Ask HN: What's your current AI agentic setup?

Deepseek/Deepseek Harness with about 30 plugins and a lot of customization. I tried IDE integrations with Jetbrains for a few months and hated it. Now I enjoy juggling 3-4 projects at once. Costs maybe $20/week. A lot of jobs you can work at for a long time with little cost because there's a 99% cache hit rate.

Sometimes I despatch it on open-ended tasks that I'd never take on otherwise; for example I have a little fleet of 10 agents digging up medieval Japanese Buddhist parables, translating them from scratch, and feeding them into a custom interface optimized for language study.

Most of the time I give it a moderately detailed description of the scope and key/unique features I want in a new project, and it banks on work from previous projects to know what sort of deliverables I want, track and review its own mistakes etc., then I steer it from a rough prototype into something more polished. I find it equally useful for coding/application development and research/synthesis tasks.

In the process of moving from claude code (opus 5.5 sub) to opencode with a custom sandbox system and using openrouter locked to certain models and providers with US data region requirements. Claude code is/was great. Just need to move due to industry regulations.

1) Ollama, Pro, Single account. Will not trust my serious work to Big Tech.

2) Tried some local models. Need bigger GPU for that though. On Ollama, I'm super happy with (cloud-hosted) DeepSeek 4.1 Flash and GLM 4.3 Flash , which almost don't burn any tokens at all(!), until I can buy a better GPU.

3) OpenCode, running in the official Ollama Docker image.

4) Exploring https://epiq.sh which is a local TUI issue board optimized for agents

5) Nope.

1. Claude (max) + Opencode Zen. 2. Tried some other models via OpenRouter but the pricing just doesn't justify usage sometimes. 3. Claude + OpenCode harness. Using Paseo sometimes to coordinate parallel tasks although I quickly run out of memory or grind to a halt doing this. Mentally I can't coordinate more than 3 or so coding tasks at once, and physically my Macbook pro suffers when going more than this. Convenient. 4. Forget swarms, I can't even handle 4 parallel tasks. 5. Tried, and these seem deeply overcomplicated, very AI-built, and ultimately not useful.

$DAY_JOB gives me GitHub Copilot with generous limits so I use GitHub Copilot CLI. We're a Microsoft shop so that dictates some choices too.

My workflow is a windows terminal app with multiple sessions running under wsl2 in each pane since LLMs seem to do better with bash than PowerShell. I don't trust these things much so I've got a careful list of read only tool calls and filesystem sandboxing set up so it can do some useful stuff like read my task board and publish draft PRs without a ton of overbearing permissions prompts.

I usually chat with that for a bit on a task until it's plan sounds good then I have it spin up a Docker Sandbox microvm under Windows so it can safely run yolo mode and make all it's changes. When it's ready I carefully review and iterate on the result until it's ready to publish the PR.

Bit kludgy but strikes a balance of safety and multitasking I'm comfortable with. IME most folks don't think much about isolation so curious to hear if anyone else has a similarly isolated but better workflow. I'd like to try OpenShell instead of docker sbx but it lacks microvm support for windows and I don't want another layer of nested virtualization since my windows machine itself is a cloud VM.

Work also gives me access to GHCP for personal use so I use it for side projects too. Idk what I'd use if I had to pay out of pocket, probably something a cheap Claude plan. For noncoding personal use I mostly just use free tier Gemini. If this stuff ever slows down I'll invest in some GPU nodes for my homelab and run local models.

1) One 5x Claude sub, one pro lite codex sub

2) Not really, the value proposition on the subs are just so much greater.

3) I'm using Claude Code and Codex, crucially thru Muster[0] which I've been working on. It's a herdr inspired Libghostty-powered terminal which understands agents you're running, helps you manage them, supports remote devenvs, and it provides a CLI for agents to spawn, work, and message each other, no matter the harness and across machines.

4) I'm working on my own factory atm, which combines Muster and Kan[1] which is a offline, Kanban-as-plain-files-in-VCS project I'm working on and happens to work really well with agents. I recently added card dependencies to Kan and a kan ready command so I can have director agents orchestrate and hand out tasks based on what's ready and prioritized in Kan.

5) Not at this time. I played around with dots but I haven't been convinced it can do anything for me that my own solutions aren't better at.

[0] https://github.com/amterp/muster

[1] https://github.com/amterp/kan

1/ Claude and Codex, but mostly Codex with the Business Plan 2/ No other models 3/ Default CLI most of the time, plus some agent-made tooling for some orchestration 4/ No - frontier models are already super good at this 5/ I'm using Dot, and I find it helpful as a workload dispatcher

I also don't see many differences anymore in the various frontier model - between GPT 6-Sol or Astra or Fable or Opus 5.5... Maybe my tasks are easy enough, or maybe I'm missing a lot here.

Current setup is pi with github-copilot sub at work - limiting self to luna-6 model. I have custom tmux + nvim + lazygit setup that allows me to quickly toggle modals and jump in and out of code / markdown files for quick review. Im limiting myself like this to get a feel for agent limitations and develop a better sense for it. I could use better models but I've found that they just hide the limitations better and it's harder to learn.

1) 3x Claude Ultra subscriptions and $20 tiers of Codex/Cursor/Gemini, the latter three mostly for multi-provider testing and Google's bundled cloud storage. I basically only use Opus xhigh, but never touch Ultracode.

2) No. The subscriptions are too much value compared to API. If i were to start using any model on API, the first one I'd consider would probably be Inception Mercury 3, for the 1000t/s speed.

3) I use my own custom kanban agent management tool named Kotkit, which I have been developing since March. It has a built-in multi window desktop which I can use from my phone as a PWA.

4) I am currently building orchestration/swarm capabilities into my tool. Currently adding multi-agent deep research and code review workflows orchestrated by my tool, so that they are cross-provider and my agents can trigger these on demand, as well as experimenting having one agent complete an epic ticket on the kanban board by orchestrating task agents (this is all wired up so AskUserQuestion and ExitPlanMode, etc. on the task agents are answered by the main agent, and if the main agent is unsure, it delegates to me). Currently doing it on a >20-task code migration epic with a lot of success.

5) No. AI is not yet good enough at long-term planning for these to be useful for real work. You have to build step-by-step up to it. These agent platforms are good for simple personal tasks, but to use them for actual work would be skipping a lot of steps.

I build my own coding agent : Spurcode https://github.com/getspur/SpurCode which enable to support me to orchestrate difference other coding agent : like Codex + claude/Goose ...etc

Also : give out product agent notebook workbench : https://getspur.dev/spurlab to make all coding agent need to explore/grouding before coding with notebook

I'm currently using https://www.conductor.build/ for working on multiple projects at the same time with git worktrees and my Claude subscription. The annoying part is that if I have a frontend repository and a backend repository I have to tell each session "talk to this workspace to adapt the backend" if I'm working on the frontend. I wish they had better support for multiple repos in one session.

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.

1) Subscriptions - None Using OpenCode BigPickle 2) Models - OpenCode BigPickle and deepseek v1 3) Harness - OpenCode as primary , but started liking Pi recently because of all the customizations 4) None 5) Played around with OpenClaw for a really long time , now been exploring the Hermes Agent

Personally: I have a XTX7900 card which can run some decent models, eg, Qwen 27B and Gemma. For bigger stuff I have the Ollama Cloud subscription to access (mostly) GLM. I have a server with OpenWebUI, and for harnesses I use OpenCode, but I have been experimenting with pi.dev to create a workflow that takes the ideas from the Rational Unified Process (RUP) so that everything gets properly documented and reviewed by a human before getting to the implementation phase.

At work: Claude Code subscription, mostly with Opus.

I use a tool I made that lets me orchestrate lots of AI agents (claude/codex/gemini) both on my laptop and on a k8s cluster. I set them up to run on various triggers and access them from my phone/laptop: https://github.com/jonwiggins/optio

1) What AI subscriptions are you personally paying for? (Claude, ChatGPT/Codex, Cursor, etc)

> Claude

- Which tiers?

> Claude Ultra (as it's now called)

- Have you purchased multiple subscriptions from the same provider (eg two Claude accounts)?

> No. Only a paid ChatGPT (Pro I think) subscription I barely use.

2) Are you using models outside (or instead) of those subscriptions? For example, pay-as-you-go APIs, OpenRouter, or locally hosted models.

Yes. Primarily OpenAI models for some projects with "AI" integration(s).

- Which models and providers?

> OpenAI. Depends.

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?

Straight up Claude Code.

Lots of my own Skills, Commands and my own MCP servers.

- What made you switch harnesses (if you switched)?

> Tried Codex initially. Then Claude. Never looked back.

4) Are you using any agent orchestration or swarm tools?

> No.

- For example, Munder Difflin, Gas Town, Ruflo, or something custom.

> I'm building my own specialized "bots" and "agents".

5) Are you using broader agent platforms like OpenClaw / Hermes Agent / Grok bot / Dots / Muse?

> No. Not interested.

For local inference, DS4.1F 1017 quantized to 2.25 bpw from oh-my-pi; this is slow (~500 tps prefill, 30 tps decode) because it's a Radeon R9700 on PCIe4. When I don't need local inference, Opus 5.5 reviewed by GPT-6.1 Sol in VS Code, both $20/month. Mostly I use them to build small analysis tools because I am not really an individual contributor any more. I used to hit both my session and week quotas frequently, but that is much less common since Opus 5.5.

1. - OpenAI $200 - Claude Max 20x (Granted via Claude for Open Source) 2. - Various Qwen via Local 128GB Strix Halo - Some HuggingFace API use when I need a specific model for something 3. Pi, Pi-web, Custom built 4. No 5. No

1. Paying for Open Router only.

2. Local VPS: serve small models like Desert Ant, Laya, etc only (the VPS has GPU).

3. Hermes only: Stick with one, arch is converging.

4. No. Used to use Hedr but that's about it. I ask Hermes to do that for me. (or create custom Hermes agents by specifying graph in text)

5. Just Hermes: refer to #3. - Fun at home, build, automate, disabled gateways for online chatting becauese of bugs (not sharing)

Hermes, OpenRouter, . No Claude/Codex sub too expensive. Use them at work instead.

I feel like I'm just scratching the the surface with AI coding but am already incredibly productive. My setup is purely Claude Code Max (£90/month) within PHPStorm's terminal view. I have /rc permanently enabled too so I can interact from my phone.

The only "issue" I have is (due my local stack choice) is I can only have one project running at once, but I feel like I will find a solution to this soon enough.

At work:

Opus 5.5, fast mode, xhigh/max reasoning, ultracode as needed. Usually 5-8 agents going at any given moment. In-house frameworks for Claw-like workflows and agent orchestration.

At home:

Cry

I am using mainly claude code on a Pro subscription.

I also have an OpenCode Go subscription, so I can keep an eye on the capabilities of the Chinese models.

Opus 5.5 medium for the vast majority of coding and code review tasks. I will sometimes save on tokens by dropping to sonnet if I have a well detailed plan built with opus.

I spend a lot of time on the design/architecture of features. These tasks are assisted by Gen AI but I still need to make a lot of corrections. It's my main bottleneck.

For orchestration and sandboxing I've used plain VMs (I have a make VM script which installs Claude in a fresh VM).

I've used Scion at work, which gave me a lot of ideas and got me excited about building a better orchestration, messaging, sandboxing and web UI thingy which I am currently working on (GitHub link in my profile).

My biggest pain point I wanted to address with my tooling is cleanly separating projects and accesses. I do a lot of web dev and sys admin stuff. I'm building Egzo so I can safely grant and monitor access to remote systems and cloud services and keep myself organized.

$200/ea plans on Claude and Codex, plus OpenCode Zen for experimenting with other models, plus Qwen3.8-28b locally. (I test-drove DS4 Flash locally in a 128GiB MBP for a while, but the tokens per second were too slow to be useful for more than being a toy.) At my prior anchor client I had an additional max20 plan; at my current anchor client they have a teams plan.

I use both Openrouter and OpenCode to get Kimi, GLM, big Qwen, etc, but not at great scale. I have a security product that consumes API tokens that I built against Opus 4 when that was the strongest available; when I get around to it I’ll likely shift it to prefer GLM or Kimi, slightly for cost but mostly for non-refusal.

I spend a lot of time in Claude Code because it’s the only Anthropic subscription-friendly harness. Additionally use OpenCode and codex. Not much time spent in pi these days. I used Aider before Claude Code’s beta. Claude Code’s plugin framework is pretty decent, so I tend to stand up a repo of custom plugins against every client repo I work with. It’s a nice efficiency layer for me up front and often grows into a bonus client deliverable after a couple months of refinement.

OpenClaw runs persistently, mostly for little calendar tasks and trying to mitigate my ADHD: energy level check-ins, redirects to use attention for things that matter. It orchestrates Hermes under the hood but I don’t interact with the latter directly.

I still mostly just use tmux directly and tell running sessions about each other, sending messages to each other via text files or send-keys/capture-pane. Herdr is installed but mostly unused. The GUI clients aren’t my thing; I’m a born console junkie.

What I really want to change next is pulling this all back into emacs.

1. Claude code, ultra plan, chatgpt go plan (India has a ~3$ plan) 2. Use pay as you yo openrouter with kimi2.6 for an api wrapper interface I have to work with my business APIs, connected to whatsapp. 3. I use opencode alot at my office that connects to a bunch of mixed models gpt-luna, claude. But prefer claude code, because (dunno if others feel it) opencode feels clunkier, and slow. I suspect that's because of the llm routing through my companies infra. 4. Have not made anything work, have tried GasTown, its horrible imo. Also, I think I am not able to trust the setup, and worry about token wastage (which cheaper models do more off when left unsupervised) 5. Open law - connecting with my personal calender, gmail, whatsapp, side gig infra - first responder for my business whatsapp for a slice of whitelisted interactions.

1) Claude Ultra (aka Max 20x)

2) No

3) Claude Code

4) Custom WIP https://muster.town/

5) Custom personal agent setup https://github.com/mitchellgordon95/miniclaw

Usage is mainly wiki building around personal info (finances, topics of interest), calorie counting, and doing various things from my dumb phone (rideshare booking, checking MTA Bus schedules, etc.)

A key part of mine is using voice input to give max context quickly to my agents. I know some solutions exist, but on Linux they all frankly suck

So I made my own. Including patching onnx myself to run parakeet model (way better than whisper)

Fully FOSS: voiceio.dev

I do not like terminal tui much as I think it's a poor fit for a coding agent.

But I do use claude code tui because I have a sub: it is a good model and I like its aesthetics. If I could use the sub in my own harness I would. It's also a foil to GPT's models that overengineer everything.

I have a Codex subscription that I use in my own harness, dreamcoder.ai, which has a tiling window manager and all the other mod cons you'd expect a frontier harness to have.

In addition to that, I run Qwen 3.8 27B NVFP4 with ninfer on my 5090. It's a great model for local development. I also use that in dreamcoder.

1) i use my brother's claude pro subscription. if i needed to, i would use openrouter + API if i didn't have his subscription, but i don't think i really need it. i've never purchased an ai subscription myself, nor paid my brother for his. i would never use frontier us models for anything serious on openrouter + API

2) yes, when claude starts getting too preachy and the task at hand is important to me i use openrouter + api + chinese models. my computer can't even run qwen 3.8 27b.

3) i use claude code because i think using other ones isn't allowed. i don't really like it, and generally prefer opencode (i've had to use it to do some things for my brother). i'll try using other ones though

4) no, and i didn't actually know they existed. opencode and claude code's agentic things are enough for me, though i don't do actually complex projects

5) no, i won't use them unless i get good local inference going (i.e. never).

Rolled my own for a Claude Max sub, basically tmux and an elaborate MCP for persistent semantic memory, Forgejo, etc. (https://github.com/ASIXicle/Coterie)

I sense more people will do so as you can fairly easily tailor any harness and MCP/LXC combo to suit the way you work. It's a bespoke future.

None. It prevents brain athrophy.

These comments read like people just bragging about having multiple AI subscriptions but not actually giving any info about what they're using them for

1) Codex $200 * 2, Claude Code $200, Muse Code $50, OpenCode $40. I run them in 6 machines (2 Linux, 2 MacOS, 2 Windows)

2) No. I try my best to use oauth

3) Claude Code + Custom Harness(set of skills) + Mod. This orchestrator (I call her as "Team Leader") orchestrates other machines with Tailscale. - I've used Claude Code (Opus 5.5) by model satisfaction and mod.

4) None

5) Dots and Instinct. Main use case is research, code search and raise issue, PR reviews.

1. Claude Ultra (200) and ChatGPT at 20

2. Experimenting with qwen3-coder-next 80B and a few other local models for coding tasks on my M4 MBP (128GB RAM) - no other models or pay-as-you-go apis

3. I have a custom built setup primarily driven by claude code via telegram with a checked in "brain", a separate "watch" structure of crons that i can setup and tweak, and then a task farm run by that orchestrator with containerized cc (and a mixture of sonnet and local llms based on task) and application devcontainer stacks (if it's coding related)

4. Custom

5. Custom - mainly rebuilding the ideas from there into my own workflows, but not using any of them directly

Trying to split more things out of CC and use it as a pure harness on route to trying other harnesses out like pi, etc -- it's a work in progress as and when I have the bandwidth.

I built railvio.com for myself initially, it’s taken me a year to build and it’s a full harness for building applications + fully integrated Jira and Confluence clone. That altogether has become a lovable clone which I’ve used now to deploy a tradingview clone, a risk rating rules engine clone, and an agent terminal that is a stripped down clone of Iterm2 but built with a middle layer so I can connect to long lived tmux sessions. 3x Claude ultra, codex pro, + local Qwen 27b fp8 on Radiance engine on 2xRS700 and ComfyUi on a separate machine with a rtx 4090. It’s been super fun building everything. I’ve averaged around ~40B tokens per month..

1) Claude Ultra 2x + Chatgpt Plus 2x 2) none 3) defaults 4) T3 code -> really great for multi-machine orchestration + multi-harness work 5) Made a OpenBot fork mainly as "captains" to control my t3 threads across projects better

I've been increasingly interested in language-oriented programming and denotational design. So i get claude to create a domain specific language in Racket modelling the software i'm trying to build, we create nouns and verbs whose meaning fits the behaviour i'm going for, then when we find bugs or notice we need more exceptional (less-elegant) one-off behaviour to tackle edge-cases, we iterate on the language in such a manner that it these are tackled emergently with preferably less concepts, more cohersion and composition. It's somewhat similar to how memory safety is handled at compile time in Rust but for business logic.

1. claude pro, ollama pro and opencode go 2. Openrouter for testing 3. I use VScode and claude code 4. I've actually built my own for agentic workflows - https://vectorstep.io 5. I use openclaw for my personal stuff, VectorStep for proper trusted workflows (and production workflows)

I’ve build myself a framework how a group of agents can verify if it’s done a good enough job.

After around 30 days I’ve implemented around 90% of how you manage a team in emergency medicine by accident and then applied the rest of it to it.

I’m quite happy with what they produce.

I'm hoping to read people's experiences with cmux. My son showed me a demo, and I was pretty blown away. I haven't had time to look into it much myself.

Currently I am using the regular Claude extension with VS Code, but one of my friends is working on a new harness called NodeCode that doesn't require regular compaction, so I'll be trying it out as soon as I can get some time to do it: https://nodecode.ai/

For building, I started with Kiro and later switched to Antigravity (Opus 5.5 for planning, Gemini 3.8 for implementation - but now using Argon for everything and quite happy). Claude for design.

Had a Hermes set up with a dual NVIDIA DGX Spark and Deepseek v4 Flash, but then built my own harness (getcinnamon.ai) and pretty much switched to that 100% including family members.

1 - Opencode Go $40, Claude $20, $0-100 on Deepseek API

2 - No

3 - I use a lot of Opencode + Deepseek, strategize some of that work with Claude Opus, and some gtm, research, and project stuff in Hermes with its coding agent. When I guide by hand I use Orca Dev, which is lovely.

4 - Claude drops GitHub issues that Opencode picks up on a schedule. It’s simple and resilient enough for me. Hermes has a lot of scheduled tasks to move things forward.. it has gtm and research and dev loops (the latter builds autonomously for future projects vis a vis my attention, I’ve used quite a bit of it).

5 - Hermes Agent, which has become a core tech for me. I’ve tried to use Openclaw but it has not been something I can keep running. It spirals and crashes after a week in ways I’ve never experienced from Hermes, doing the same things. I have little interest in those generalist agents, maybe after a year.

1. Personal Claude Max $100 tier; Work Claude Team, and ChatGPT Team. I use almost exclusively Claude Opus 5.5 Medium for everything. ChatGPT seems to miss a lot that Claude doesn’t; I’ll occasionally ask it to do an adversarial review where it finds something, but that’s about it.

2. No.

3. Claude CLI and Codex, but I rarely use the latter, and just call its review function from within Claude. If Anthropic didn’t require API usage for external tooling, I’d be interested in trying a lighter harness, but it’s not that big of a deal for me.

4. No.

5. No.

I'm currently on Raven as a sort of "meta harness". The main chat is with the orchestrator, which delegates all work to other harnesses. I just use different seat-based plans. Mostly the latest Sol with my corp chatgpt account.

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.

1. Claude and Codex 2. Openrouter for deepseek and Helmcode 3. All of them, mostly claude, codex and pi 4. We use agent-swarm.dev (self-hosted OSS MIT) 5. See 4 :D

1. Claude $20/month and Cursor $20/month (I've been meaning to close it) I mostly use Opus 5.5 on Medium. I've been experimenting with High effort, mainly at work.

2. I have an OpenRouter $50 pay as you go API key that I use for Mercury 3 at this point, primarily for tokens per second. I also use GLM 5.3 when I inevitably get [cyber] blocked (or for reverse engineering in general, apparently) by the morality police at Anthropic.

3. I run things pretty stock. OpenCode with OpenRouter but otherwise I just use Claude code.

4. I've never used these, but I'm curious about them at this point.

5. Not yet, but also interested. My plan is to use Hermes for some personal agent work on a local model, but I have not set it up to test this yet.

I'm yet to find any value in complex software factories and multi agent harnesses. If you know what you're doing, you can just use Codex or Claude for the core research and development.

I use both Claude Code and Codex with a bunch of project-specific skills and AGENTS.md files. Worktrees have been really useful when running multiple sessions on the same repo, otherwise they can step on each others changes.

Still figuring out how much should go in AGENTS.md though. Mine keeps growing lol.

I built my experimental system and I'm using it. I'm genuinely very happy with it. If I had more compute and could run a real, full 30B model locally, I'd be absolutely thrilled.

https://github.com/8lamaster8/GIN

I use Muse Code $5 month

It has a 5 hour usage limit, and if using the wonder model, you basically only get 1 or 2 prompts. However, I find it will basically do unlimited 'turns', so as long as I give a good prompt, I can get my work done.

No ide/harness. I only do light coding and don't have time to actually sit at my computer.