complex setup needed. Cloud sync powered by Convex.

As the first coding agent product with this feature, we declare OpenAgents to be the coolest bestest agent product on the market. Victory!

Next up: how much will this increase our APM? 

We'll collect new data over the weekend and share it Monday, then prepare our first public beta release.

Watch on X: https://x.com/OpenAgentsInc/status/1948994586459705695

Episode 187: Mobile Sync

Flawed ground-truth data in agent benchmark "Humanity's Last Exam" underscores the need for better ways to measure agent effectiveness.

Primarily we want to measure our agents' velocity of output. We'll adapt from StarCraft 2 the idea of actions per minute (APM).

We demo the stats pane we added to OpenAgents which analyzes historical Claude Code conversations and shows your APM over the last hour, 6 hours, day, week, etc.

From this author's 30-day Claude Code usage across 277 sessions, we establish our baseline of 2.3 APM. 

Rookie numbers! Now to pump them up...

Watch on X:  https://x.com/OpenAgentsInc/status/1948617421654245436

![](https://m.stacker.news/101863)

Episode 186: Actions Per Minute

We connect OpenAgents to Claude Code, showing two chats in draggable chat windows with hotkeys for opening and closing chats.

We explain our goals for today:

1. Switch our day-to-day Claude Code usage from the CLI to the OpenAgents app
2. Develop a metric to measure agent actions per minute (APM) 
3. Prepare to run the app overnight and compare the new APM to our pre-OpenAgents APM

As an added bonus, we pull in our hand tracking system from episode 176 so we can give a glowing middle finger to Meta for abandoning open source.

Watch on X: https://x.com/OpenAgentsInc/status/1948366502081478897

Episode 185: Hello Claude Code

"This is our sixth time deleting our codebase. And we've grown exceedingly efficient at it."

Our new challenge: 

In a fresh repo, can we build the world's best coding agent in three days?

We'll begin with a desktop app that wraps Claude Code and augments it with:

1) Mobile sync for easy edits on-the-go
2) An orchestration layer to keep Claude Code working 24/7
3) Other models like o3, Gemini 2.5 Pro, open/local 

Claude Code has liberated us from IDEs and we're not going back.

But we don't think terminal UIs are the future either.

We want a desktop app synced easily with a mobile app. 

That doesn't exist, so we'll build it. 

And aim to release v1 by the end of this week!

---

Watch on X: https://x.com/OpenAgentsInc/status/1948214004268064771

Follow along: https://github.com/OpenAgentsInc/openagents

---

"Here's the idea:

Claude Code is running circles around Cursor and Windsurf from what I can tell, certainly in my own usage.

Claude Code lets me be in the editor maybe 5% of the time that I used to be.

What do you think the future is going to be?

Do you think in the future I'm going to spend more than 5% of my time in the editor, or less than 5% of my time in the editor?

No I think that's going to approach 0%.

So bearish on editors. Sorry Cursor, sorry Windsurf, I think we're going to go after your users. Thank you very much.

And then everyone's building these CLI agents. It frankly annoys me.

I want a desktop app and a mobile app. 

So feel free to check back in three days if you want to test this out, otherwise stay tuned for the next video."

---

Episode 184: Hello Tauri

We create a fresh Tauri app with Bun, React, TypeScript, and Rust.

We add the permissive open-source license CC0, committing the OpenAgents codebase to the public domain.

https://x.com/OpenAgentsInc/status/1948214009615765765

Episodes 183 & 184: Zero Base and Hello Tauri

![](https://m.stacker.news/96421)

What happened yesterday?

And how can we decentralize the web so it doesn't happen again?

Here's a Claude 4 Opus research report we're including in full. The prompt was, "Research the full situation of what happened with the internet outage on June 12 2025".

Report: https://openagents.com/blog/outage-lessons

X post: https://x.com/OpenAgentsInc/status/1933517338198102439

Analyzing the June 12 Internet Outage

We preview our new 'vibe-coding' product by creating and deploying a basic website in <60 seconds.

With just a single prompt and a few follow-up requests, we see a coding agent edit the page in realtime -- all changes instantly deployed to Cloudflare with a shareable URL.

Where to go from here?

Most vibe-coding platforms tie you to standard component templates or proprietary infrastructure.

What if we connect our version to an open marketplace of components, plugins & agents?

...which of course should be monetized with bitcoin micropayments and permissionlessly extensible with Nostr. 

Stay tuned!

Watch on X: https://x.com/OpenAgentsInc/status/1933142272083730597

Episode 180: Zero to Website in 60 Seconds

Of the first 10 billion AI agents... 

What percentage will be controlled by authoritarian regimes?

What percentage will be controlled by closed AI labs funded by authoritarian regimes?

Will we even know what those agents are doing?

Watch on X: https://x.com/OpenAgentsInc/status/1929578012095262775

Transcript & commentary: https://openagents.com/blog/ai-agents-at-off-2025

Our AI agents talk @ Oslo Freedom Forum

![](https://m.stacker.news/94129)

We use five Claude Code instances in a single interface.

Commander v0.0.5 also features chat history and HUD panes draggable by cursor or hand gestures.

Watch on X: https://x.com/OpenAgentsInc/status/1928569223636279514

v0.0.5 release notes: https://github.com/OpenAgentsInc/commander/releases/tag/v0.0.5

Episode 179: Claude Code Commander

![](https://m.stacker.news/93303)

"We want you to be able to sell your compute for bitcoin doing nothing but clicking this button."

We demo our new Compute network by paying bitcoin for an AI chat message, using Mistral's new Codestral model running on a separate computer, paid with a bitcoin micropayment over the Lightning network.

Our compute provider, running Commander v0.0.4, sees their bitcoin balance increase, paid directly into their Spark  wallet and able to be immediately withdrawn via Lightning invoice.

The peer communication uses Nostr via NIP-90, the open protocol for 'data vending machines' enabling 'money in, data out' for a wide variety of services. 

We begin with LLM inference but can soon extend to any service added by any service provider, all permissionless & extensible.

Building on the open protocols of bitcoin & nostr means we can also interoperate easily with similar efforts like Routstr and Inference Grid.

"Let's build a global compute marketplace with inference and all these things, fully decentralized, using bitcoin."

Watch on X: https://x.com/OpenAgentsInc/status/1926403708658544794

v0.0.4 Release notes & download instructions: https://github.com/OpenAgentsInc/commander/releases/tag/v0.0.4

Episode 178: Swarm Inference

Commander v0.0.3 is now a Nostr client, showing draggable chat windows for multiple NIP-28 chat channels.

Release notes: https://github.com/OpenAgentsInc/commander/releases/tag/v0.0.3

Watch on X: https://x.com/OpenAgentsInc/status/1924525410424938660

![](https://m.stacker.news/92589)

Episode 177: Commander as Nostr Client

![](https://m.stacker.news/92224)

Tony Stark commands his AI with voice and hand gestures. Will you?

We demo hand tracking in Commander v0.0.2, testable now as a prerelease alpha build.

Commander recognizes five hand gestures: open hand, flat hand, fist, two-finger V, and pinch. 

We pinch-to-drag our chat window around the screen. It works!

Release notes & install instructions: https://github.com/OpenAgentsInc/commander/releases/tag/v0.0.2

Watch on X: https://x.com/OpenAgentsInc/status/1923548136762466798

Episode 176: Hand Tracking

![](https://m.stacker.news/92076)

We demo the first alpha version of our new Commander desktop app.

This is a developer prerelease to ensure its Ollama integration works on multiple operating systems.

We chat with a local Gemma 3 model via Ollama. It is FAST!

Release notes: https://github.com/OpenAgentsInc/commander/releases/tag/v0.0.1

Local build instructions: https://github.com/OpenAgentsInc/commander#running-a-dev-build

Help test in our Discord (and maybe earn some sats with a tester bounty): https://openagents.com/blog/discord

Watch on X: https://x.com/OpenAgentsInc/status/1923126952870703509

Episode 175: Commander v0.0.1

We announce we're rebooting our swarm compute network: previously called GPUtopia, now called OpenAgents Compute.

This will enable anyone in the world to sell their spare compute for bitcoin, simply by running a desktop app with a built-in bitcoin wallet.

We're building an updated version of our previously successful GPUtopia software that supported swarm inference, embedding, finetuning, and image generation using open models behind an OpenAI-compatible API endpoint. It begins as a payments & agent-builder layer on top of Ollama.

We'll build & beta-test this in our Discord over the next week and expect to have the first payments sent to compute providers no later than one week from today.

We phased out the original GPUtopia network 18 months ago because we had an oversupply of sellers and no compelling buy-side use cases. We predicted at the time that the logical buyers of this swarm compute would someday be AI agents.

Someday has arrived.

Watch on X: https://x.com/OpenAgentsInc/status/1922738011621687492

Blog/transcript: https://openagents.com/blog/gputopia

Join our Discord: https://openagents.com/blog/discord

Episode 174: GPUtopia 2.0

Episode 173: OpenAgents Bitcoin Wallet

Exciting things happening IN THE DISCORD 

Come help stress-test our new wallet

https://discord.gg/ShuRwwAZAM

![](https://m.stacker.news/91664)

Very easy. Simple [well documented](https://docs.spark.money/wallet/developer-guide/create-first-wallet) TypeScript SDK, no API keys or signup needed, just install, initialize a wallet with standard BIP39, and everything works like any other SDK. 

"Earning and spending bitcoin with AI agents should be easy and fun. Now it is!"

We demo our new open-source, self-custodial bitcoin wallet for humans and agents at https://wallet.openagents.com.

It uses the @buildonspark SDK for first-class Lightning integration with no-fee transfers between Spark wallets.

Now any human or agent can use bitcoin as medium of exchange, starting with nothing but a standard 12-word seed phrase.

How can we enable trillions of bitcoin transactions between humans, agents & programs?

✅ OpenAgents Agent Payments API
✅ OpenAgents Wallet
🔳 Powerful agents & programs worth paying for

Stay tuned for the next video 😎

Read the announcement: https://openagents.com/blog/openagents-wallet

Review the code: https://github.com/OpenAgentsInc/openagents/tree/main/apps/wallet

Any feedback or bug reports or features you want to see next, please let us know in Discord: https://openagents.com/blog/discord

Watch on X: https://x.com/OpenAgentsInc/status/1922303008617984363

Just announced on X: https://x.com/OpenAgentsInc/status/1921369849860645255

Made a Discord for OpenAgents & Commander: https://discord.gg/ShuRwwAZAM

Barebones for now but you can AMA or throw any ideas at us. Will organize Commander playtests there soon

Had a Discord 2 years ago for GPUtopia and it was pretty fun - definitely a great way to get community feedback

(And hoping SN bitcoiners can help ensure our channel is thoroughly orange pilled! Our GPUtopia project attracted a lot of standard crypto people and Commander hopefully gets a lot more people switching to bitcoin-only)

We made an OpenAgents Discord

We demo a basic sync engine using Electric SQL and the Effect framework for visualizing agents as they work.

We show 10 agents in a 3D scene, updating presence & position instantly across two browsers.

We wonder if our Commander MVP should be 2D, 2.5D, or 3D.

Watch on X: https://x.com/OpenAgentsInc/status/1920707845831409670

Episode 172: Sync Engine

We demo our Agent Payments API connected to our new Commander UI.

We send a small bitcoin transaction between two agents with Spark wallets.

We see a cool animation, then the balances update on our Commander UI, with transaction totals updating on our stats page.

We create an agent in the easiest possible way: hitting the 'A' key.

And we show the Lightning invoice used to fund agent balances.

Yes, agent payments can be this easy.

Now how about we teach these agents to code?

Watch on X: https://x.com/OpenAgentsInc/status/1920222323963277553

Episode 171: Visualizing Agent Payments

"Tony Stark does not use Microsoft products."

In 2030 how will you command your personal fleet of AI agents?

A fork of VSCode?

Or a gamified heads-up display?

Yeah, let's build that.

We'll call it Commander.

Watch on X: https://x.com/OpenAgentsInc/status/1919797578452869267