# Cursor — The AI code editor — an agent that reads, writes and edits across your whole codebase.

> Source: The Agents Index — https://theagentsindex.com/cursor (structured, researched, re-verified)
> Facts last verified: 2026-07-13

Cursor is an AI-first code editor (a fork of VS Code) built around an in-editor coding agent. It pairs fast tab-completion with an agent that can read the whole repository, plan a change and apply edits across many files — making it one of the most widely-adopted AI coding tools among professional developers.

| Fact | Value |
| --- | --- |
| Website | https://cursor.com |
| API | No |

## Strengths and weaknesses

- ✓ Fluid, fast in-editor agent that most developers can adopt in minutes.
- ✓ Model choice — run Claude, GPT and others per request.
- ✗ Closed-source and subscription-priced; heavy use can hit fast-request limits.
- ✗ The agent can over-edit on vague instructions — the diff review matters.

## Key features

- **Agentic multi-file edits** — Plans and applies changes across many files from one instruction, with a reviewable diff.
- **Predictive autocomplete** — Tab-completion that suggests the next edit, not just the next token.
- **Codebase chat with retrieval** — Ask questions across the whole repo; the editor retrieves the relevant context.

## Use cases

- **Ship features faster** — A developer implements a feature end-to-end with the agent handling the cross-file plumbing.
- **Refactors** — Rename and restructure across a large codebase with the agent tracking every call site.