alt Hacker NewsAsk HN: What's your current AI agentic setup?
I'm curious how people on HN are using AI day to day, and came up with a list of questions I thought could be interesting to know. No need to answer every question of course, just wanted to get a gut feel how people are using AI.
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 harnesses (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.
Comments
I use Codex and Claude Code with piles of project-specific skills and AGENTS.md files.
For my main work at my startup, we're very careful with how these are setup.
Everywhere else, I simmer in chaos.
I also have strong boundaries around generated prose. I don't like making other people read AI slop, but I don't mind having AIs read it.
ChatGPT Pro 200 x2
No
Codex
Codex
Dots
Gemini Pro with web chat interface. I upload files, ask for changes, copy & paste the files back, and test and vet the code changes.
No other models or software.
Locally (MBP 128Gb) I have MLX-Serve constantly running with Clef (for model routing and decisions), Qwen-35B-A3B and Ornith-1.5-35B.
And I switch to Qwen3.8-27B (the Perplexity Pro version that works well with MLX-Serve) or GLM-5.3-Flash (sushi) when I need to do serious work offline.
As a general harness for coding, etc. I use Swival.dev . Configured to use Clef for model routing, with Qwen-35B-A3B for documentation tasks, Ornith to ask questions about code, and various GPT models from a ChatGPT subscription for more difficult tasks.
For music, pictures, etc. MLX-Serve is all I use, with the recommended models. It's really nice.
And as a general agent for research, etc. I absolutely love Perplexity. This is by far the AI produce I use the most, ever since it's been available.
It's a little bit sad that they are forcing people to use Perplexity Computer, because it's so expensive. But it works incredibly well.
Perplexity can now run locally, but even though they include the best Qwen3.8 quant in my experience, the Perplexity tool itself has major issues with context management and tool calling. So, when that doesn't work, I fall back to MLX-Serve and Swival with the Chrome MCP server.
For agentic web browsing, I can't live without Comet anymore. So many websites are painful to use, and finding the right buttons to click even to perform very common tasks is a challenge. So, I frequently just ask Comet to do it for me. I also use it to compare products, compare places on AirBNB, write personalized messages on Instagram, etc.
As for an OpenClaw-like tool, I'm using NBClaw. I was initially very excited about it. Look, I can just send messages on Signal and let the agent do work for me! And I occasionally found it useful to remotely fix issues on the host it was running on, or long tasks such as making sure that all my projects worked with a new version of the Zig compiler. It became a replacement for Perplexity because, hey, it's cool, everything's running locally, using my own web browser, etc.
But eventually, I used it less and less. Nowadays, I still enjoy the fact that it's sending me a summary of cool things it found in Hacker News and research papers on topics I'm interesting in. But that's pretty much it. I don't use it much for agentic tasks anymore. It still happens (I recently used it to fix a bug in an opensource project while I was on the bus), but mostly just only when I ran out of Perplexity Computer credits.
Personal exe.dev subscription.
1. Claude Ultra, three accounts. Mostly to get enough Fable usage.
2. Early in experiments with locally hosted GLM Next, not writing code with it beyond experiments.
3. Claude Code, system prompt, minimal skills; mostly bash scripts for common actions.
4. tmux send-keys for messaging between panes.
5. No. Claude Code does that, too.
For personal work. I use Orca.
1. Claude Code with $20 Claude subscription. This used to be a terrible value but now it's a great value, probably because of the IPO. I do a lot of coding and other things and I rarely get close to my weekly limit. I mostly use Opus 5.5 medium. Codex with gpt used to be good value but recently I canceled it cause I kept reaching my limits.
2. When I want a "different pair of eyes" to review things I'm working on with Opus, I use Pi with other model providers and just pay API prices.
3. Deepseek harness with a deepseek API key. Really great value.
4. I have a Muse $5/month subscription that I keep as a backup although I don't really need it.
I also use cloud agents to setup reoccurring jobs. For expensive agent runs, like visit 5000 websites and extract something from each, I would set up something cheap with an agents sdk and for the model use either Muse, Deepseek, or GPT-6-luna using their batch API.
I maintain all my dotfiles and agent files / context in a github repo so that I can switch easily between harnesses and providers.
$200 ChatGPT + $200 Claude, I don't pay for it, agents quant trade and pay for their own subscriptions. I then use the rest of the tokens to build stuff.
none; no; none; no; not needed; no; none; unnecessary; no thanks; and not interested. "I've seen enough, kiddos."
I've made a multiplayer environment for me and a few friends, where we can prompt (currently three) emergents and experiment with various models and instructions for them.
I've rarely been so inspired by a project.
It's publicly readable, but writable by a group of ~20.
I still just pay $100/mo for Claude. Use the CC extension in VSCode. I’m actively investigating various ways of getting a Hermes Agent going on my homelab with either a local model, Openrouter ZDR models, or both but I’m unlikely to pull the trigger on that yet. I would never use Muse, Grok Bot, etc as a personal agent.
I use OC with various subs, and am testing DeepSeek Harness, JetBrains Thinkrail, and Volt. Extending the harness with plugins is my main interest these days.
I mostly work on problems at the intersection of manufacturing, mechatronic design, electronics, software and physics. So I'm not really building software per-se which likely accounts for the probably slightly weird choices here.
1. Claude Max (upsold me as of today); generally Sonnet 5.5 with the occasional Fable 5.1 when it gets stuck or I am executing a high value step; and Perplexity Pro (legacy).
2. Mostly local voice-to-text w/Parakeet Unified EN 0.6B via Handy[0] (awesome; use it!). Not for coding, but for note taking, AI interfacing, and general typing reduction and RSI avoidance.
3. None. I tried Pi and after much kerfuffle I don't like any of the harness interfaces. I find the type of work I do they are not very useful, because I often switch between variant approaches, planning, data, and don't want unrestrained context bloat.
4. No.
5. No.
I would add that I am very interested in obtaining good enough hardware to run this level of model locally at any pace, believe Qwen is basically there but too slow locally to use as a daily driver on my current rig, and can see myself making that investment in single digit years. Not right now, the hardware is overpriced for what it is versus venture funded cloud AI subsidies.
- LLM reverse proxy
- agents work in their own lxc spawn automatically in a proxmox node, where they can go wild without sandboxing or isolation, network is firewalled too
- all sync sessions and everything to a centralized agentsview in a realtime, where I get to track and watch it from anywhere on the go
- i just ssh into the lxc if i needed anything
- different harnesses depending on the task, maki is great one, but I use others
- I also have other stuff but I won’t mention it here regarding the tokens for obvious reasons
I tried most of the tools like herdr or paseo or desktop clients but they never clicked with me
1.) Claude or ChatGPT Chatbot.
2.) Text Editor or IDE.
3.) A compiler/interpreter/SDK and potentially other dependencies.
Super lame and boring, but that's basically it.
As for my day job, it's the same minus #1 -- AI is banned.
Opencode with $10 Opencode Go plan until his heinous Clammy Sammy lets me have enough Ram for a local inference setup.
I run
2) kapitsa + pi + Qwen 3.6 35B a3B q4. pi is the harness, kapitsa is the inference engine
people that I considered intelligent have associated Qwen with "chinese cloud" when it implies not using a cloud at all. I think that's weird. I think there is a "western" centric view that limits perspective to using A cloud, instead of aspiring for locally run
1) I also pay for Claude, I should downgrade again to the $100 plan, thanks for the reminder, but currently the $200 max x5 plan
4) no. I handroll my agents
5) I use Claude desktop as an agent platform
i dont have one
1) anthropic ultra; single sub
2) payg on opencode
3) standard claude code and opencode driven by t3 code
4) nope
5) grok bot - at work, to manage my tasks, and to highlight what happened on slack when i was off; random one offs there
test
I built a "software factory" on top of pi agents so I can automate most product dev work
moved to openclaw for everything, with occasional claude usage for tricky bits. I have $200 of both codex and claude subs.
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.
here is my production grade setup for agentic ai on windows 11
- setup windows 11 with Rufus boot to disable online MS account creation https://rufus.ie/en/
- [download window 11 x64 iso from here ](https://www.microsoft.com/en-us/software-download/windows11)
- then download vmware workstation pro (you ll need to create a free account to get the download link on their website)
- install vmware workstation pro
- turn internet off
- plug your pendrive in with the rufus w11 x64 iso on it (mind ya, this pen drive ll first need full formatting before burning a w11 image to it)
- press f2 to reach bios in vmware settings and make it boot from pendrive
- turn internet off on your machine (DO NOT keep it on)
- install w11 (keep a 100gb for vmware)
- without updates it ll load real fast and you wont need an MS account (rufus takes care of it)
- while it installs, download revo uninstaller pro on a separate machine https://onefiles.net/9d170d01078634b5 (latest version 5.4.x) and put it inside a second pendrive / portable hdd
- once w11 loads, it ll ask you to enter a password, keep existing password blank and enter literally anything for a new password
- voila you are done with w11 setup inside vmware
- now connect the 2nd pendrive with revo and install it (need to clean uninstall many tools, hence we need this one)
- now go to search bar and type check for updates and update everything on w11 inside vmware
- next stop get unigetui from ms app store or from here https://devolutions.net/unigetui/ (it is a package manager responsible for installing just about everything else with auto updation of all packages)
- the open unigetui and search for the following packages vlc, winrar, winhance
- winhance is the fully customizable debloater you ll need to turn off all telemetry (we ll debloat after installing all the other requirements)
- next go to ms app store and install python or open powershell and type python
- the open unigetui and search for the following packages vlc, winrar, winhance
- winhance is the fully customizable debloater you ll need to turn off all telemetry (we ll debloat after installing all the other requirements)
- next go to ms app store and install python or open powershell and type python
- mind you this installs a python version manager that lets you install and uninstall multiple python versions
- after this python version manager is setup, install a specific version of python like
``` py install 3.13 ``` - next we need a node.js version manager, use fnm for it
https://github.com/Schniz/fnm - once installed, it may need to be added to environment variables manually
- once again choose a specific version of node.js and install it using
``` fnm install 23.12.0 ``` check fnm --help for commands - next we need a java version manager, use jvms for it
https://github.com/ystyle/jvms
- pretty self explanatory
- now install git and again it ll give you some trouble over environment variables, command not recognized etc, fixable with some gpt help
- at this point, we got git, node version manager, java version manager and python version manager and are ready to rumble
- install vscode/ visual studio whatever
- install codex
- install claude
- install opencode (both cli via npx and desktop app) and check their plans out https://opencode.ai/console/go
- install ghidra , ghidra-mcp (mind you open ghidra-mcp first because it only works with specific versions of ghidra and java) this is the reason we installed a java version manager
- check out setup for rea https://github.com/morluto/rea requires npx setup for rea and ghidra both, read documentation
- run winhance, check recommended settings under optimize and every other tab and restart the vm a few times for full debloat with 0 telemetry services
- congrats you have a full blown agentic environment at this point (if I missed anything i ll come back and update)
1.a) At work: I can choose between Cursor and Claude on a meter. Been using Cursor for a long time and happy with it until they started to force Grok down our throats. I was happy with Composer 2. Recently switched to Claude Code. The company also runs some open weight models in-house and I have been using them through Claude Code itself, with VSCodium as my Code Viewer. I almost never need anything stronger than Sonnet at work - 80% of which is YAML and Terraform these days (or rather markdown, if you really think about it).
1.b) For personal stuff I maintain an Opencode GO subscription, USD40 tier. I also have a Google One subscription which is supposed to have some AI capabilities, haven't tested it yet.
2) Besides my Opencode GO subscription, I sometimes add a few bucks to use Zen. It's rare: my USD40 is usually fine for the month. I've recently started using Nvivia NIM free tier models for some time insensitive tasks too. I have a Qwen model available on my Mac (M1 PRO 64GB) but haven't found it to be useful, as I need my laptop for everything else I'm doing beyond inference.
GLM 5.3 Flash and Deepseek 4.1 Flash do most of the work for my personal stuff. Nemotron does the time insensitive stuff, which is mostly summarizing text. I've been using GPT Luna 6 a lot because it's currently cheap as hell, so I'll often talk to GPT Luna and hand off coding to GLM or Deepseek. I find that Luna communicates MUCH better than the Chinese models - I assume because it does not go through the extra language barrier step between English and Chinese. GLM, Qwen and Deepseek are incredible tool callers, but their prose is insufferable.
3.a) At work I'm using Claude Code for the Anthropic models and Opencode for the self-hosted ones. Ditched Cursor recently. I've been meaning to try to integrate the self-hosted models into Claude Code but haven't yet, so hand-offs between the two harnesses involve a lot of markdown.
I've switched out of Cursor because A. they've been bullying us into using grok for everything and B. The company setup would not support the use case of mixing the self-hosted and closed models in the same harness - this limitation is on our side.
3.b) For my personal stuff I've been using mostly Hermes. Some actual coding goes into Opencode, often piloted by Hermes itself. I'm using Zed as my code editor, but with the AI features disabled. My opencode subscription is actually configured in Zed, but I prefer the UI without them.
4) No. I don't really need them. I run 5-6 parallel sessions at most, otherwise I can't keep track of what's being done anyway. Each parallel session is on a different task, so I generally don't need them to spit enormous amounts of code. I rarely have to wait more than a few minutes for a task to finish, and I'm always thinking or writing or managing something else in between anyway - not looking at the screen waiting.
5) Hermes. Generally happy with it - despite it being extremely unstable between updates, with frequent regressions, weird UI bugs and half assed features (bot mode, anyone?). I have 3 distinct instances (laptop, home server, VPS) doing different things - all hooked up to the same memory provider (honcho) under a single user profile, and a handful AI profiles on each. All have limited access to my Obsidian Vault, which is synced between them using Obsidian Sync.
I generally use the laptop instance for day-to-day use: planning work, assigning tasks to myself and to the other agents, capturing ideas, light coding, etc. The homeserver instance manages a limited set of features on the server itself, from upgrades, documentation and more devopsy stuff to organizing files, managing transcoding queues, etc. The cloud hosted version automates is not very used yet. I plan to have it pilot an n8n instance I keep to automate some boring stuff, like filing weekly tax records and automatically forwarding bureaucratic e-mails, nothing fancy.
herdr, opus 5.5 (max), codex (max), and I am still refining how they all communicate, currently codex became unwakable at some point while claude can be woken with a message just fine.
devin
Right now, it's Claude Code on Opus 5.5 w/ herdr to manage multiple sessions at a time.
Ok I don't understand how people can deal with the information coming from a fleet of agents burning 100s-1000s of €/$ as month.
I have a Claude Code pro subscription, and mostly have Opus as a thinking buddy, we have thoroughly designed a data model together, we have implemented it in Django. Then we designed the RBAC system and now we are making views per role.
It is so intense! Constant decisions, walls of text with pros and cons to decisions. I mean the speed is amazing, the code quality is also amazing, but the amount of information I get to process is just insane, and I enjoy it less than the flow-state writing of code. I think I'll get used to it, and the speed is motivating, but man. I can not picture keeping 10's of agents on tasks. What am I doing wrong? Should I trust the system more? Or am I just mostly working on decisions now and the 1000$ token burners are not bothered with that because they have a full backlog, where I need to fill it myself?
I deal with the overload by making abstractions (a visual of the data model/db schema with color coded relations etc, a table for RBAC, think about permissions in "Axes"... I'm always looking for smart tricks to "think better", to be able to hold more information and reason about it. What must exist in me, what can I outsource?
Btw, as a FOSS person I so hate that I am not owning my means of production anymore, I have a home battery for all my infra, very proud of what I build, but I can't run my agents :( I really hope that will change soon (for privacy and for control reasons.)
For the company I do all IT for we have a Mistral Team subscription, I find it hard to work with anything other than Claude Opus, I really force myself to do it but I often think: Pff, Opus would have gotten this right. But I remember feeling the same when I switched from Google to DDG (3000 years ago) and I never switched back. So it's probably just familiarity.
I also have HermesAgent on a nuc here in front of me, it makes small automations: Scans for positions or projects for my company, parses RSS feeds for relevant cybersecurity news, researches things when I ask, stores notes and articles with I can interrogate as a "body of work" <- love that btw, it's like an external memory where the faintest glimmer of a memory can help you dig up that one nugget of knowledge. Or you can find trends in TFAs you love. You can really get to know yourself a bit better.
VS code with claude plugin. Basic private git repos per project on github, nothing special, I keep everything simple.
1. subscription: claude max 20x
2. other subscription: nope
3. harness: vs code with claude plugin
4. orchestration: no
5. broader agents: grok for outreach.
my development setup is a high-end local esxi server (multiple internet cons and a graphics card). The server has about 30 different OSes on it (static ips / ssh setups for all vms.) I use a VM on that machine to run my IDE with full access to the other VMs. I have good snapshots for all the VMs so if anything breaks they are easily restored. This setup makes it easy to develop software for any OS and also test complex software interactions.
For hosted internet services: I use a single OVH debian machine. I pre-pay everything over a large period so the bills are always paid. That keeps it reliable as I can say that even if I go broke in the future I'll have paid it for quite a while (useful in this economy, lol.)
Session notes: I feel like the best approach is for us all to just maintain a personal wiki for our projects. But I must admit I've been lazy in that respect. All my attempts to manage my notes never works because im such a messy, chaotic person. My natural state is disorder. So I'll just (1) destroy it by accident (2) forget to back it up (3) forget to use it (4) get tired of using it. I envy those super organised people.
Backup: my services are backed up locally. My local repos are backed up to github, email, and remotely. Agents deleting anything by accident isn't something i have to worry about. They have ruined VMs before. I can easily restore them. So far I've only ever lost notes because of laziness.
Security: my security setup could be vastly improved by using discrete key pairs with restricted permissions for github. What I worry about most is just things like prompt injection and the agent accidentally downloading malware. Lateral traversal out of vms is hard but not impossible. I'd wager there's still lots of private stuff on the vms too. I monitor everything closely at least and can restore a snapshot if i get paranoid.
[flagged]
[dead]
[flagged]
[flagged]
[flagged]
[flagged]
[flagged]
[flagged]
[flagged]
[flagged]
[flagged]
[dead]
[flagged]
[flagged]
[flagged]
[flagged]
2) I am running Qwen Flash Next on Strix Halo with Halogen inference server. This is great setup that can get you 4 concurrent agents for 300W of power with 1k prefill and 30-80tk/s decode. I do not fill like using subs that I have from work with this.