Any Effect fans?
Releasing nostr-effect v0.0.1
A type-safe Nostr relay & client library in @EffectTS_
Building this mainly for the new OpenAgents platform but you may like it too
At the rate we're going we should have ~100% of NIPs implemented next week for both clients & relays
https://npmjs.com/package/nostr-effect
AtlantisPleb
npub1tlv6...7fdm
Founder, OpenAgents
OpenAgents Episode 197: Reverse Engineering Cursor
The year is 1900 and the world's "top" investors massively funded the company building the fastest horse.
We'll keep building the Model T, but first let's see what we can learn from @cursor_ai.
PRs welcome: https://github.com/OpenAgentsInc/openagents/tree/main/docs/re/cursor
X (formerly Twitter)
OpenAgents (@OpenAgentsInc) on X
Episode 197: Reverse Engineering Cursor
The year is 1900 and the world's "top" investors massively funded the company building the fastest horse.
...
OpenAgents Episode 196: Ditch the TUI
Upgrade #1 of 10: "Replace janky fake terminals with a proper desktop app featuring a sidebar, chat history, and widgets for managing long-running agents."
Here's what that looks like.
And surprise! We're back on Tauri so this will be cross-platform (Windows/Mac/Linux/Android/iOS) from the start. 👍
Big props to @assistantui for a beautiful UI out of the box!
X (formerly Twitter)
OpenAgents (@OpenAgentsInc) on X
Episode 196: Ditch the TUI
Upgrade #1 of 10: "Replace janky fake terminals with a proper desktop app featuring a sidebar, chat history, and widget...
OpenAgents Episode 195: Designing 10x Better
How can our product become ‘10x better’ than the competition?
We discuss ten upgrades:
1. Ditch the TUI (and your old IDE)
"There's no reason to be in the terminal because you're not using actual terminal commands. There's nothing about the TUI you couldn't also do from a desktop app. Give me a sidebar. Get rid of this screen flicker. I can't copy paste properly. All this stuff's already been solved. Give me a ChatGPT-style desktop app with history on the side, some widgets if I want to manage long-running agents."
2. Go Mobile
"I want to have a desktop app that syncs to my mobile phone. So give me the exact same flow, the same UI components, the same controls. If I'm at home doing my usual workflow, let me have the desktop app, but if I want to go to the store, let me be able to do all of the same stuff from my mobile phone."
3. Code Overnight
"I want to be able to let stuff run overnight. And not in this hilarious horrible way that you have to do with Codex: continue, continue, continue, continue, continue."
4. CLI Agents as Subagents
"You know how Claude will delegate to a sub-agent and it'll have its own context window. When it issues a task, that's what it's doing. Why can't I just have my main OpenAgents chat delegate to Codex, delegate to Claude Code in the context of a single conversation with all of that context available to agents who want it?"
5. History & Memory
"Give me the sidebar with the chats so I can actually see what's already happened. And like let me easily reference past chats. There should be a local SQLite database... Right now, all of the Claude Code and Codex conversations are just in these giant JSON blobs, not optimized for discovery at all."
6. Hassle-Free Interop (MCP or...)
"All the hoops you have to jump through to get MCP working. People say the tool registry definitions are too long so now you need to create an API from it... stop it. Stop making me think in those terms. If you're in an app, you should be able to easily pull in integrations" - or let the agent do that itself.
7. Embrace Open Source
"The leader here on the app side for coding agents is opencode. They've built a massive community of contributors... We want to do that kind of thing, but for our more opinionated agentic flow with OpenAgents."
8. Local+Swarm+Cloud Inference
"If I've got a bunch of compute on my computer, if I've got stuff that my Foundation Models API via the M2 chip is able to do for summarization, for updating title summaries-- let's use your local compute where it's needed... There should be a mix of inference possibilities. People should be able to mix and match based on their cost preferences or have that done automatically."
9. Compute Fracking
"You -- YOU -- have compute available to you that you are not doing anything with. Why are you not doing anything with it? You've got an M2 chip that's just sitting there. Are you using that compute right now to run agents? No? Then you're wasting electricity.
Well there just hasn't been any software for you to run on your computer that was just able to have agents run around the clock, or -- if you don't have any economically sensible use cases -- why can't you sell that to your neighbor who will pay you a tiny fraction of a dollar, tiny fraction of a bitcoin, to use your compute?
The big labs are not going to innovate in this direction because they are now drinking the NVIDIA koolaid, but we have no such limitations. So just remember: compute fracking, you heard it here first."
10. Revenue Sharing
"To anyone who's like, Chris why are you spilling all the all the juice here? The sauce, you're giving it all away. The alpha, you're just leaking it out here. No, no, no.
We're here to build network effects. So we're going to be open source. We're going to be building in public. We're going to monetize this. And how we're going to build the biggest network is because we're going to get developers paid by building an actual marketplace.
This is going to solve so many of the coordination problems around why MCPs suck in implementation, because no one has an actual financial incentive to maintain them or make them good.
Hey developers, you wrote an agent plugin. Would you like to put that in a registry and get paid a tiny fraction of a cent every time someone uses it?
How do you do that? Oh, a built-in bitcoin wallet.
We built this already. That's the benefit of having been around for two years and on episode 190+.
We've built all of this stuff in prototype form and now we're just mashing it into a single product now that we've got the agentic coding go-to-market piece figured out."
---
"What would you add to this list? Please tell us.
We are aiming to get at least basic versions of every one of these ten upgrades in place by the end of this year, six weeks from now."
WHAT WOULD YOU ADD? 😇
X (formerly Twitter)
OpenAgents (@OpenAgentsInc) on X
Episode 195: Designing 10x Better
How can our product become ‘10x better’ than the competition?
We discuss ten upgrades:
1. Ditch the TUI (a...
Cookin
OpenAgents Episode 194: The Trillion-Dollar Question
What percentage of global AI workloads in 2030 will run on Apple silicon?
ChatGPT Pro thinks the range could be anywhere from 7% to 35%, depending in part on how broadly its edge inference APIs are adopted by developers.
We've got a few things to say about that.
We demo agentic search through a codebase using nothing but Apple's on-device Foundation Models API.
It works-- even while offline. It's local and private with a marginal cost of zero.
How far can we take this?
What percentage of coding agent workloads can shift from cloud to the edge?
We are about to find out.
X (formerly Twitter)
OpenAgents (@OpenAgentsInc) on X
Episode 194: The Trillion-Dollar Question
What percentage of global AI workloads in 2030 will run on Apple silicon?
ChatGPT Pro thinks the range ...
Episode 193: Codex & Claude Code On Your Phone
Introducing the OpenAgents Tricoder mobile app, enabling developers to easily use OpenAI Codex and Claude Code from their phone, anywhere in the world.
The app is live now in TestFlight, coming soon for Android, and 100% open-source under Apache 2.
How it works:
1. Download the app
2. Run a single npx command from your desktop and get a pairing QR code
3. Scan the QR code from the app and start chatting
"I'm excited for developers to experience what I experienced last week, where I had probably my single greatest daily increase in my own personal productivity just getting this working, walking around my house and talking to it."
Pairing devices can be done in either of two ways:
1. Local network -- Direct pairing over wifi, no accounts needed. Devices must stay nearby on the same network
2. @Tailscale VPN -- Enables you to stay connected anywhere. Leave your desktop on at home, use the mobile app from the grocery store. Just needs a free install of Tailscale on both devices. (Support for other VPNs coming soon)
The desktop bridge communicates with Claude Code and Codex via the amazing new Agent Client Protocol from @zeddotdev. We'll add support soon for @opencode and other agents as users request them.
Please forgive its very basic UI and inevitable bugs. The codebase is just <1 week old but now that the hard parts are done, we'll be rapidly adding features and polish based on user feedback.
For now this app can be a nice supplement to your desktop coding work. Over the coming months, we're excited to explore replacing old-fashioned IDEs altogether.
Much more to come. Please send us feedback-- and stay tuned!
- Website: openagents.com
- Docs: docs.openagents.com
- GitHub: github.com/OpenAgentsInc/…
- Join TestFlight: testflight.apple.com/join/dvQdns5B
X (formerly Twitter)
OpenAgents (@OpenAgentsInc) on X
Episode 193: Codex & Claude Code On Your Phone
Introducing the OpenAgents Tricoder mobile app, enabling developers to easily use OpenAI Codex ...
Episode 192: OpenAgents Upgrades Itself
We ask the OpenAgents Tricoder app to edit its own code.
It commands OpenAI Codex over websockets via Tailscale, updating the app over-the-air via React Native expo-updates.
Works! No coding or IDE necessary.
Shall we automate this?
X (formerly Twitter)
OpenAgents (@OpenAgentsInc) on X
@TauriApps @convex @RuinsMMO Episode 192: OpenAgents Upgrades Itself
We ask the OpenAgents Tricoder app to edit its own code.
It commands @OpenA...
OpenAgents Episode 191: Project Tricoder
"You would think that with the hundreds of billions of dollars of VC money coming into the AI space that someone would have created a good mobile app for coding on the go.
No, nothing.
I'm not talking about remote terminals, typing with the little keyboard, or an IDE, I mean give me an app that lets me manage and talk to my coding agents on the go.
If I'm sitting on the pot why am I scrolling X when I could be scrolling updates from my coding agent?
Doesn't exist.
And before you say 'Have you tried ____?', is it open source? No? Go fuck yourself. It's got to be open source."
And so it is: github.com/OpenAgentsInc/…
Run it yourself now (Android or iOS) or fork it or wait for the TestFlight next week 👍
X (formerly Twitter)
OpenAgents (@OpenAgentsInc) on X
@TauriApps @convex @RuinsMMO Episode 191: Project Tricoder
"You would think that with the hundreds of billions of dollars of VC money coming into ...
OpenAgents Episode 190: Goodbye Claude Code
We're four weeks clean off Claude Code-- with no withdrawal symptoms!
OpenAI's Codex has worked great as a drop-in replacement. And because it's open-source, we can build powerful things on top.
Like a new coding agent mobile app that's 10x better than Anthropic's. 😂
Details this week. Stay tuned!
X (formerly Twitter)
OpenAgents (@OpenAgentsInc) on X
@TauriApps @convex @RuinsMMO Episode 190: Goodbye Claude Code
We're four weeks clean off Claude Code-- with no withdrawal symptoms!
OpenAI's Code...
OpenAgents Episode 189: Toward an Agentic MMORPG
To field the first billion AI agents on open protocols, we must innovate the medium.
So we're building the world's first agentic MMORPG: Ruins of Atlantis.
Follow along at ruinsofatlantis.com.
Watch on X: 
X (formerly Twitter)
OpenAgents (@OpenAgentsInc) on X
@TauriApps @convex Episode 189: Toward an Agentic MMORPG
To field the first billion AI agents on open protocols, we must innovate the medium.
So ...
OpenAgents Episode 188: The Dashboard
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: 
X (formerly Twitter)
OpenAgents (@OpenAgentsInc) on X
@TauriApps @convex Episode 188: The Dashboard
We finally replace our standard Claude Code usage with the new OpenAgents dashboard, a clean web app...
Stacker News
Episode 188: The Dashboard \ stacker news ~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 mul...
OpenAgents Episode 187: Mobile Sync
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: 
X (formerly Twitter)
OpenAgents (@OpenAgentsInc) on X
@TauriApps @convex Episode 187: Mobile Sync
We demo the two-way sync of Claude Code chats between our desktop app and iOS app.
Chats started on t...
Stacker News
Episode 187: Mobile Sync \ stacker news ~openagents
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 v...
OpenAgents Episode 186: Actions Per Minute
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 Claude Code usage across 277 sessions, we establish our baseline of 2.3 APM.
Rookie numbers! Now to pump them up...
Watch on X: 
X (formerly Twitter)
OpenAgents (@OpenAgentsInc) on X
@TauriApps Episode 186: Actions Per Minute
Flawed ground-truth data in agent benchmark "Humanity's Last Exam" underscores the need for better ways...
Episode 185: Hello Claude Code
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: 
X (formerly Twitter)
OpenAgents (@OpenAgentsInc) on X
@TauriApps Episode 185: Hello Claude Code
We connect OpenAgents to Claude Code, showing two chats in draggable chat windows with hotkeys for openi...
OpenAgents Episode 183: Zero Base
"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:
- Mobile sync for easy edits on-the-go
- An orchestration layer to keep Claude Code working 24/7
- 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: 
Follow along: 
X (formerly Twitter)
OpenAgents (@OpenAgentsInc) on X
Episode 183: Zero Base
"This is our sixth time deleting our codebase. And we've grown exceedingly efficient at it."
Our new challenge:
In a fre...
GitHub
GitHub - OpenAgentsInc/openagents: Agent command center (wip)
Agent command center (wip). Contribute to OpenAgentsInc/openagents development by creating an account on GitHub.
Stacker News
Episodes 183 & 184: Zero Base and Hello Tauri \ stacker news ~openagents
"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 w...
Claude’s research report on yesterday’s 7-hour outage:
OpenAgents
Episode 180: Zero to Website in 60 Seconds
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: 
X (formerly Twitter)
OpenAgents (@OpenAgentsInc) on X
@MistralAI Episode 180: Zero to Website in 60 Seconds
We preview our new 'vibe-coding' product by creating and deploying a basic website in <60...
Stacker News
Episode 180: Zero to Website in 60 Seconds \ stacker news ~openagents
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 re...
Episode 179: Claude Code Commander
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: 
v0.0.5 release notes: 
X (formerly Twitter)
OpenAgents (@OpenAgentsInc) on X
@MistralAI Episode 179: Claude Code Commander
We use five Claude Code instances in a single interface.
Commander v0.0.5 also features chat histor...
GitHub
Release v0.0.5 - Claude Code Integration · OpenAgentsInc/commander
This is an alpha pre-release version for developers.
This release introduces a groundbreaking integration with Claude Code CLI, bringing AI-powered...
Episode 178: Swarm Inference
"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: 
v0.0.4 Release notes & download instructions: 
X (formerly Twitter)
OpenAgents (@OpenAgentsInc) on X
Episode 178: Swarm Inference
"We want you to be able to sell your compute for bitcoin doing nothing but clicking this button."
We demo our new Co...
GitHub
Release v0.0.4 - NIP-90 Swarm Inference & DVM Capabilities · OpenAgentsInc/commander
This is an alpha pre-release version for developers.
This release marks a significant step towards a decentralized AI ecosystem by fully integratin...