Cursor
AI code editor forked from VS Code with built-in agent, multi-file edits, and tab-completion.
Cursor is an AI code editor forked from VS Code with built-in agent, multi-file edits, and tab-completion. Native multi-file editing across an entire codebase.
What it does well
- Native multi-file editing across an entire codebase.
- Supports frontier models from Anthropic, OpenAI, and Google with a single subscription.
- Built on VS Code so existing extensions and keymaps work out of the box.
Where it falls short
- Pro tier limits the number of fast premium-model requests per month.
- Telemetry and code-indexing must be configured explicitly for private repositories.
Tagged
- Supports Claude
- Supports GPT
- Supports Gemini
- MCP Support
- Agentic Mode
- Multi-file Edits
- Git Integration
- Freemium
Compared with similar things
Picked by shared tags inside the AI Code Editors.
- 01Freemium →GitHub Copilot
GitHub's AI pair programmer with chat, inline completions, and agent mode across major IDEs.
- 02Freemium →OpenHands
Open-source autonomous coding agent platform, formerly OpenDevin, by All Hands AI.
- 03Freemium →Claude Code
Anthropic's official CLI agent for Claude — runs in the terminal, edits files, executes commands, and ships PRs.
- 04Freemium →Windsurf
AI code editor by Codeium with Cascade agent for autonomous multi-step coding tasks.
- 05Free →Aider
Open-source CLI coding agent that pair-programs in your terminal and commits to git automatically.
- 06Free →Cline
Open-source autonomous coding agent for VS Code, formerly known as Claude Dev.
Concepts you should know
- Agentic coding
A development style centred on coding agents — the human describes intent, the agent plans and executes the work, and the human reviews diffs or PRs rather than authoring code line by line. The umbrella term for vibe coding and adjacent practices.
- Coding agent
An AI agent specialised for software-engineering tasks. Exposes file editing, terminal execution, code search, and git operations as tools and pursues multi-step coding goals like "add a /signup route with tests".
- Context engineering
The discipline of shaping what an LLM sees in its context window — instructions, examples, retrieved data, conversation history — to elicit reliable behaviour. Evolved from 'prompt engineering' to acknowledge that the prompt is one piece of a larger context budget.
- Context window
The maximum number of tokens an LLM can attend to in a single inference call — both the prompt and the generated output count against it. As of 2026, frontier models range from 200k tokens (GPT-5) to 1M+ tokens (Gemini 2.5, Claude Sonnet 4.6 with 1M extension).
Frequently asked questions
- What is Cursor?
- Cursor is an AI code editor forked from VS Code with built-in agent, multi-file edits, and tab-completion.
- Is Cursor free?
- Cursor offers a free tier and paid plans with higher limits or premium features.
- What platforms does Cursor support?
- Cursor runs on mac, win, linux.
- What category does Cursor belong to?
- Cursor is in the AI Code Editors category — Desktop IDEs built around AI — Cursor, Windsurf, and forks that ship inline edits, multi-file refactors, and agent modes by default.
- What are the downsides of Cursor?
- Pro tier limits the number of fast premium-model requests per month. Telemetry and code-indexing must be configured explicitly for private repositories.