I see some tools like this that keep popping up (don't mean that in a bad way! it's clearly exciting and the README itself compares itself to similar tools). however, for coordination strategies like this, aren't you always having to use token-based pricing via some API Key? that's the largest think that holds me personally back from getting into something like these frameworks. With a claude code max plan, all my delegation and coordination has to be done within a session (between some agents) with persisted artifacts. Unless I'm missing something that has changed?
Perhaps it's all moot as the usage you get from a subscription plan will eventually no longer be subsidized. Also, I have to wonder about what layers of coordination done externally to a model can be persistently better than within tool coordination? Like, with an anthropic feature like agent teams, I feel like it might be tough to beat anthropic native coordination of various Claude sessions because they might have better internal tool and standards awareness, which makes feeling like plugging something like this more difficult unless one's goal is to plug something like this into an open source model.
Geniunely curious how other people are thinking about this!!
Edit: I actually see that this tool claims that it can run within your existing Claude Code subscription, so now I'm extra interested.
If you invoke Claude Code with --input-format stream-json --output-format stream-json, you can use it headlessly. I built a personal UI / orchestration framework around it. Most features are available, but not exactly all (e.g. there is no way to undo via this protocol, but you can still do it manually by terminating / editing the session file / resuming). Other agentic software has similar features (Codex uses JSON-RPC, Copilot CLI has ACP which is also based on JSON-RPC).
disclaimer: I work on a different project in the space but got excited by your comment
DeepSteve (deepsteve.com) has a similar premise: it spawns Claude Code processes and attaches terminals to them in a browser UI, so you can automate coordination in ways a regular terminal can’t: Spawning new agents from GitHub issues, coordinating tasks via inter-agent chat, modifying its own UI, terminals that fork themselves.
Re: native vs external orchestration, I think the external layer matters precisely because it doesn’t have to replicate traditional company hierarchies. I’m less interested in “AI org chart” setups like gstack (we don’t have to bring antiquated corporate hierarchies with us) and more in hackable, flat coordination where agents talk to each other via MCP and you decide the topology yourself.
I was intrigued and had a look at deepsteve.com, but I couldn't figure the website out. I'm guessing it won't give you any information about it until you install it?
Deepsteve is a node server that runs on your machine, so the website is designed to look like DeepSteve's UI. You really just access it at localhost:3000 in your browser, not via deepsteve.com
You could use something like GLM 5 which is very capable. You get APIKEY and you don't have to pay for tokens if you stay within generous limits. And if you exceed them it's many times cheaper than frontier models.
I was also just recommended this interview on youtube. honestly it makes sense if the algo decided it was the right time to recommend this video and resultantly this post is making it's way to front page of HN
I subscribe to the channel, so I had already downloaded the episode. But glad PE is getting some algorithm-love; it's a great channel/podcast. Gergely is a great interviewer.
genuinely curious if you have some sources I can read on the subject? most of the benefits/papers I've seen have not touched on or included studies for patients on GLP's where weight loss was ruled out as the factor?
Actually even in the very beginning I saw numerous studies showing effects outside weight loss, I'm sure a search would find them. I remember seeing at least 3-4 a couple years ago.
im surprised this is earning such downvotes. idk about the "opinionated" vm perspective but I think it needing its own engine oe not is at least something worth considering. firefox has been my go-to alt browser for years as my backup to chrome. it was what I would use to "test again in another browser" but as time has gone by, more and more stuff just doesn't work on firefox :(
It's already problematic to have Chromium dominating/near-monopolizing, and add salt to the wound letting Gecko die this way.
Chromium is so prevalent as an engine, that most developers don't test their code on Firefox and just tell everyone to use Chrome/Chromium when they run into issues.
This has the unintentional side-effect of strong-arming the W3C into compliance with the engine and not the other way around. Why do we bother with the W3C then? if they are powerless and Chromium can do as they please?
>> This has the unintentional side-effect of strong-arming the W3C into compliance with the engine and not the other way around.
I don't want any engine to have that much dominance, but I especially don't want that dominating engine owned by an ad company who's main goal is to spy on people.
I thought the FDA guideline was once the internal temperature reaches 160 or 165 or something it didn't need to sustain that temperature? it was only the lower temperatures that required some duration to achieve the same log reduction as reaching 160/165?
That gets you your log7 reduction of salmonella, so it is safe to eat, but I don't know if it would be "cooked" (changing to an acceptable texture) if you could instantaneously bring it to 165 F.
I have no idea what that cooking process is like. In a water bath, I run chicken breast at 62C instead of 60C because the texture is better for dicing and putting in kid's lunches or wraps. I might try 60C if I was searing and serving whole. I haven't done dark meat this way, but I suspect it'd need a higher temperature or time to break down connective tissue. And I know that for lower temperatures (58C? - I haven't made that in years), you need to hold short ribs for a couple of days.
I can say I've cooked chicken sous vide incorrectly before that had cooked long and hot enough to be safe, but the texture and feel of the meat could only be described as a meat gusher, if you've ever had those candies. Every bite exploded with liquid and the meat itself was squishy, it was very disgusting
Are you certain the person you just replied to is not in a marginalised group? If that person is, would you be running afoul of that law with "Don't be a moron."?
Any chance you mean the ACA? (affordable care act). GP I think is talking about the AMA as a body that artificially constrains the supply of dr's (at least that is my guess as GP also mentions reducing limits on building hospitals).
IMO the GP is touching on removing regulatory burdens (more traditionally republican/conservative ideas) and adding in funding/care via medicare for all etc (democrat position). the combination of reducing/improving/simplifying regulatory burdens while increasing government spending seems to be a combination of ideas that hasn't been winning enough support. afaik, Ezra Klein in his book Abundance is one of the only voices trying to push this balance.
Perhaps it's all moot as the usage you get from a subscription plan will eventually no longer be subsidized. Also, I have to wonder about what layers of coordination done externally to a model can be persistently better than within tool coordination? Like, with an anthropic feature like agent teams, I feel like it might be tough to beat anthropic native coordination of various Claude sessions because they might have better internal tool and standards awareness, which makes feeling like plugging something like this more difficult unless one's goal is to plug something like this into an open source model.
Geniunely curious how other people are thinking about this!!
Edit: I actually see that this tool claims that it can run within your existing Claude Code subscription, so now I'm extra interested.