How to Set Up Supermaven in VS Code

November 15, 2026

Supermaven is an AI code-completion extension for VS Code, JetBrains IDEs and Neovim built around a 300,000-token context window and sub-250ms suggestion latency. The free tier is unlimited for individual use, and setup in VS Code takes about two minutes.

What makes Supermaven different from Copilot?

Speed and context, mainly. It reads your whole open project into a large context window rather than a small window around the cursor, which shows up in cross-file completions: rename a function in one file and the completion in another file uses the new signature.

It is also completions only. There is no chat panel, no agent that edits files, no test generation. If you want a conversational coding assistant, this is one piece of that stack, not a replacement.

How do you install it?

  1. Open VS Code and go to the Extensions panel.
  2. Search for Supermaven and install the official extension.
  3. Reload the window when prompted.
  4. Sign in with GitHub or email — the extension prompts on first keystroke in an editor.
  5. Open a real project, not a scratch file. Completions before indexing finishes are weaker.

The whole process takes under two minutes. There is no API key to paste and no model selection — the service picks the model server-side.

Which settings are worth changing?

Open Settings and search for Supermaven. Most defaults are sensible; four are worth a look:

Setting Default Change it when
Suggestion delay ~50ms Raise to 100–150ms if suggestions feel noisy
Enable for languages All Turn off for YAML/JSON where completions get in the way
Inline suggestions On Off for prose-heavy files like Markdown
Status bar indicator On Useful for confirming it is active

The delay setting is the one people should adjust and rarely do. At the default, a fast typist sees a ghost suggestion appear and vanish constantly. Raising it makes the experience calmer and does not hurt acceptance rate in practice.

How do you accept and dismiss suggestions?

Tab accepts the whole suggestion. Escape dismisses.

What most people miss: word-by-word acceptance. On macOS it is Ctrl+Right arrow to accept the next word; the VS Code keybinding is configurable. For a long suggested block you only half want, accepting word by word is faster than dismissing and retyping.

A workflow that works for unfamiliar codebases: read the suggestion before accepting it. Supermaven is fast enough that accepting blind is tempting, and that is how subtle bugs enter a codebase. The suggestion is a draft, not an answer.

What are the honest limits?

No chat. No explanations. No multi-file edits. If a suggestion is wrong, you have to know enough to fix it, so it helps strong developers more than beginners.

Context is large but not magical. In a monorepo with 2,000 files, indexing takes a noticeable amount of time on first open and afterwards the most relevant files still win over distant ones. Cross-repo suggestions do not happen.

Language support is uneven. TypeScript, Python, Go, Rust and Java get strong completions. Niche languages and templating file types are weaker, which is why the settings table suggests disabling it for config formats.

Free tier versus paid, in practice

The free tier covers unlimited completions for individual developers, which is the whole product for most users. The paid Pro plan around $10/month adds team features and administrative controls, and longer context for large repositories.

For a solo developer the free tier is genuinely sufficient — an unusual situation in this category, and worth testing before assuming you need to pay.

What is the realistic verdict?

Set it up, use it for a week, and check two things: how often you accept a suggestion without editing it, and whether cross-file completions are actually better than your current tool’s. If acceptance is high, keep it. If you spend more time dismissing than accepting, the completion model does not fit your style and no setting fixes that.

Quick Summary

  • Supermaven installs as a VS Code extension and works in about two minutes with GitHub sign-in.
  • It offers completions only: no chat, no agent, no test generation.
  • 300,000-token context yields noticeably better cross-file suggestions than small-window tools.
  • Raise the suggestion delay to 100–150ms if ghost text feels noisy.
  • Word-by-word acceptance beats dismissing a long suggestion you half want.
  • Free tier is unlimited for individuals; Pro near $10/month adds team controls.