AI coding agent setups from a 663-comment Ask HN: tool counts and 7 patterns to copy An Ask HN thread posted November 4, 2026 by user eggbrain asking developers for their current AI agent setup drew 663 comments from 530 people, and an analysis counted on November 6, 2026 found that 424 of those commenters named at least one AI tool, with Anthropic's Claude Code leading at 180 users and OpenAI's Codex second at 103. The count also found 120 of the 424 named both a Claude product and an OpenAI product, 156 use two or more coding agents, and 148 named an open-weight or local model such as DeepSeek, Qwen, GLM or Kimi, including 58 who named no Claude or OpenAI tool at all. The most detailed setups shared habits including running several agents at once in separate git worktrees, assigning a fresh second reviewer to every change, and sandboxing any agent allowed to run without asking. AI coding agent setups from a 663-comment Ask HN: tool counts and 7 patterns to copy On November 4, 2026, an Ask HN thread asked developers for their current AI agent setup, and 663 comments came back. We read every one, counted the tools 424 people say they use, and turned the most detailed setups into seven patterns you can start using today. This explains reporting by Ask HN: What's your current AI agentic setup? Hacker News, November 4, 2026 https://news.ycombinator.com/item?id=50366117 . Read the original first: https://news.ycombinator.com/item?id=50366117 https://news.ycombinator.com/item?id=50366117 In one minute - 424 of the 530 people who commented named at least one AI tool they use. Claude Code leads with 180 people, then Codex with 103. We counted on November 6, 2026. - Most people mix vendors. 120 of the 424 named both a Claude product and an OpenAI product, and 156 use two or more coding agents. - Open-weight models do real work here. 148 people named DeepSeek, Qwen, GLM, Kimi or another open-weight or local model, and 58 of them named no Claude or OpenAI tool at all. - The most detailed setups share a few habits: several agents at once, each in its own git worktree; a fresh second reviewer on every change; and a VM or container around any agent allowed to run without asking. - Even heavy users say the basics matter most: write down what done looks like, and review the work before it ships. What the thread asked and who answered On November 4, 2026, the user eggbrain posted "Ask HN: What's your current AI agentic setup?" It asked five questions: which AI plans people pay for, which other models they use, which coding harness the program that runs the agent they use, whether they use tools that run many agents at once, and whether they use always-on agent platforms. We fetched the thread on November 6, 2026, at about 9:00 AM MST. It had 534 points and 663 comments from 530 different people. 392 comments were direct answers to the post. The rest were replies. Three readers each read every comment. For each one they wrote down the tools the person says they use, the tools they only mention, and any signs of an advanced setup, such as parallel agents or a review loop. We then counted people, not comments, so a person who posted five times counts once per tool. All the links for tools and comments named on this page are in the Sources list at the bottom. The tools, by how many people use them These are people who say they use each tool, out of the 424 commenters who named at least one. One person can use many tools, so the numbers add up to more than 424. When someone said Claude while talking about coding, the readers counted it as Claude Code. Counted November 6, 2026. Tool what it is People Claude Code Anthropic coding agent 180 Claude plan Pro, Max or Team 145 Codex OpenAI coding agent 103 ChatGPT plan or app 92 Claude Opus model 80 DeepSeek open-weight models 78 OpenCode open-source coding agent 69 Pi open-source coding agent 67 OpenRouter one API for many models 55 Qwen open-weight models 46 GLM from Z.ai open-weight models 44 Gemini Google models and app 36 Hermes Agent personal agent 29 Herdr runs many agent sessions 28 GPT models through the API 26 VS Code editor 26 GitHub Copilot 22 Claude Sonnet model 19 Grok models and app 17 tmux terminal multiplexer 17 Antigravity Google agent IDE 17 - Claude Code is the most used agent by a wide margin, but most of its users run something else too. Only 73 of its 180 users named no other coding agent, and 67 people use both Claude Code and Codex. - Open-source agents are not far behind. OpenCode 69 people and Pi 67 each have close to twice the users of Gemini 36 and three to four times those of GitHub Copilot 22 or Cursor 16 . - Cheap open-weight models carry real load. DeepSeek 78 people is named almost as often as Claude Opus 80 , and two of the setups below use it as their main builder model. - Running many agents needs a tool to watch them. Herdr 28 people and tmux 17 are the most common ways people here keep track of which session needs them. Nine setups worth studying We picked these because each one shows a pattern clearly and gives enough detail to copy. We re-read each full comment. The setups are as the commenters describe them; we did not test them. - paustint: parallel agents in long-lived worktrees. They keep numbered worktrees open all the time and run up to eight Claude Code agents on different tasks inside Herdr, which flags the pane that is done or needs them. lazygit handles git. Long jobs go to remote machines over SSH so the laptop can close. A Claude skill reads GitHub Copilot's PR review comments, checks each one, replies and pushes fixes. Why it counts: the whole loop from ticket to reviewed PR, run in parallel. - skwee357: every project in its own VM. Each project runs in a Lima microVM with Claude Code's skip-permissions mode on, 5 to 7 worktrees run side by side in Herdr, and a secrets tool keeps API keys out of the agent's reach. Package installs happen in the VM, never on the laptop. If a VM goes bad, "I just wipe it off, and restart from scratch." Why it counts: full speed with no permission prompts, and a small blast radius. - thefunnyman: plan outside, build inside a box. They use GitHub Copilot CLI under WSL2 with a short list of allowed read-only tools, chat until the plan is right, then have the agent start a Docker Sandbox microVM where it can run without asking. They review the result before any PR goes out. Why it counts: a clean split between a safe place to plan and a sealed place to build. - KronisLV: fresh reviewers until nothing serious is left. They pay for one Claude plan and one OpenAI plan, tried many add-on tools, and dropped most of them. The main session hands work to subagents, then starts new subagents with a clean context to review it, and repeats until no serious issues remain. Their view: "all you need are Git worktrees and a decent OS environment." Why it counts: the simplest review loop that still catches real bugs. - gregwebs: three models, three jobs, under $100 a month. Claude $20 plan plans, Codex $20 plan reviews, and DeepSeek $1 to $3 a day builds and coordinates, all from one /implement skill in the Pi agent. A plugin switches providers when quota runs low, Herdr organizes sessions, and a mobile app reaches them over Tailscale. They say it is about 3 times slower than a single ask, but "defects cost time and money later." Why it counts: model routing plus a second-model review on a small budget. - glennfiedler: tiers that move up on failure. A coordinator, usually Claude Opus, sorts each task card into one of four tiers, from fast cheap models up to the strongest, and moves a card up a tier when it fails. Every card gets several model reviewers. In another comment they describe running about 200 cards at once across 20 machines linked by Tailscale. Still, they say "for 99% of stuff I need to do Opus 5.5 @ medium is ideal." Why it counts: the clearest rule we saw for when to pay for a bigger model. - enesalatas: long-running agents you talk to from chat. Named Claude Code loops wake on a timer or a message, each in its own container with an egress allowlist the only sites it may reach , and they talk to them from Telegram or Slack. Codex reviews each PR through a Claude Code hook. A web page shows what each loop is doing and what it costs. Why it counts: unattended agents with network limits and a built-in second reviewer. - sudhirj: phone first, issues to PRs. They run Claude Code Remote Control in every project and work from the Claude app on phone and iPad, and use mosh from Blink Shell on the iPad for a plain terminal on a home server. For bigger projects, a service they maintain reads GitHub issues, starts a one-shot Claude run, and handles CI, commits and the PR. Why it counts: work keeps moving away from the desk, and routine issues need no one to start them. - cpobuda: the spec comes first. They write the design and spec by hand, and "we don't start coding until the specification is unambiguous." An AGENTS.md protocol then runs phases for design, tests, building, security and QA. Each phase has a builder and a fresh reviewer who must check claims instead of trusting reports, and each phase ends in pass or fail, never a score. It runs on OpenCode with DeepSeek and a small local model. Why it counts: most bugs get caught before any code exists. Pattern 1: Run several agents at once, one git worktree each What it is: each task gets its own folder and branch, made with git worktree, and its own agent session. Agents cannot overwrite each other's files, and you merge each branch when it is ready. Why it helps: an agent often works for minutes at a time, so one agent means a lot of waiting. Our readers tagged 105 people as running agents in parallel. The top comment in the thread, from thefourthchime, says to keep at least five things going so you are not sitting around for one agent. one folder and branch per task git worktree add ../myapp-login -b fix-login git worktree add ../myapp-search -b add-search or let Claude Code make the worktree and start a session in it claude --worktree fix-login Tools: git worktree, Claude Code's --worktree option, and a session manager that shows which agent needs you, such as Herdr 28 people , tmux 17 , Zellij, Orca, Paseo or T3 Code. paustint and skwee357 run this every day. Watch out: glennfiedler warns that code written by many models working alone can come out as a patchwork that needs a cleanup pass. Start with two or three agents and add more when review keeps up. Pattern 2: Have a fresh reviewer check every change What it is: when the builder finishes, a second agent with no memory of the build reads the diff and lists real problems. It can be a new subagent of the same model or a model from another vendor. Fix, then review again. Why it helps: the agent that wrote the code tends to trust its own work. Our readers tagged 56 people with a review loop. KronisLV loops until nothing serious remains, gregwebs gives the reviewer job to Codex, and glennfiedler says each model sees things the others miss. a read-only second opinion from a different model codex exec runs in a read-only sandbox by default codex exec "Review the changes on this branch against main. List real bugs and missing tests only." inside Claude Code, ask for a reviewer with a clean context Start a new subagent with no context from this session. Have it review the diff against main and report only serious problems. Fix them, then review again. Tools: Codex non-interactive mode codex exec , Claude Code subagents, GitHub Copilot code review on PRs, and Herdr, which lets one agent start another in the background with a command such as hc run --bg codex. enesalatas fires the Codex review from a Claude Code hook so it never gets skipped. Pattern 3: Plan with a strong model, build with a cheap one What it is: the expensive model writes the plan and the tests that prove it. A cheaper model follows the plan. If the cheap model fails, the task moves up to a stronger one. Why it helps: most of the tokens go into building, not planning. Our readers tagged 75 people as routing work by model. gregwebs keeps a three-model setup under $100 a month this way, and glennfiedler's coordinator moves a failed card up a tier instead of retrying the same model. 1. the strong model writes the plan, no code claude -p "Write a step-by-step plan for