VS Code AI Dev Stack
BeginnerVS Code stays your editor; the AI extension and version control underneath are both your choice.
Published 27 September 2026
About VS Code AI Dev Stack
VS Code is the most widely used code editor, and its AI story is that almost every major coding assistant plugs into it as an extension rather than requiring its own editor. GitHub Copilot is the default here: Tab completions, chat, and an agent mode that edits files and runs commands, with GPT, Claude, and Gemini models in its own picker.
Cline and Kilo Code are open-source, bring-your-own-key alternatives to Copilot's bundled subscription, trading convenience for direct control over which model runs and what it costs per token. Claude Code and Codex are also available as their own official extensions, bringing each vendor's agent into the editor's sidebar, running on that vendor's own models. Code lives on GitHub by default, or on GitLab for teams that need self-hosted source control.
VS Code isn't tied to your own laptop either. GitHub Codespaces opens the full editor in a browser, extensions and AI included, on a cloud machine GitHub runs, with a free monthly allowance on personal accounts. On a paid Copilot plan, the Copilot cloud agent takes a task from a GitHub issue or the GitHub Mobile app and works on it in GitHub's cloud, so your machine can be off. On your own computer, vscode.dev reaches the full editor through a Remote Tunnel, and Copilot CLI sessions can be steered from GitHub Mobile, as long as that computer stays on. VS Code can also run agent sessions on an always-on server of your own over SSH.
This is the natural starting point for developers who already use VS Code and want AI assistance without switching editors. Extensions can be swapped as needs change without touching VS Code's settings, keybindings, or the rest of its extension ecosystem, and Docker or a CI/CD pipeline can be added once a project needs them.
Key Features
- ✓GitHub Copilot Tab completions, chat, and agent mode, with GPT, Claude, and Gemini in its model picker
- ✓Cline and Kilo Code as open-source, bring-your-own-key alternatives to Copilot's bundled subscription
- ✓Claude Code and Codex available as official extensions, bringing each agent's own workflow into the sidebar
- ✓The full editor in a browser through GitHub Codespaces or vscode.dev, extensions included
- ✓Copilot cloud agent that works on GitHub issues in GitHub's cloud, assignable from GitHub Mobile
- ✓Full VS Code extension and keybinding ecosystem stays intact whichever AI extension is chosen
When to Use VS Code AI Dev Stack
- →Adding AI assistance to an existing VS Code setup without switching editors
- →Comparing AI coding assistants by swapping the extension without changing anything else
- →Assigning a GitHub issue to Copilot's cloud agent from a phone and reviewing the pull request later
- →Coding from any computer's browser in a Codespace, with the same extensions and AI as at the desk
- →Teams standardizing on one extension while individual developers keep their own VS Code setup
Pros
- The largest extension ecosystem of any editor, unaffected by which AI extension is active
- Free to switch between Copilot, Cline, Kilo Code, Claude Code, or Codex without losing any editor setup
- Copilot's cloud agent keeps working on GitHub with the laptop closed, on any paid plan
- Bring-your-own-key options (Cline, Kilo Code) give direct control over model choice and per-token cost
Cons
- Extensions work within what VS Code lets an extension do, so the AI is less woven into the editor than in an AI-native one
- Bring-your-own-key extensions require managing API keys and costs directly, rather than one bundled subscription
- Copilot's free tier has no cloud agent, and premium models use up AI credits quickly
- Suggestions from any extension can be confidently wrong; review is still required
AI Extension Options for VS Code AI Dev Stack
VS Code AI Dev Stack with GitHub Copilot
GitHub Copilot is the default here: the most widely deployed AI coding assistant, with the deepest VS Code and GitHub integration and support for multiple underlying models including GPT, Claude, and Gemini.
VS Code AI Dev Stack with Cline
Cline is an open-source, model-agnostic alternative that connects to your own API key for Claude, GPT, Gemini, or a local model, giving more control over cost and model choice than Copilot's bundled subscription.
VS Code AI Dev Stack with Kilo Code
Kilo Code forked from Cline with an expanded feature set and its own hosted model marketplace, while staying open-source and bring-your-own-key like its origin.
VS Code AI Dev Stack with Claude Code
Claude Code's official VS Code extension brings its autonomous, multi-file agent workflow into the editor's sidebar with inline diffs, rather than running purely from the terminal.
VS Code AI Dev Stack with Codex
Codex's official VS Code extension brings OpenAI's agent into the editor the same way, for teams standardized on ChatGPT and OpenAI rather than Anthropic.
These are highlighted picks. To see all the tools, check the AI Coding Agents category.
Version Control Options for VS Code AI Dev Stack
VS Code AI Dev Stack with GitHub
GitHub is the default here: Copilot's integration is naturally deepest with GitHub given the shared parent company, and it's the platform most tutorials assume.
VS Code AI 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.
VS Code AI 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.
VS Code AI Dev Stack with Hetzner
Hetzner is the default here: a 4 GB server is about €5.49/mo, the lowest price per gigabyte in this list. VS Code recommends 2 GB for a remote host; 4 GB leaves room for an agent session and the builds and tests it runs.
VS Code AI Dev Stack with DigitalOcean
DigitalOcean's 4 GB Droplet is $24/mo (2 GB is $12/mo, enough for VS Code alone but tight with an agent), in exchange for a more polished dashboard and wider region coverage. Its 1-Click Codex CLI and OpenCode Droplets come preinstalled for those agents.
VS Code AI Dev Stack with Hostinger
Hostinger's KVM 1 has 4 GB of RAM at $6.49/mo introductory, renewing at $11.99/mo. It offers a Claude Code VPS template, useful when Claude Code is the extension picked here and you also want its CLI on the remote machine.
VS Code AI 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. VS Code's remote server supports its ARM64 builds, though some extensions ship no ARM binaries, and the memory ceiling limits how much runs at once.
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.
VS Code AI Dev Stack with Tailscale
Add Tailscale alongside a server to reach it privately over SSH from any of your devices without exposing it to the public internet. VS Code's own dev tunnels are the built-in alternative; Tailscale covers everything else on the machine too. The personal tier is free.
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.
VS Code AI 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.
VS Code AI 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.
VS Code AI 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.
VS Code AI 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.
VS Code AI 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.
VS Code AI Dev Stack with Docker
Add Docker when the project needs environment parity between a developer's machine and production, or when onboarding a new teammate should be a single command instead of a page of setup instructions.
These are highlighted picks. To see all the tools, check the Containerization category.
Frequently Asked Questions about VS Code AI Dev Stack
Can the AI keep working when I'm away from my computer?
Yes. GitHub Codespaces runs the full editor in a browser on a cloud machine GitHub hosts, with your extensions and AI, so it works from any computer with your own machine off; personal accounts get a free monthly allowance. On a paid Copilot plan, the Copilot cloud agent works on an issue in GitHub's cloud, assigned from the website or GitHub Mobile, and opens a pull request when done. Your own computer can also be reached from a browser through vscode.dev, and Copilot CLI sessions steered from GitHub Mobile, but only while it stays on and online. Running VS Code on an always-on server of your own is possible too, though few developers need it.
Which AI extension should I start with?
GitHub Copilot if you want the least setup: one subscription, no API keys, and GPT, Claude, and Gemini in its model picker. Cline or Kilo Code if you want to bring your own API key and pay per token for any provider, local models included. Claude Code or Codex if you already use that agent; each runs its own vendor's models and bills through that vendor's plan.
How is this different from Cursor?
Cursor is a fork of VS Code with its agent, Tab completions, and a multi-provider model picker built into the editor itself, and it runs VS Code extensions too, including Claude Code and Codex. This stack keeps stock VS Code and adds AI through an extension, which can be swapped freely but works within what an extension is allowed to do. Pick Cursor for the most integrated experience, or VS Code to keep the editor unchanged and choose the AI separately.
What does it cost to combine extensions?
Each extension bills on its own: Copilot through its plan's AI credits, Claude Code and Codex through Anthropic and OpenAI plans, and Cline or Kilo Code through whichever API key or credits you load. Installing several means paying for several, so most developers keep one active and disable the rest. The Pricing section has the current figures.
Can I run more than one AI extension at once?
VS Code doesn't stop you, and it can be useful to keep Copilot's completions while a Claude Code or Codex agent works in the sidebar. Two chat-based agents on the same files at once is where it breaks down: they don't see each other's pending edits, so one can overwrite the other's changes.
Scores
Popularity5/5
VS Code is the most used editor and Copilot the most widely deployed AI coding assistant.
Learning Curve1/5
Installing an extension in an editor most developers already know is the gentlest start of any developer stack; the AI works from plain-language requests.
Flexibility5/5
Five interchangeable AI extensions, any model through the bring-your-own-key ones, and the largest extension ecosystem of any editor.
Performance4/5
Completions are fast and the cloud agent moves long tasks off the local machine, though extension-based agents add some overhead over native integrations.
Portability5/5
Stock, open-source VS Code with a swappable extension: changing the AI or leaving the editor costs almost nothing.
Tools in the VS Code AI Dev Stack Stack
Development Tools
Add-ons (optional — add any, or none)
Server
Remote Access
Code Review
CI/CD
Containerization
VS Code AI Dev Stack Pricing
GitHub Copilot has a free tier for light use without the cloud agent; Pro is $10/month and Pro+ $39/month, both metered in GitHub AI credits, with the cloud agent included. Cline and Kilo Code are free extensions billed per token through your own API key, or Kilo Pass credits from $19/month. Claude Code and Codex need their own vendor plans. GitHub and GitLab are free for individuals. The optional server is about €5.49–24/month for 4 GB.
Copilot Free has no cloud agent; Pro $10/mo, Pro+ $39/mo. Cline and Kilo Code bill per token with your key, or Kilo Pass from $19/mo.
Free tier covers individual devs and small teams; GitHub Team is $4/mo, GitLab Premium is $29/mo for more seats.
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.
Tailscale's personal tier is free for up to 100 devices; VS Code dev tunnels are free.
Docker Desktop is free for personal use; Docker Pro adds team features from $5/mo.
GitHub Actions and GitLab CI/CD both include free monthly minutes before paid tiers kick in.