Claude Code Dev Stack
AdvancedClaude Code in the terminal, desktop app, or web, paired with Claude and the add-ons to run it anywhere.
Published 27 September 2026
About Claude Code Dev Stack
Claude Code is Anthropic's coding agent, and in this stack it's the implementer rather than an assistant: it reads the repository, plans a change, edits however many files it needs, runs the tests, and fixes what fails, while the developer directs and reviews. It's built for Claude models, the only ones Anthropic supports it with, which is why Claude sits in this stack's core rather than behind a model choice.
The same agent ships on several surfaces: the terminal CLI, a desktop app for macOS, Windows, and Linux, extensions for VS Code and JetBrains IDEs, and the browser. Sessions, project memory files, hooks, and settings carry across them, so the choice is about where you like to review work, not about what the agent can do.
Work keeps going away from the desk in two ways. Cloud sessions run on machines Anthropic manages: start one from claude.ai/code, the Claude mobile app, the desktop app, or the terminal, close the laptop, and come back to a branch or pull request. They're included in Pro, Max, and Team plans and need the repository on GitHub. Remote Control keeps a session on your own machine and lets you follow and steer it from the Claude iOS or Android app or a browser, as long as that machine stays on. Some developers run the CLI on an always-on VPS or home server of their own for the same purpose.
Repositories live on GitHub by default, or on GitLab when source control has to be self-hosted. A faster terminal emulator, Docker for a reproducible environment, and a CI/CD pipeline are common additions; none of them change how Claude Code works.
Key Features
- ✓Claude Code as the implementer: plans, edits across files, runs tests, and fixes failures
- ✓One agent across the terminal, desktop app, VS Code and JetBrains extensions, and the browser
- ✓Cloud sessions on Anthropic-managed machines that keep running with the laptop closed
- ✓Remote Control from the Claude iOS and Android apps or a browser for sessions on your own machine
- ✓Hooks, subagents, and project memory files for custom automation and persistent context
- ✓Commits and pull requests for review, on GitHub or GitLab
When to Use Claude Code Dev Stack
- →Experienced developers working at an architectural level while Claude Code handles implementation
- →Large-scale refactoring across many files driven by a single high-level instruction
- →Starting a cloud session from a phone and reviewing the pull request at a desk later
- →Steering a long local session from the couch through the mobile app
- →Teams evaluating AI-first engineering workflows where the agent does the implementation
Pros
- High leverage per hour: reviewing generated output rather than writing every line
- Full codebase awareness enables coherent large-scale changes
- The same agent in the terminal, desktop, IDE, browser, and phone, with sessions that move between them
- Cloud sessions carry no compute charge beyond the plan itself
Cons
- No free tier: Claude Code starts at the $20/month Pro plan or pay-per-token API use
- Built for Claude; other providers' models work only through unofficial Anthropic-compatible endpoints
- Review burden is higher as the agent generates more code per session
- Cloud sessions need GitHub, so GitLab repositories get local and Remote Control use only
Version Control Options for Claude Code Dev Stack
Claude Code Dev Stack with GitHub
GitHub is the default here: the largest pull-request ecosystem and the platform most CI/CD and review tooling assumes by default.
Claude Code Dev Stack with GitLab
GitLab bundles source control, merge requests, and CI/CD in one self-hostable platform, the pick for teams that need code and pipeline data to stay on their own infrastructure.
Claude Code Dev Stack Add-ons
Each addition below extends this stack with a capability the base stack works fine without. None are required: include the ones your product actually needs when building this stack, and skip the rest.
Server Add-ons
Add a server when you want the agent to keep running somewhere other than your own laptop, reachable at any time and not tied to your machine staying on. Some agents also offer their own managed cloud sessions as an alternative to self-hosting; check the stack's own description for details.
Claude Code Dev Stack with Hetzner
Hetzner is the default here: a 4 GB server, Claude Code's documented minimum, is about €5.49/mo, the lowest price per gigabyte in this list. A plain VPS with nothing preinstalled, fine for one always-on Claude Code session.
Claude Code Dev Stack with DigitalOcean
DigitalOcean's 4 GB Droplet is $24/mo; its $4 plan has only 512 MB, too little for Claude Code. Its Managed Agents, in public preview, run Claude Code in isolated microVMs billed per second, an alternative to keeping a whole server.
Claude Code Dev Stack with Hostinger
Hostinger's KVM 1 has 4 GB of RAM at $6.49/mo introductory, renewing at $11.99/mo, and offers a VPS template with Claude Code preinstalled, the most direct route to a Claude Code server in this list.
Claude Code Dev Stack with Raspberry Pi
A Raspberry Pi 5 with 4–16 GB of RAM is a one-time hardware cost instead of a monthly bill. Claude Code runs on its ARM64 processor, though a 4 GB board sits right at the minimum; 8 GB leaves room for builds and tests.
These are highlighted picks. To see all the tools, check the Hosting & Cloud category.
Remote Access Add-ons
Add remote access when you want to reach an agent running on another machine — a VPS or a home server — without exposing it to anyone but you.
Claude Code Dev Stack with Tailscale
Add Tailscale alongside a server to reach it privately over SSH from your laptop or phone without exposing it to the public internet. Remote Control covers steering the agent; Tailscale covers everything else on the machine. The personal tier is free.
Session Persistence Add-ons
Add session persistence when the agent runs on a server or over SSH: a terminal multiplexer keeps the session working after the connection drops or the laptop closes, and you reattach from any machine to pick up where it left off.
Claude Code Dev Stack with tmux
Add tmux when Claude Code runs on a server or over SSH: the session keeps working after the connection drops or the laptop closes, and you reattach from any machine. It's also what Claude Code's experimental agent teams use to give each teammate its own pane.
Claude Code Dev Stack with Zellij
Add Zellij when you want the same keep-running sessions with an easier start: its status bar shows every shortcut, closed sessions come back with their layout after a reboot, and a built-in web client opens them in a browser. Agent teams' split panes need tmux, though.
Terminal Add-ons
Add a terminal when you want a faster, more configurable place to run the agent than your OS default — most agent CLIs live here all day.
Claude Code Dev Stack with Ghostty
A GPU-accelerated terminal with fast startup and native platform integration on macOS and Linux, a solid default for running Claude Code all day.
Claude Code Dev Stack with Alacritty
A minimal, GPU-accelerated terminal focused purely on speed with almost no built-in features beyond rendering; pick this if a separate multiplexer or window manager already handles everything else.
Claude Code Dev Stack with WezTerm
A GPU-accelerated terminal with built-in multiplexing, tabs, and a Lua-based config, useful for one tool that replaces both the terminal and tmux.
Claude Code Dev Stack with Kitty
A GPU-accelerated terminal with its own graphics protocol and scripting API, popular with developers who want deep customization through its kitten plugin system.
Claude Code Dev Stack with iTerm2
A free, open-source macOS terminal with more than a decade of features: split panes, profiles, triggers, and tmux integration. The familiar pick for Mac users who want Claude Code in the terminal they already know.
Code Review Add-ons
Add code review when you want an AI reading every pull request before it merges: it comments on the diff so bugs, security issues, and inconsistencies surface before a human has to catch them.
Claude Code Dev Stack with CodeRabbit
Add CodeRabbit when you want an AI reviewer on every pull request: it installs as a GitHub or GitLab app, summarizes the diff, and leaves line-level comments before anyone merges, with a free tier for open-source repos.
Claude Code Dev Stack with Greptile
Add Greptile when you want review that reads the whole repository rather than just the diff: it indexes the codebase so its GitHub and GitLab pull request comments carry wider context, and it can be self-hosted.
Claude Code Dev Stack with Cursor Bugbot
Add Cursor Bugbot when a bug-focused reviewer is enough: it reviews GitHub or GitLab pull requests whatever wrote the code, though it bills through a Cursor account and plan rather than its own subscription.
CI/CD Add-ons
Add CI/CD when you want a dedicated pipeline for running tests, linting, or multi-stage builds before a deploy goes out. Many hosting platforms already redeploy automatically on every push on their own — a CI/CD tool adds the most value on top of that by gating the deploy on a passing test suite, and matters even more when the hosting choice does not auto-deploy at all, such as a self-hosted server.
Claude Code Dev Stack with GitHub Actions
Add GitHub Actions when the repo lives on GitHub and you want tests and deploys running automatically on every push Claude Code makes.
Claude Code Dev Stack with GitLab CI/CD
Add GitLab CI/CD when the project is on GitLab and needs the same automated pipeline, defined in a .gitlab-ci.yml file that can run entirely on your own infrastructure.
These are highlighted picks. To see all the tools, check the CI/CD Pipelines category.
Containerization Add-ons
Add containerization when you want the app packaged the same way across local development, staging, and production, or need to deploy somewhere that isn't a managed serverless platform.
Claude Code Dev Stack with Docker
Add Docker when the project needs environment parity between wherever Claude Code runs and production, or when the agent's own execution environment should be reproducible and disposable.
These are highlighted picks. To see all the tools, check the Containerization category.
Frequently Asked Questions about Claude Code Dev Stack
Can Claude Code keep working when my laptop is closed?
Yes, with a cloud session. It runs on a machine Anthropic manages, starts from claude.ai/code, the Claude mobile app, the desktop app, or the terminal, and keeps going with your laptop off; you come back to a branch or pull request. Cloud sessions are part of Pro, Max, and Team plans and need the repository on GitHub. Remote Control is the other route: the session stays on your own machine and you steer it from the Claude iOS or Android app or a browser, but that machine has to stay on and online. An always-on server of your own does the same job for developers who want the environment under their control.
How does Claude Code compare to Codex?
Both are standalone coding agents with a CLI, a desktop app, IDE extensions, and a cloud mode, so the practical difference is the model family and the plan. Claude Code runs Claude models on a Claude plan; Codex is built around OpenAI's models on a ChatGPT plan, which also has a free tier, and officially supports other providers through its config. Claude Code's Remote Control works with a session on any system, Linux included, while Codex's phone access needs its desktop app on macOS or Windows as host. Many developers pick whichever subscription they already pay for.
Do I have to work in the terminal?
No. The terminal CLI is the original surface, but the desktop app, the VS Code and JetBrains extensions, and claude.ai/code run the same agent with the same project settings, and a session can move between them. The terminal suits developers who review diffs and test output directly; the desktop app and IDE extensions show changes as visual diffs next to the code.
Which plan do I need for heavy use?
Pro covers regular daily use; Max raises the limits five or twenty times for long sessions, several parallel sessions, or heavy use of the largest models. Cloud sessions, Remote Control, and local sessions all draw on the same plan limits, so running many at once uses them up faster. API billing per token is the alternative for irregular or automated use. The Pricing section has the current figures.
Does GitLab work as well as GitHub here?
Locally, yes: Claude Code only needs git, so commits, branches, and merge requests on GitLab work the same from the terminal, desktop app, or an IDE. The difference is cloud sessions, which clone repositories and open pull requests through GitHub. A GitLab project can be sent to a cloud session as an upload, but the session can't push results back to GitLab, so GitLab users mostly work locally or through Remote Control.
Stacks Related to Claude Code Dev Stack
Paseo Dev Stack
Developer
Run Claude Code, Codex, and other coding agents on your own machine with Paseo and steer them from any device.
T3 Code Dev Stack
Developer
One open-source app for Claude Code, Codex, OpenCode, and other coding agents, on desktop and mobile.
Conductor Dev Stack
Developer
Run Claude Code, Codex, and Cursor's agent in parallel on your Mac with Conductor, each in its own workspace.
Orca Dev Stack
Developer
Run Claude Code, Codex, and other coding agents side by side in Orca, each on its own branch and model.
Scores
Popularity4/5
One of the most widely used coding agents, discussed well beyond AI-focused developers, with a large community of shared workflows and configuration.
Learning Curve3/5
Plain-language tasks work on day one, but directing an agent well, writing project instructions, and reviewing large diffs are skills that take practice.
Flexibility5/5
Hooks, subagents, MCP servers, and five surfaces from terminal to phone make it adaptable to almost any workflow, within Claude's own model family.
Performance5/5
Handles large multi-file changes with full repository context, and cloud sessions run parallel tasks off the local machine.
Portability5/5
Works on plain files and git from any machine; project instructions are markdown, so leaving costs little beyond habits.
Tools in the Claude Code Dev Stack Stack
Development Tools
LLM
Add-ons (optional — add any, or none)
Server
Remote Access
Session Persistence
Terminal
Code Review
CI/CD
Containerization
Claude Code Dev Stack Pricing
Claude Code has no free tier: it starts with the Pro plan at $20/month, Max plans at $100 or $200/month raise the limits for heavy use, and Team seats are $25 or $125/month. Pay-per-token API billing is the alternative. Cloud sessions carry no extra compute charge. GitHub or GitLab are free for individual developers, the terminal emulators listed are free, and a VPS runs about €5.49–24/month for 4 GB.
Pro $20/mo; Max $100/mo (5x) or $200/mo (20x); Team seats $25 or $125/mo; or pay-per-token API. The free Claude plan doesn't include Claude Code.
Free tier covers individual devs; GitHub Team is $4/mo, GitLab Premium is $29/mo for more seats.
Ghostty, Alacritty, WezTerm, Kitty and iTerm2 are all free, open-source terminal emulators.
Tailscale's personal tier is free for up to 100 devices, enough for one person's own machines.
A 4 GB VPS: Hetzner €5.49, Hostinger $6.49 intro ($11.99 renewal), DigitalOcean $24; or a Raspberry Pi as a one-time cost.