💻
Cursor
by Anysphere
Cursor is an AI-first code editor (a fork of VS Code) that puts GPT-4 and Claude directly into the editing experience. It can rewrite entire functions from a description, explain unfamiliar codebases, generate tests, and apply multi-file edits with a single instruction. Developers describe it as the closest thing to having a senior engineer pair-programming with you full time.
Cursor features and capabilities, including which plan they need and how they compare in the CanIUse matrix.
cursor-anysphereAdded 2025-09-21Catalog rank 10
Used in combinations
More from Anysphere
Compare Cursor with:
Directory alternatives
GitHub CopilotAI pair programmer for code completion and generationAdded 2025-09-21developer_toolscode_generationinfrastructuredeploymentWindsurfAgentic AI code editor by CodeiumAdded 2025-01-01code_generationdeveloper_toolsproductivitycodingCodeiumFree AI code completion for every IDEAdded 2025-09-21code_generationdeveloper_toolsproductivitycodingClaude CodeAnthropic's agentic coding tool that works directly in your terminalAdded 2025-09-21code_generationdeveloper_toolsproductivitycodingReplitAI-enhanced online IDE and development platformAdded 2025-09-21developer_toolscode_generationinfrastructuredeploymentClineAutonomous AI coding agent in VS CodeAdded 2025-01-01code_generationdeveloper_toolsproductivitycodingAiderTerminal-based AI pair programmer for your git repoAdded 2025-01-01code_generationdeveloper_toolsproductivitycodingAmazon Q DeveloperAWS's AI coding assistant with deep AWS service knowledgeAdded 2025-01-01code_generationdeveloper_toolsproductivitycoding
✨ Modalities
💬
Yes. Agent chat is driven by text prompts in the input. You type instructions, attach @ context, and switch models from that same field.Text Input
🖼️
Yes. You can drag an image into chat or paste a screenshot. Agent also reads image files (.png, .jpg, .gif, .webp, .svg) for vision-capable models.Image Upload / Vision
🎨
Yes. Agent can generate images from text or reference images for UI mockups and diagrams. Files land in the project assets/ folder and show inline in chat.Image Generation
🎙️
Partial. A microphone in the chat input dictation-transcribes prompts, and iOS can dictate to agents. That is one-way voice input, not a two-way spoken conversation loop.Voice Mode
🎥
Partial. Grok Bot accepts video attachments (up to 200 MB) so that Bot can inspect recorded footage. Core Agent chat is documented for images and files, not a general YouTube/video-watch loop, so this is not product-wide video understanding.Video Understanding
🎬
No. Not a video generation product.Video Generation
📁
Yes. Chat @-mentions attach files and folders. Grok Bot also takes PDFs, Office docs, CSV, JSON, source, and notebooks as message attachments.File Upload (PDF, DOCX)
💻
Yes. Agent runs shell commands in the terminal, watches output, and can execute tests, linters, and builds as part of a task.Code Execution
🔊
Partial. Grok Bot message attachments include audio files (25 MB each) in the same table as documents and images, so pre-recorded audio can be sent for a task. Core Agent chat is not documented as a general audio-file transcribe surface, so this is Grok Bot only.Audio Input
🖌️
Yes. The Agents Window is an agent-first workspace beside the classic IDE editor, with diffs, file search, and split layouts. Agent also opens in a Cmd+I sidepane.Canvas / Artifact Editor
🖥️
Yes. Cloud Agents run a full desktop and can drive mouse/keyboard plus the browser (computer use). You can take over the remote desktop, then hand control back to the agent.Screen Sharing / Computer Use
🧠 Memory & Context
🧠
Partial. Grok Bots retain facts and summaries across work. Core Agent chat relies on Rules instead of auto-memory between completions, so this is not ChatGPT-style global memory.Persistent Memory
📏
Yes. Each chat has a fixed model context window with a usage ring. Cloud Agents let you pick context size; several models document up to 1M-token extended context.Large Context Window
⚙️
Yes. Project and user Rules (.cursor/rules plus User Rules) inject persistent instructions into Agent. Always Apply, glob, and @-mention rules are documented.Custom Instructions
📜
Yes. Past chats persist so you can @Chats into a new prompt. CLI resume/continue reloads prior threads; iOS keeps an agent inbox of running conversations.Conversation History
🔌 Integrations
🌐
Yes. Agent has a Web tool that generates search queries and performs live web searches during a task.Web Search / Browsing
🔌
Yes. Cursor Marketplace installs official plugins that bundle rules, skills, MCP servers, and hooks. Teams can ship a private marketplace; VS Code extensions still work in the editor.Plugins / Extensions
🔧
Yes. Cloud Agents API, TypeScript/Python SDKs, Admin API, Analytics API, and related endpoints are documented. They run agent workflows, not a raw chat-completions API.API Access
⚡
Unknown. No first-party Cursor Zapier app was listed on cursor.com/docs. Automations document GitHub, GitLab, Slack, Linear, and webhooks instead.Zapier Integration
🤖
Yes. Grok Bots are named durable agents with a profile, skills, routines, and shareable templates. You create, duplicate, and share a Bot the way Custom GPTs are specialized agents.Custom GPTs / Bots
👥
Partial. You can share a Cloud Agent URL with teammates (read-only unless team follow-ups are on). Grok Bot group chats exist. This is not a simultaneous multiplayer editor session.Real-time Collaboration
🐦
Live Social Data Integration
📚
Live Citation Mapping
👨💻 Developer
🛠️
Yes. Cursor connects to MCP servers that expose tools the model can execute. Agents call those functions from chat and Plan Mode, with user approval before each tool run by default.Function Calling
⚡
Yes. iOS follows agent work live and watches the chat stream as the agent codes. The TypeScript SDK iterates streams; ACP clients handle streaming session updates.Streaming Responses
🎛️
No. Public APIs run hosted agent workflows. Docs do not offer a customer fine-tune SKU for foundation weights; you pick Cursor and third-party hosted models.Fine-Tuning
📐
No. Cursor APIs are agent, admin, and analytics endpoints, not a vector embeddings API for converting text into embeddings in your own app.Embeddings API
📋
Unknown. ACP and SDKs exchange JSON-RPC/tool payloads, but no first-party JSON-schema guarantee for model replies was documented on the API overview.Structured Output (JSON)
🧩
Yes. The model catalog lists Thinking variants and GPT reasoning-effort options (for example gpt-5-high). The SDK exposes thinking messages and a reasoning-effort parameter.Reasoning / Thinking Mode
🏠
Local Execution
🔓
Open Weights
🤖
Multi-Agent Orchestration
📱 Platforms
🌐
Yes. Cursor Web at cursor.com/agents starts and manages cloud agents from a browser on any device, alongside desktop and iOS.Web App
📱
Yes. Native Cursor for iOS (App Store) directs cloud and local agents, reviews PRs, and streams work. Requires iOS/iPadOS 26+; listed on Start through Enterprise.iOS App
🤖
Partial. There is no native Android app; docs say Android is planned. Use cursor.com/agents in Chrome and Install App for a PWA.Android App
🖥️
Yes. Cursor is a native IDE: .dmg on macOS 12+, .exe on Windows 10+, and apt/yum/AppImage on Linux. Quickstart starts with installing that desktop app.Desktop App
🔵
No. Documented clients are the desktop IDE, cursor.com/agents, iOS, Slack, GitHub, Linear, and the API. Agent uses a built-in IDE browser, not an official Chrome extension.Chrome Extension
🔒 Privacy
🔒
Yes. Enterprise docs link a GDPR-compliant DPA and state Cursor maintains GDPR compliance alongside SOC 2 Type II. Individual plans follow the Privacy Policy, not the DPA.GDPR Compliant
🚫
Yes. Privacy Mode is a settings toggle: with it on, Customer Data is not used for training by Cursor or model providers under ZDR. Teams/Enterprise can enforce it org-wide.Opt Out of Data Training
🏢
Yes, requires enterprise plan. Enterprise adds Privacy Mode enforcement, ZDR, optional CMEK, data residency, SSO/SCIM, and a DPA. Privacy Mode is on by default for Enterprise teams.Enterprise Privacy Mode
💼 Workspaces
📂
Yes. You open a project folder after install. Agents Window adds multi-workspace; Agent search docs cover multi-root workspaces with per-folder context.Projects / Folders