Cursor

An AI-first code editor built for agent-led development.

About

Cursor is a code editor built around AI assistance, based on the familiar VS Code editing experience. Its agent can search a codebase, edit several files, run terminal commands and review changes, while Tab completion predicts your next edit as you type. It is aimed at developers who want the editor and the AI to work as one system, rather than bolting an assistant onto an existing setup.

Key features

• A full code editor with an AI agent that can search, edit and test across a codebase
• Tab completion that predicts the next edit, not just the next few characters
• Chat and inline editing for explanations, refactors, bug fixes and new features
• Cloud agents and automations on higher plans for work that runs outside the editor
• Bugbot code review that checks pull requests for likely problems
• Support for project rules, skills, model context tools and hooks to shape agent behaviour
• A choice of first-party and third-party models, depending on plan, with usage pools that refresh weekly

Pricing

Free $0/month; Plus $8/month; Premium $30/month; Super $100/month; Ultra $200/month; Teams from $30 per user/month

Prices change — check the official pricing page. Third-party models are billed separately at API list price on Premium and above, and are not included in the plan price.

Best for

Developers who want an editor designed around AI agents and multi-file work.

Limitations to know

AI code suggestions can be wrong, insecure, or outdated, and an agent can change working code in ways that need careful review. Human review and testing are still required before shipping code.

What users like

• Strong awareness of codebase context and fast multi-file editing
• An intuitive, familiar editor experience for people coming from VS Code
• Productivity gains on debugging, feature building and routine code generation

What users complain about

• Pricing and usage limits that feel confusing, changeable or hard to predict for heavy users
• Agent edits that occasionally break working code or miss edge cases
• Billing and support frustration reported around plan changes and unexpected usage charges

Our editorial score

Our editorial score: 8.4/10 — our own judgement, not an aggregate of user ratings. See the full review for the reasoning.

Read the full Cursor review · More Coding tools · All AI tools

Related AI tools