To me, orchestration is not really the core problem. The bigger challenge is handling agent coherency over long periods of time, (drift) so my solution is a living forum-like system where agents shout to one another, document work in items, and follow doctrine handed down by the developer and work against a known specification that's checkable. I have used this workflow in several large projects that MUST be correct, and it works for me. Currently cleaning it up for other users.
pitched 17 hours ago [-]
Not saying this counts specifically but I love seeing devs who hate Jira build something like Jira to solve managing a team of agents. It’s a beautifully ironic thing to watch.
xgb84j 8 hours ago [-]
You either die a software engineer or you live long enough to see yourself become the project manager.
dummydummy1234 57 minutes ago [-]
We're all project managers now...
wccrawford 19 minutes ago [-]
Or you get laid off and go do something else. :/
toddmorey 1 hours ago [-]
I get it, but would YOU use Jira to manage agent-based work cycles?
pea 14 hours ago [-]
I think we'll see it more and more... open-ended Q&A / novel work is everyone's first experience of LLMs, but I don't think it's actually representative of most of the work people do. Coding kind of sits in the middle as it's novel but semi-structured.
Chat is great for novel open-ended work, but is terrible at concurrency - i.e. managing > 1 agent runs. As agents get cheaper, I suspect we'll see more more bounded processes where you want to run lots of items through them at once, and thus Jira-like things... (we ended up having this problem and building something like this, albeit more medieval themed [0])
We also found the other piece that Jira-style solves (and that chat makes super hard) is multi-player. I've yet to see a good implementation of a multi-player chat solution to agents working concurrently; and we found that an async model is the only sane solution to this.
I don't think people hate issue tracking system, they just hate Jira.
redhale 16 hours ago [-]
And I think most people who hate Jira actually just hate the process their company has imposed inside of Jira.
The vanilla out of the box product is actually quite close to old Trello, in simplicity. But there are so many ways to fuck it up and overcomplicate it, and so many companies proceed to fuck it up and overcomplicate it.
zerkten 2 hours ago [-]
>> And I think most people who hate Jira actually just hate the process their company has imposed inside of Jira.
I think what you describe is a problem for a lot of people, but what isn't acknowledged is that some people don't want any kind of process, or rather, they don't want to deal with any kind of friction. These people don't like Jira without the customizations. They don't like equivalent tools.
Given these tools regiment the world to some extent, many programmers are fine with the minimal friction. However, you have big problems when people who don't value any process get into positions of authority. This is also often a problem when you interface with other units of an organization who don't understand the value of a process.
saguntum 10 hours ago [-]
+1
I have learned recently that I don't inherently hate JIRA, I hate our JIRA and byzantine process flows.
I think because other task trackers like Trello are simpler and have less config options (per my last use, long ago, pre-Atlassian-acquisition), it's impossible knock on wood to get into the antipatterns I've seen in those tools.
Ironically I think one of the main goals of management I have seen consistently over time - ensuring tickets are accurate, up to date, and reflect reality - would end up much more true if the task tracking tools were just much simpler, with fewer fancy features.
ionetan 2 hours ago [-]
It might be you'd like Epiq. It is an issue tracker I built that actively does what it can to not be another Jira. It has way less fields and configurations per ticket (description, tags, assignees, attachments, comments), and it integrates with your code/repo, it is local-first and distributed so super fast.
https://ljtn.github.io/epiq/
greggh 16 hours ago [-]
This is absolutely it for me. I've never had to use a Jira instance that wasn't absolutely ruined by its maintainers.
greysonp 10 hours ago [-]
I actually just hate Jira :) It's horrendously slow for what it does, the search is mediocre at best, and I regularly run into bugs.
tomashubelbauer 5 hours ago [-]
Yeah, my company has a simple, straight-forward system, but I still dread using Jira. And I love Linear, so it's not general ticket management system hate! Jira just sucks.
makeitdouble 5 hours ago [-]
And how their company setup JIRA is more often than not a decent representation of the company's vision of how work should be done.
So what they really hate is their company. Which is usually fair and understandable.
Zambyte 16 hours ago [-]
Yup, I literally just hate their web UI. Once I found the Atlassian-blessed jira "cli" [0] (after searching for a long time for a tui, which is actually what the "cli" is primarily) I have actually be fine with using Jira again. As an added bonus, being a cli has made it easy to interface with using my AI tooling.
They released twg mainly for agents which is totally fine and useful as well.
alemanek 12 hours ago [-]
2nd this but I did need to write a session start hook to prune out most of the skills so it was just the non Rovo ones. Took about 15min to setup though so I am not complaining. twg works really well.
x-complexity 13 hours ago [-]
Exactly. A plain basic issue tracking system is all that's needed for 90% of cases.
Need a specific feature? Plug that in later when you actually need it.
dionian 2 hours ago [-]
used jira from its beta days. i never hated jira. i hate what they (companies) did with it though
How do you handle the context? As in: you have a forum like system as you say, how are agents finding the correct "posts"? How do you handle drift or specs that change over time?
j_bum 16 hours ago [-]
> The local-first work board for teams of coding agents. Nothing ships until a second agent verifies it.
> gate: failing
Gave me a good chuckle. Cool idea though, and I like the records. Reminds me a bit of the OpenAI hacking incidents.
Olscore 16 hours ago [-]
Haha. Locally it was passing. That badge is GitHub running the tests on its own machines, where a couple of new browser tests fail. Fix is going through the same loop: one agent fixes, another verifies, then it merges.
smashed 9 hours ago [-]
I'm trying to fix the "agent said work was done, it was not" problem by defining work as runnable specifications in the form of a pytest suite.
Work is first defined in new or updated specifications, then the change gets made. You have to resist making natural language Todo lists and have the agent write runnable unit tests. My project is a CLI tool so it's fairly easy.
Verifying if it's done is a matter of running the specifications test suite.
In a totally not original way, I'm testing this workflow in my own agent orchestration tool. I know, there's just so many already. I'm building it for myself.
So far, the system is holding up but it's way too early to declare it a success.
I think the same idea could be applied to other projects in different domains.
With this workflow I can read and update the specs, and run it against a built binary and be much more confident that the code works. Claude code has picked up the system without complaining for the most part.
mgw 9 hours ago [-]
Congratulations on shipping! Really interesting ideas in there, especially the Doctrine.
We do have what you call Items and Shouts in the form of an agent communication system and a Linear style issue tracker that agents and humans use together.
In our case everything around orchestration is discussed with the agent itself and they take action for the user via our CLI. We found any UI to prescribe how teams of agents should coordinate too clunky. So in our case you just tell the agent: "every codex luna max implementer gets an opencode muse spark reviewer. when a subtree is done, review with opus high.". It then sets up the graph and the system enforces the rules.
It works really well for us.
taocoyote 10 hours ago [-]
A lot of the approaches to orchestration that I have seen feels like a company hiring more managers to make the dev team work faster.
Thank you for coding something that I intended to code but have been too lazy to do.
iamjustrach 7 hours ago [-]
pullboard looks pretty interesting, how does it compare with other frameworks! do you have any benchmarks on that regard?
woah 16 hours ago [-]
> docker-agent lets you create and run intelligent AI agents that collaborate to solve complex problems — no code required.
How is "no code required" a selling point when we all have agents that can almost instantly puke out all the mostly-correct code you could want?
Code means a bit of mental engagement, more than yaml, json etc. You either review that or not review that, but it's an addition. While I am not touching anything made by docker-the-bloater anytime soon, I could think that at least.
hahn-kev 6 hours ago [-]
Yeah that is odd. Also most non programmers would say yaml is programming
partyficial 3 hours ago [-]
At the end of the day, all programming is language. it just happens to be languages normal people don't speak.
All these translation layers exist because the computers only understand 0s & 1s. Imagine talking to a person who only understood binary numbers.
blakeashleyjr 21 hours ago [-]
While I love new open source dev (especially in Go!), agent harnesses are turning into JS frameworks from yesteryear.
All the cool kids have one!
crossroadsguy 10 hours ago [-]
With the advent of LLMs my one true hope for humanity was the final death of the "JS/ilk things" like Electron, React Native, other things like that, and the culture of "everything is TS/JS or can be turned into that". Looks like it's rather growing exponentially.
lifty 8 hours ago [-]
Rust + GPUI is becoming the new hotness, and I’m all up for it.
pjmlp 21 hours ago [-]
Coupled with VSCode forks to manage them
yipinwong 18 hours ago [-]
You know which one will win for sure. ones with the worst experience.
Vue and svelte are easy to use and learn/adopt. But look what won. React.js.
So whatever the ai agent with the vast user basae will win regardless.
---
I know it's a slippery slope, but given you brought up JS framwork analogy, I had to fall into it
ravenstine 17 hours ago [-]
It's all about what story you can tell.
Cursor is easily the worst experience I've had with an AI harness, yet it was acquired for billions of dollars in spite of being a middleman tied to a ripoff of VS Code. None of the colleagues of mine who were touting it last year are still using it. But if you can make yourself look like the next big thing, you'll get money thrown at you. Just look at Omarchy.
A good experience necessarily takes time and careful thought. Nobody these days can do that while also remaining relevant, or even surviving.
disgruntledphd2 7 hours ago [-]
> Cursor is easily the worst experience I've had with an AI harness
I kinda like cursor, mostly because it provides a nice review UI and I can use whatever model I want.
Getting away from all the Claude-speak has been a revelation, and fortunately Anthropic helped me here by hyping up GLM 5.3. Like, if there's an open weight Fable competitor, then why wouldn't I use it?
hhh 9 hours ago [-]
Omarchy is such a shit distro but it has a nice enough basic ricing for the WM
shepherdjerred 11 hours ago [-]
Many people genuinely prefer React over Vue/Svelte
pjmlp 3 hours ago [-]
Some of us would rather use Angular, or none at all.
React was cool before the hooks and "use whatever" all over the place.
girvo 18 hours ago [-]
I mean as someone who was there at the time, early React was easy to learn and adopt. It’s complexity came later after it had already won
Now Angular v1, man… if I ever see another digest loop error in my life, I will scream
ravenstine 16 hours ago [-]
So glad I never had to deal with Angular, especially v1. I tried learning it and it just seemed like it would actually make applications more incomprehensible than before. React originally addressed the actual problem that most frameworks mistook for not being that important. I still don't particularly like React, but it makes sense why it became popular.
v3ss0n 12 hours ago [-]
A good model with svelte make things buttery smooth.
Terr_ 18 hours ago [-]
"Look, LLMs will free you from the tyranny of frameworks!"
"Uh, OK, so how do I get this thing working? Where are the docs?"
"Well, first you install its unique framework..."
caskeycoding 20 hours ago [-]
[flagged]
aklingel 14 hours ago [-]
[flagged]
verdverm 20 hours ago [-]
Go doesn't have a good mod/plugin story for harness devs to provide to their users
I say this as a gopher who also has a custom harness written in Go, it's a real challenge compared to the TS setups, but TS plugins are also a security concern
gandreani 19 hours ago [-]
I agree! Comes with the territory of a compiled language I suppose?
I haven't given this much thought (I also just started with golang last year) but I'm assuming the only real path here is to provide extension SDKs in Lua or other languages whose interpreters have been implemented in go.
I think that's what grafana's k6 [1] does with a JS interpreter
I was thinking I recalled something like that, but the nice thing about the TS ecosystem is that you can write the same language, importing and using the harness sdk types.
Go has the plugin package, but I haven't actually seen anyone use it (outside of toys and blog posts)
fails at step two, precompiled binary is already built, you can't change the code
why not just use an SDK where you are using a plugin?
otterley 17 hours ago [-]
Why isn’t IPC good enough?
verdverm 16 hours ago [-]
My custom harness has a dagger based environment, binary runs in the host, every tool call and file modification creates a new layer in a container - for better session time travel and forking
It may work for some things, but you really want to be wired into that system to do the more interesting things.
otterley 16 hours ago [-]
I don't understand why dynamically loading code into a Linux process is essential to make this work. Can you explain?
verdverm 15 hours ago [-]
I didn't say it couldn't work, it's just way more complexity and effort with IPC or Go than TS. That's one of the reasons harnesses are choosing TS. It's also a very popular language.
If, like me, you couldn't find any security-related info on the linked page.
gregwebs 19 hours ago [-]
Docker Agent is a harness. There is a sandbox mode that can be used to run it in docker sandbox (a VM, not a container). If you don't use sandbox mode then I assume it is running in a container.
If you don't want to use their harness then you wouldn't use docker agent and instead use their `sbx` cli to run the harness of your choice (claude, codex, pi, etc).
I think it will be great if Docker can get people used to using secure VMs. I am developing a similar project (still a work in progress): https://github.com/gregwebs/agent-vm
I've found sbx to be very helpful. really like the sentinel value wrapper they have going so you can add secrets but the model can't see them. Outbound calls get looked up by sentinel value and the real one goes out to whatever API you're auth'ing too. There's other features but just having claude run in a sandbox and easily see what it does and doesn't have access to has been great.
gwlthr 16 hours ago [-]
I just wish sharing whitelisted domains between sandboxes were easier or more intuitive. Last time I tried doing this with sbx I was handling their yaml files by hand.
14 hours ago [-]
ShinyLeftPad 20 hours ago [-]
i remember going through the entire docs of docker sandbox and there was not one mention of attack vectors. did they fix that?
kydanet 19 hours ago [-]
[flagged]
booster-rooster 51 minutes ago [-]
[flagged]
magnusokik 4 hours ago [-]
We built something similar, the ideas are strangely converging for production it feels like. But we used routing rather than direction agent invocation of agents. It gets exhausting to keep track of large number of concurrent agents. Best to keep a single orchestration agent that can route to agents based on capabilities.
Better read the terms and conditions and if they can retain your data, docker now collects inputs and outputs ...
pomsense 15 hours ago [-]
The models are converging (directionally), and the rest of us, including all these agent harnesses, are trying to figure out how to stay relevant
rodolphoarruda 18 hours ago [-]
Last year (2025), I lost count of how many times I tried using an LLM to set up Docker. It was still the era of prompting, then copy-pasting the response and seeing if it worked... and it almost never did. It’s great to see this new Docker agent. For me, it would be even more appealing to see an agent and a model specialized in Docker working together, capable of proposing advanced configurations and getting them working on the first try.
aheritier 17 hours ago [-]
Modern models should be better with mainstream technologies like docker engine or docker compose, but still to try to help them we started to work on distributing skills ( https://github.com/docker/skills ) in addition of our specialized agent (gordon) integrated in various products.
scottydelta 6 hours ago [-]
I literally built this for self hosting apps at Tarvis.io
You can drop any GitHub repo and the agent builds and deploys the app to your Tarvis workspace along with taking care of ssl domain and any other configuration and making sure the app is healthy.
17 hours ago [-]
beckford 20 hours ago [-]
Docker Agent could be beneficial for research studies. For example, while writing a ML paper about agents I need to rerun experiments so that:
- others can repeat my results
- validate that variability from LLMs is not causing overconfidence in the results
But currently uv is good enough to create isolated, repeatable environments. And it isn't limited to Linux like standard Docker. So when I want to test small samples on my local PC's GPU (Windows or mac) before running on beefier hardware, I can do that easily.
agentdev001 15 hours ago [-]
I mean, if you're going to do that at scale, not that you are, but something like https://github.com/kvcache-ai/AgentENV is much more suitable for research purposes
5 hours ago [-]
CBLT 19 hours ago [-]
I tried really hard to make this work for me a couple of weeks ago but it was the brittlest harness out of any that I've used. I'd come back when it's more mature.
dgageot 19 hours ago [-]
Would love to know what didn't work for you
CBLT 19 hours ago [-]
Sessions just broke all the time for me. The one time I dug into it, it ended up being a known issue where if codex returned over 10k characters for a turn it breaks the session. Because docker agent does not use protocols like ACP, instead trying to parse Codex's internal state in a brittle manner.
I tried not to do anything too crazy, but even use using an API key in the docker agent natively was getting me sessions that would hang and couldn't be recovered.
Combination with Codex is indeed not the most common use case around us. I'll see what can be improved. Sorry that it broke your workflow!
nujabe 19 hours ago [-]
How is not using it with the most popular coding agent not a common use case?
girvo 18 hours ago [-]
Not the most common use case around them: likely meaning that the Codex harness isn’t used that often internally at Docker, is what I would surmise, at least that is how I read it.
I work at another big tech company, and up until recently that would’ve been true for us as well (but it’s changed now, we partnered with OpenAI)
FirstClassTree 5 hours ago [-]
[flagged]
triyambakam 19 hours ago [-]
> bittlest
Sorry, what do you mean there?
shawabawa3 19 hours ago [-]
Typo for brittlest, most brittle
CBLT 18 hours ago [-]
Correct. Updated the message to brittlest. Thank you.
maxdo 21 hours ago [-]
they hope they can annoy and email every person in the org asking for money , same way as they did it with docker.
looks like a weird abstractions. why do i need this if i have modal.com, e2b, cloudflare that use original docker + some toolings around + way to run + isolations on network level.
mplewis 21 hours ago [-]
What does this have to do with Docker?
cryptos 8 hours ago [-]
This was also my first reaction. I'm always doubtful if projects add features that are not really close to the core use case.
Does anyone remember all these web portals from 2000? What people mostly wanted was a search engine but they added everything else and lost focus.
speedgoose 21 hours ago [-]
I guess people at Docker wanted to make an agent.
Having it docker branded, I could understand. It’s confusing but the docker brand is strong.
But exposing it as a docker subcommand is very confusing to me.
dgageot 20 hours ago [-]
You don't really have to use the docker agent sub-command. docker-agent is a standalone binary. When it was created, though, 1.5 year ago, the idea was that it would be the docker compose for agents (original name was cagent, compose for agents).
But it evolved differently and although it runs very well in docker containers and docker sandboxes, it also runs very well anywhere else.
binsquare 21 hours ago [-]
It reads to me like chasing trends
throwitaway222 21 hours ago [-]
That's the economy we've always been in. X is popular, if your company doesn't have a solution for X you're irrelevant.
sleepybrett 19 hours ago [-]
that's all docker has been doing for years.
verdverm 20 hours ago [-]
the tools and features certainly indicate so
bmacho 20 hours ago [-]
Based on the repo short description and the first sentence of the readme:
It is called 'Docker' as the company, and it has nothing to do with the container technology.
redleader55 21 hours ago [-]
The quest for staying relevant.
20 hours ago [-]
nwhnwh 19 hours ago [-]
This made me laugh. Not sure why. But the whole situation is very absurd now.
sneak 19 hours ago [-]
Docker is rapidly fading into irrelevance now that they have missed their strategic acquisition interval via the Microsoft collab misstep, and now has to hype chase as fewer and fewer people believe in their long term viability as a company.
Great tech. Not a business.
esafak 20 hours ago [-]
It's the Docker you know and love... with AI!
tamimio 21 hours ago [-]
>What it is, what it isn’t
Yep, open ai sol model wrote that.
lukemercado 21 hours ago [-]
It frustrates me that there's a prisoners dilemma in communicating this to other humans. If I flag it and write it out (as you've done) I've let the author know that they're losing trust and let others know that they should be more skeptical. I've also created the perfect eval data pair for the ai labs. It's deeply frustrating.
baby_souffle 19 hours ago [-]
I think the cat is out of the bag.
There was a brief point in time at the beginning of the internet where if you saw an image online you could be kind of confident that it hadn't been manipulated significantly... But somewhere around the mid to late 2000s it became prudent to just assume any image you've seen online got at least a blemish filter pass through something like Photoshop.
Same thing now with written text. Sometimes you'll be a little bit more or less sure than an llm produced the output but never able to say 100% confidently.
cyanydeez 19 hours ago [-]
AI is going to eradicate, for good, all trust in the Internet.
That's a benified "not a drawback".
IncreasePosts 20 hours ago [-]
Your probably spare yourself some RSI by inverting this and only writing out a message when you find human generated content on hn
kingcauchy 15 hours ago [-]
I'm curious about these agent harness frameworks that release their harness before they've released a good agent on top. It's a little cart before the horse.
maximilianfeix 5 hours ago [-]
Really important repository for me. I virtualize all my cloud server with docker
Bringing first-class agent orchestration directly into containerized environments is a logical step for secure, reproducible developer workflows.
15 hours ago [-]
mococa 21 hours ago [-]
Pretty vague
tonymet 15 hours ago [-]
If Docker is containerized resources ( cpu, memory, iops, network) with configured limits , I would like to see more ACLs around command and credential restrictions
Something like a containerized sudo ACL for commands and for network credential , scoped by oauth scope
That way you could truly establish boundaries for an agent before it’s launched , and it could request additional permissions during execution .
Miyamura80 4 hours ago [-]
Hey! We built infrastructure that can provide ACLs around command & credential restrictions, using MCP as auth middleware encrypted credentials to prevent agent overpriviledge - see sealgate.ai and let me know if this solves any issues here
Sattyamjjain 7 hours ago [-]
[flagged]
sebastienburel 10 hours ago [-]
[flagged]
smashah 19 hours ago [-]
Why can't we set the harness? Seems like the missing piece
sergiotapia 20 hours ago [-]
very weird. why does this have dockers name on it? might as well use an agent harness from kohl's or steak n' shake. odd..
dgageot 20 hours ago [-]
It was created to be the docker compose for agents. 2 years ago, people, including ourselves, started to mix agentic loops and non agentic components in docker compose files. We created docker agent to make this more powerful.
At the end, the link with docker compose is just the yaml form. Which by the way can be replaced with hcl files or Go code.
20 hours ago [-]
esafak 20 hours ago [-]
What's new or interesting here? Docker's AI story ought to be around sandboxing, yet the word appears nowhere. Oh, and it's YAML, which I despise.
dgageot 20 hours ago [-]
Docker Agent predates Docker sandboxes. It was created almost two years ago when not everybody had a AI harness. Nowadays, it does run very well in Docker Sandboxes but it runs also very well anywhere you like.
skyzhao1223 12 hours ago [-]
[flagged]
throwrioawfo 19 hours ago [-]
gimmick
leowoo91 16 hours ago [-]
is there a word for enshittification by ai?
NamlchakKhandro 13 hours ago [-]
i mean... what's the point.
just use and customise Pi.
Nothing else even comes close.
chelseahermes 1 hours ago [-]
[flagged]
masonroy12 2 hours ago [-]
[flagged]
chengjunsuger 6 hours ago [-]
[flagged]
singularityisne 8 hours ago [-]
[flagged]
alescalaios 6 hours ago [-]
[dead]
lin7c 14 hours ago [-]
[flagged]
bewareofscams 24 minutes ago [-]
[dead]
benjy3379 20 hours ago [-]
[flagged]
folayii 14 hours ago [-]
[flagged]
oxcartctl 21 hours ago [-]
[dead]
ravenstine 16 hours ago [-]
Just what I need in my life; more YAML! /s
I'm not sure why anyone would want this. Is there something this actually does better than any other harness? Do current harnesses suck that bad at orchestrating things like Docker? If I do all my work inside a Linux VM and tell an agent inside of it what I need done, it figures out everything, including container orchestration.
The very job that AI gents are meant to do should mean that most of the documentation for this Docker Agent is obsolete/unnecessary.
rfgplk 20 hours ago [-]
> Go
Nowadays there are only two justifiable public languages you should be using for anything
a) C++
b) Rust
Rust itself is dubious due to abysmal compile times and the fact that the only guarantees it gives you are of security (aka a skill issue). Modern LLMs write C++ that is as safe if not safer than Rust. Any other language choice is objectively wrong.
* For those inquisitive enough the keyword "public" is doing all the heavy lifting here. Pretty much everyone should be developing and using an in-house DSL at this point.
furyofantares 20 hours ago [-]
Yeah well I'm doing everything in AssemblyScript.
triyambakam 19 hours ago [-]
This is an almost rage bait take, but in any case I agree that the models ability to write correct code and fuzz and test that code does make language choice a different tradeoff than it was before.
I've been working on Pullboard and just open sourced it: https://github.com/pullboard-dev/pullboard
To me, orchestration is not really the core problem. The bigger challenge is handling agent coherency over long periods of time, (drift) so my solution is a living forum-like system where agents shout to one another, document work in items, and follow doctrine handed down by the developer and work against a known specification that's checkable. I have used this workflow in several large projects that MUST be correct, and it works for me. Currently cleaning it up for other users.
Chat is great for novel open-ended work, but is terrible at concurrency - i.e. managing > 1 agent runs. As agents get cheaper, I suspect we'll see more more bounded processes where you want to run lots of items through them at once, and thus Jira-like things... (we ended up having this problem and building something like this, albeit more medieval themed [0])
We also found the other piece that Jira-style solves (and that chat makes super hard) is multi-player. I've yet to see a good implementation of a multi-player chat solution to agents working concurrently; and we found that an async model is the only sane solution to this.
[0] https://pumpup.com
https://yegge.ai/gastown
The vanilla out of the box product is actually quite close to old Trello, in simplicity. But there are so many ways to fuck it up and overcomplicate it, and so many companies proceed to fuck it up and overcomplicate it.
I think what you describe is a problem for a lot of people, but what isn't acknowledged is that some people don't want any kind of process, or rather, they don't want to deal with any kind of friction. These people don't like Jira without the customizations. They don't like equivalent tools.
Given these tools regiment the world to some extent, many programmers are fine with the minimal friction. However, you have big problems when people who don't value any process get into positions of authority. This is also often a problem when you interface with other units of an organization who don't understand the value of a process.
I have learned recently that I don't inherently hate JIRA, I hate our JIRA and byzantine process flows.
I think because other task trackers like Trello are simpler and have less config options (per my last use, long ago, pre-Atlassian-acquisition), it's impossible knock on wood to get into the antipatterns I've seen in those tools.
Ironically I think one of the main goals of management I have seen consistently over time - ensuring tickets are accurate, up to date, and reflect reality - would end up much more true if the task tracking tools were just much simpler, with fewer fancy features.
So what they really hate is their company. Which is usually fair and understandable.
[0] https://github.com/ankitpokhrel/jira-cli
Need a specific feature? Plug that in later when you actually need it.
How do you handle the context? As in: you have a forum like system as you say, how are agents finding the correct "posts"? How do you handle drift or specs that change over time?
> gate: failing
Gave me a good chuckle. Cool idea though, and I like the records. Reminds me a bit of the OpenAI hacking incidents.
Work is first defined in new or updated specifications, then the change gets made. You have to resist making natural language Todo lists and have the agent write runnable unit tests. My project is a CLI tool so it's fairly easy.
Verifying if it's done is a matter of running the specifications test suite.
In a totally not original way, I'm testing this workflow in my own agent orchestration tool. I know, there's just so many already. I'm building it for myself.
So far, the system is holding up but it's way too early to declare it a success.
You can check it out here:
https://github.com/egzo-ai/egzo/tree/main/specs
I think the same idea could be applied to other projects in different domains.
With this workflow I can read and update the specs, and run it against a built binary and be much more confident that the code works. Claude code has picked up the system without complaining for the most part.
We also open-sourced a similar system called https://github.com/madeinorbit/podium
We do have what you call Items and Shouts in the form of an agent communication system and a Linear style issue tracker that agents and humans use together.
In our case everything around orchestration is discussed with the agent itself and they take action for the user via our CLI. We found any UI to prescribe how teams of agents should coordinate too clunky. So in our case you just tell the agent: "every codex luna max implementer gets an opencode muse spark reviewer. when a subtree is done, review with opus high.". It then sets up the graph and the system enforces the rules.
It works really well for us.
Thank you for coding something that I intended to code but have been too lazy to do.
How is "no code required" a selling point when we all have agents that can almost instantly puke out all the mostly-correct code you could want?
All these translation layers exist because the computers only understand 0s & 1s. Imagine talking to a person who only understood binary numbers.
All the cool kids have one!
Vue and svelte are easy to use and learn/adopt. But look what won. React.js.
So whatever the ai agent with the vast user basae will win regardless.
---
I know it's a slippery slope, but given you brought up JS framwork analogy, I had to fall into it
Cursor is easily the worst experience I've had with an AI harness, yet it was acquired for billions of dollars in spite of being a middleman tied to a ripoff of VS Code. None of the colleagues of mine who were touting it last year are still using it. But if you can make yourself look like the next big thing, you'll get money thrown at you. Just look at Omarchy.
A good experience necessarily takes time and careful thought. Nobody these days can do that while also remaining relevant, or even surviving.
I kinda like cursor, mostly because it provides a nice review UI and I can use whatever model I want.
Getting away from all the Claude-speak has been a revelation, and fortunately Anthropic helped me here by hyping up GLM 5.3. Like, if there's an open weight Fable competitor, then why wouldn't I use it?
React was cool before the hooks and "use whatever" all over the place.
Now Angular v1, man… if I ever see another digest loop error in my life, I will scream
"Uh, OK, so how do I get this thing working? Where are the docs?"
"Well, first you install its unique framework..."
I say this as a gopher who also has a custom harness written in Go, it's a real challenge compared to the TS setups, but TS plugins are also a security concern
I haven't given this much thought (I also just started with golang last year) but I'm assuming the only real path here is to provide extension SDKs in Lua or other languages whose interpreters have been implemented in go.
I think that's what grafana's k6 [1] does with a JS interpreter
[1] https://github.com/grafana/k6
Go has the plugin package, but I haven't actually seen anyone use it (outside of toys and blog posts)
https://oneuptime.com/blog/post/2026-01-25-plugin-system-go-...
why not just use an SDK where you are using a plugin?
It may work for some things, but you really want to be wired into that system to do the more interesting things.
jk its trash
If, like me, you couldn't find any security-related info on the linked page.
If you don't want to use their harness then you wouldn't use docker agent and instead use their `sbx` cli to run the harness of your choice (claude, codex, pi, etc).
I think it will be great if Docker can get people used to using secure VMs. I am developing a similar project (still a work in progress): https://github.com/gregwebs/agent-vm
You can drop any GitHub repo and the agent builds and deploys the app to your Tarvis workspace along with taking care of ssl domain and any other configuration and making sure the app is healthy.
But currently uv is good enough to create isolated, repeatable environments. And it isn't limited to Linux like standard Docker. So when I want to test small samples on my local PC's GPU (Windows or mac) before running on beefier hardware, I can do that easily.
I tried not to do anything too crazy, but even use using an API key in the docker agent natively was getting me sessions that would hang and couldn't be recovered.
I work at another big tech company, and up until recently that would’ve been true for us as well (but it’s changed now, we partnered with OpenAI)
Sorry, what do you mean there?
looks like a weird abstractions. why do i need this if i have modal.com, e2b, cloudflare that use original docker + some toolings around + way to run + isolations on network level.
Does anyone remember all these web portals from 2000? What people mostly wanted was a search engine but they added everything else and lost focus.
Having it docker branded, I could understand. It’s confusing but the docker brand is strong.
But exposing it as a docker subcommand is very confusing to me.
But it evolved differently and although it runs very well in docker containers and docker sandboxes, it also runs very well anywhere else.
It is called 'Docker' as the company, and it has nothing to do with the container technology.
Great tech. Not a business.
Yep, open ai sol model wrote that.
There was a brief point in time at the beginning of the internet where if you saw an image online you could be kind of confident that it hadn't been manipulated significantly... But somewhere around the mid to late 2000s it became prudent to just assume any image you've seen online got at least a blemish filter pass through something like Photoshop.
Same thing now with written text. Sometimes you'll be a little bit more or less sure than an llm produced the output but never able to say 100% confidently.
That's a benified "not a drawback".
Something like a containerized sudo ACL for commands and for network credential , scoped by oauth scope
That way you could truly establish boundaries for an agent before it’s launched , and it could request additional permissions during execution .
At the end, the link with docker compose is just the yaml form. Which by the way can be replaced with hcl files or Go code.
just use and customise Pi.
Nothing else even comes close.
I'm not sure why anyone would want this. Is there something this actually does better than any other harness? Do current harnesses suck that bad at orchestrating things like Docker? If I do all my work inside a Linux VM and tell an agent inside of it what I need done, it figures out everything, including container orchestration.
The very job that AI gents are meant to do should mean that most of the documentation for this Docker Agent is obsolete/unnecessary.
Nowadays there are only two justifiable public languages you should be using for anything a) C++ b) Rust
Rust itself is dubious due to abysmal compile times and the fact that the only guarantees it gives you are of security (aka a skill issue). Modern LLMs write C++ that is as safe if not safer than Rust. Any other language choice is objectively wrong.
* For those inquisitive enough the keyword "public" is doing all the heavy lifting here. Pretty much everyone should be developing and using an in-house DSL at this point.