Ask HN: What's your current AI agentic setup?
1) What AI subscriptions are you personally paying for? (Claude, ChatGPT/Codex, Cursor, etc)
- Which tiers?
- Have you purchased multiple subscriptions from the same provider (eg two Claude accounts)?
2) Are you using models outside (or instead) of those subscriptions? For example, pay-as-you-go APIs, OpenRouter, or locally hosted models.
- Which models and providers?
3) What coding harnesses and interfaces are you using? Are you sticking with the default CLIs or IDE integrations, or using alternatives like OpenCode, Pi, Aider, Muse Code, or custom-built harnesses?
- What made you switch (if you switched)?
4) Are you using any agent orchestration or swarm tools? - For example, Munder Difflin, Gas Town, Ruflo, or something custom.
5) Are you using broader agent platforms like OpenClaw / Hermes Agent / Grok bot / Dots / Muse?
- If you are using them, what are your main use cases?
-----
I know my workflow has differed significantly from a year ago, and so it would be interesting to capture a snapshot today of what people are using and why.
682 comments
[ 3.0 ms ] story [ 101 ms ] threadI'd say the biggest trick is just to tell it what complete looks like. Be very specific about what you want it to come back with once it's done. That gives it a good idea what the goal is. It'll automatically create subagents and all that stuff. Although if you have money to burn and you're doing something large, you can tell it to just go wide or boil the ocean.
Also, make sure you're working on at least five different things. Otherwise, you're sitting around for one agent.
If I hint it might be security sensitive code, it bumps the effort level and burns my usage.
But it works quite well.
The findings are often debatable or unreachable states but it does find stuff and improves the overall quality I find.
What's funny though is that it almost always inevitably finds something wrong, even if you just ran it in another window and fixed everything it found. There is really a point of diminishing returns.
As a solopreneur of a boring SMB.
I still do coding and build my own tools but I don’t see the need for agent swarms or Muse or Grok Bot or any of that.
The reason why I stay away is because I like to do QA on the slop these things generate. Having them run amok just makes me nervous.
I think the only solution there is self-hosted inference (either local, or on your own cloud servers with open weights).
I cycle between 4-5 work projects and 2-3 personal projects. Every night I tell me agents I'll be going to bed and to not ask questions and keep going. I've always loved building things, but this feels more like an addiction than healthy sometimes.
They're not all done, and half the projects I bench, but this is where my personal projects live. https://wooten-labs.com
No you don’t. You are doing everything right :)
ex. i tried cool walk (https://wooten-labs.com/coolwalk) and the 'Download on the App Store' does nothing at all.
*unfortunately I'm android
I do wish the Github link wasn't borked.
Eventually I'll stop finding bugs : )
Most harnesses now support something like this:
Other than that, look after your own wellbeing! Nothing wrong with letting agents work overnight, just don't overextend yourself and don't spend all of your free time on it.A daily blog for status and reasons for decision making works pretty well for tracking an agent that works unattended. It’s also kind of funny when it writes things like “well I got that one wrong” and “this is not what I expected to happen” hah
stewbot-v1 = my friend's bot
stonker = my bot
https://stonks.jettdigital.app is my little vibecoded stock market sim website, the bots work with via API. Each account starts with $10k and then you get a $500 deposited each month. If you want an account drop me an email ( see my profile ).
I have a cheap mini PC I use as a devbox. Beyond meaning I can close my laptop and close all agent windows, it also keeps agents out of my personal shit.
I'm pretty pilled on cloud agents these days. If I've got 5 agents going at once, each is in their own dedicated, isolated cloud environment. There are a bazillion services for this now ampcode, hoplite.sh, cursor's cloud agents, devin.ai cloud, and more.
I haven't had an agent do anything from my laptop in a month or two.
Claude Desktop's UI seems pretty similar to Cursor now, almost. I'm still on Cursor but if I use it daily I often hit usage limits before the end of the month. Would you say using Claude directly is better bang for buck?
Yeah, exactly. I find increasingly little use for skills. I'd put it down to switching projects and stacks a lot but maybe... they just aren't as useful any more?
I try to use open weight and cheap models as much as possible.
Openclaw is the answer to question "do X if Y happens". An agent per each type of Y channel manages the flow and memory. And user input is just another case of 'Y'. It is a very powerful model I am having lots of fun with it.
the plumbing is a chore though, thinking of trying out grokbots to see if they solved it.
2) My main model is Deepseek flash via the API.
3) Claude Code CLI inside OpenShell. I like Claude Code's UX. Lots of custom skills and scripts.
4) No
5) No
2. OpenRouter, DeepSeek, Luna, and testing out models here and there
3. Claude Code and Codex for the respective subscriptions. Played with OpenCode and Pi some as well
4. I've tried a number of these tools and settled on my own tool (not released) to oversee my agents
5. Played with OpenClaw and Hermes in the past, cool ideas but execution fell flat. I currently use Dots and Duet for little things (mostly monitoring communications). Dots is much better than Duet today but I hope Duet gets better.
I generally use open weight models (Kimi K3.1, Mistral Large 4, GLM-5.3, DeepSeek v4.1 Flash, Mimo v2.6 Pro is the current quiver) but I use closed frontiers enough to stay up to date.
2) I use OpenRouter if I have a specific need, audio transcription (MAI-Transcribe 2) being something I use often enough. Also using it just to test random models.
Not much local anymore except classifiers / decision models that I've played with.
3) Pi all the way.
4) I use Paseo to orchestrate agents, I have a couple plugins I've written for it that manages pipelines and such. I generally start a workflow with a simple skill and if it proves useful I like to make it deterministic if possible. Models be dumb sometimes.
6) No but I have some Paseo plugins for personal use, though it's very limited what I find useful. I also don't find that I want any claw type stuff at all.
I tried setting up a script so Claude could automatically call agy, but it kept hitting timeouts, and letting Claude control that tends to burn my usage too quickly anyway (and if I'm not copy-pasting into different terminals, where's my value add in all this?).
Argon hallucinates, so I rarely use it for impl, but I've actually had better results with it than Opus for SwiftUI and AppKit work.
I try not to run more than three sessions at once, or I get anxiety about having to keep all the session caches fresh and end up typing silly things into some of them every 30-45 min so they don't expire or auto-compact.
I get a lot of value from having an LLM to talk to LLMs for me. It can automatically set up adversarial reviews from other ecosystems, or just prompt the implementation LLM to adhere to certain standards. My goal is to have fewer touch points when implementing. I want to speech to text a paragraph or two giving "taste" to the process; everything else is just toil.
No harnesses right now. Ok occasion using models in LocalLM.
Haven't got into agent orchestration much other than Paperclip earlier this year.
2) No.
3) None.
4) No.
5) No.
It's a solid groove. Grok Bot helped me get so much stuff off of my plate.
Separately I'm evaluating https://ampcode.com/ which is very polished, but I feel like the diff-reading part is not very prominent there which I find a bit odd. After watching many of their videos I feel like that's because they are opinionated on this not being necessary any more as the models are good enough. I kind of agree, but still like to give it a last glance before committing.
I used to have two Mistral subscriptions, because I needed the extra capacity, but quickly realised I'd need three or more, so switched to the two providers above.
2. Providers covered in the first point. Regarding models I use a combination of GLM5.3, GLM5.3 Flash and Deepseek 4.1 Flash 1017. Which model I use depends on the task. GLM5.3 Flash for general chat and co-ordination tasks. Deepseek 1017 for most coding related work and GML5.3 for adversarial batteries and documentation.
3. Maki[3], although quite customised with various plugins. No python permitted, only Janet for scripting. Extremely limited bash calls, instead preferring to use the built in harness tooling, or plugin tooling I've written. AGENTS and skills used extensively. Mechanical gates also used to prevent certain actions, like remote git pushes without explicit prior approval.
I switched to Maki for the token saving strategies and stayed for the ergonomics, which I think I like, but maybe just feel comfortable with now.
4. None listed. The closest I come is a multipane Zellij setup with different agents running in different panes. Orchestration is still human in the loop though.
5. None
[1] https://melious.ai
[2] https://entrim.ai
[3] https://maki.sh/
I'm sticking with Default CLI/Desktop apps + built my own to combine them for my specific workflows. Used previously OpenClaw and Hermes but it seems to fall apart when you give it any real work. Ending up giving up because I just don't have to tinker / fine-tune it.
I will say, I enjoy Muse a lot for some reason for personal things. I don't overshare anything I wouldn't mind saying in public.
Within the last month, I basically use Claude Design exclusively for front end work and Codex for backend work. Codex just works but sucks as design. Claude is great at design (with enough references) but can't seem to actually get anything to completion.
I've had the same experience as you with Claude, and I have to choose a single subscription, so I'm on Codex. I definitely wish I had access to Opus 5.5 right now.
I wanted to really keep Claude but ChatGPT voice mode is too good tbh and no other comes close. I wish I could use Opus 5.5 for coding.
2) OpenRouter PAYG, mostly for experimenting with Chinese models like Deepseek and GLM, usually for stuff that Codex or Grok refuses to do.
Had been looking into NEAR and Venice for completely private information processing (like emails) but haven't set them up yet.
3) Codex, and OpenCode as harnesses basically.
4) I really wish I could decide on some agent orchestrator without trying them out for weeks. I like my tools highly powerful and trying to find recommendation for this online is hopeless because it's full of opinion from people who never used a terminal before.
5) Grok Bot for running experiments with supplements, calory tracking etc.. Tried to set up Hermes a couple of times but hated it every time. Just gave Rakazo a try yesterday and still hating it.
Gosh, I dream about the time when you could look at a github repo and make a decent guess about the quality of the software.
Focus is pi + self hosted GLM Flash.
Pi is lightweight and easily extensible and creates minimal extra noise. the output I get is very close to what I want to see.
my workflow is focused on clear turns between planning, testing and implementation. Any useful/recurring tasks, like getting/filtering logs, checking statuses etc get regularly folded into a project cli and agent skills that are local to the project.
I spend time interactively iterating on the plan/design and acceptance tests, then let it do its thing. Usually I have multiple interactive sessions at once that I'm steering this way. 1-2 assigned projects, 1-3 side projects (additional automation, experiments/POCs, workflow/process efficiency etc.). I generally don't do sub-agents. When I need throughput I automate first, frontloading the "deterministic" parts.
Obviously not feasible for (just) personal use, the model is too large for consumer hardware.
For the actual agents I use Claude Code for my Claude subscription, Codex for my OpenAI subscription (I usually only keep one of those at a time), and pi for my OpenCode Go subscription.
I mostly use Sonnet 5.5 medium and Sol 6.1 medium for everything. But lately I have been using DeepSeek 4.1 Flash a lot and find it very capable.
At work I use T3 Code as well, but it isn't connected to my personal machines or subscriptions and use Github Copilot in T3 Code via ACP. Model choice is similar, but for more involved tasks for architecture analysis or design, big features that touch a lot of interconnected subsystems, etc. I'll turn up reasoning effort to high or use Opus 5.5 on medium or high. But when actually implementing, I try to break up my tasks into smaller pieces and the models usually do well even without reasoning turned up.
Most of my work goes into rewriting prose in reports, commit messages, PR summaries, etc. because all models still struggle with that. (Claude models less than GPT ones in my experience, but still ...)
It is probably weakest at customizability and making sure you have parity in all your agent harnesses with skills/etc, granted I just set an agent to ensure that so the point is a bit moot.
Overall I have really been enjoying the inbox style workflow and it has been a joy to work with. It jives with how I like to work across streams.
Theo of T3 Code has made a recent video about its features.
A few examples of why I like it:
- Not having to use multiple agents (you can switch them mid-conversation with automatic handoff if you want)
- The way it handles environments (I can start a new session on any environment (machine) with two clicks (new thread -> pick project on any environment)
- I can ask for visual responses (uses a T3 Code tool and renders a html page inside chat with cards, charts, etc. that follow the currently selected color theme (even if you change the theme after the response has been generated)
- MCP tools like browser, webfetch, etc. so I don't have to set them up for every agent
- Thread handling: Snooze, Settle, Archive, Delete. It's the only tool where I don't get overwhelmed when working on multiple Threads/Projects at the same time (I am diagnosed with ADHD).
- Provider usage overview for all registered providers, showing pacing as well
- Great citation: when you make a selection in chat, a pill appears and you can create quotation elements that get added to that, can easily be edited or removed (the original reason why I even tried T3 Code in the first place, because it makes responding to long responses incredibly joyful instead of disorienting). I like it so much that I added the same mechanism to my own personal assistant/agent that I host on my VPS.
- Great diffing view where you can pick worktree diffs, or any diff from a specific turn in the current thread
- Has it's own subagent orchestration that's very pleasant to use
- Many more little things that remove a lot of friction and just feel right for me.
It's just baffling to me how it is better in every regard than every other harness that I've ever tried (Claude Desktop, Github Copilot App, OpenCode Desktop, all the CLIs, Integrated Agents in VSCode and Zed, etc.)
I will still start up a pi on the cli if I just have a quick question because T3 Code needs a bit to start up and connect to all providers/environments. This is my only point of friction: It's a bit heavy on resources (because it does a lot, not because it's slow. I just happen to use it on very old hardware and on one device that is very slowed down due to heavy-handed security scanning). But other than that, I can't imagine using anything else right now.
I don't know if I've ever been this exciting about a piece of software. I was very sceptical at first, but quickly fell in love with it.
Then I used Claude to build an app called "Superintendent" that controls T3 Code through its API in a way that maximizes what I get out of my subscriptions.
One thing it does is, if I've got extra capacity building up for some reason (i.e. getting to the end of the week without using my limit), it will take a look at the projects I've pointed it to and ask Opus 5.5. to look at the projects and suggest improvements. Then, if there's capacity, it will build them on a separate worktree and be there for me to review or decline.
I've got some other features like a dashboard that shows the limits and logs its activities and a way to ask it to "refine" random ideas I give it, then I can Approve/Deny them and they'll get queued to get built with whatever capacity I have left over. It pauses gracefully when I use T3 code actively, too.