Advertise hereReach developers building with AI coding agents. →

Compiled from official documentation, checked

Google Antigravity vs Cursor: documented features compared

Short answer

Antigravity is Google’s agent-first platform with an app, IDE, CLI and IDE extensions, free to start with higher limits on Google AI Pro and Ultra. Cursor is an AI-first code editor with a CLI, cloud agents and its own plans from Free to Ultra. Both support MCP, AGENTS.md and SKILL.md skills; they differ in config files, rules format and how usage is billed.

How this comparison was made: we have not run hands-on tests or benchmarks of either agent. Every row summarises the vendor’s own documentation and links to it. Prices are list prices as published on the date above and can change.
Google AntigravityCursor
Surfaces Antigravity app, IDE, CLI, IDE extensions and SDK source Cursor editor, CLI and cloud agents source
MCP config location ~/.gemini/config/mcp_config.json (global) or .agents/mcp_config.json (workspace) source .cursor/mcp.json (project) or ~/.cursor/mcp.json (global) source
Remote MCP servers serverUrl key; OAuth sign-in, tokens stored in ~/.gemini/antigravity/mcp_oauth_tokens.json source url key; OAuth, and Add to Cursor one-click installs from the Cursor Marketplace source
Rules / instructions AGENTS.md or GEMINI.md, plus .agents/rules/*.md with a required trigger (always_on, model_decision, glob or manual) source .cursor/rules/*.mdc (description, globs, alwaysApply) and AGENTS.md source
Skills folders .agents/skills/<name>/SKILL.md source .cursor/skills/ and .agents/skills/, plus .claude/skills/ and .codex/skills/ for compatibility source
Individual pricing $0 to start with basic weekly limits; more on Google AI Pro, most on Google AI Ultra source Free $0, Plus $8 (Grok models only), Premium $30, Super $100, Ultra $200/mo source
How usage is metered Free: quota refreshed weekly. Pro and Ultra: refreshed every five hours up to a weekly limit; AI credits for overages source Usage multiples of Plus (4x, 15x, 50x); third-party models billed separately at API list price source

Which fits your setup?

Based on documented features, not our own testing. See how SaaS tools are supported in each: Antigravity tools · Cursor tools

Full pricing details: Google Antigravity pricing, plans & limits · Cursor pricing, plans & limits

Related

AGENTS.md vs CLAUDE.md vs Cursor rules

→

How to add an MCP server to Cursor

→

How to add an MCP server to Google Antigravity

→

How to migrate from Gemini CLI to Antigravity CLI

→

Cursor Agent SDK: build, test and deploy agents as code

→

Antigravity CLI (agy): install, sign in, modes and commands

→

Google Antigravity on Windows: install, WSL, sandbox and fixes

→

Antigravity skills: create, store and run SKILL.md skills

→

Cursor rules examples: .mdc files for each rule type

→

Claude Code vs OpenAI Codex: documented features compared

→

Cursor vs Claude Code: documented features compared

→

Claude Code vs GitHub Copilot: documented features compared

→

OpenAI Codex vs Cursor: documented features compared

→

Cursor vs GitHub Copilot: documented features compared

→

Google Antigravity vs Claude Code: documented features compared

→

OpenAI Codex vs GitHub Copilot: documented features compared

→

MCP config generator for every agent

→

Frequently asked questions

We have not tested them hands-on, so we do not rank them. Both document MCP, AGENTS.md and SKILL.md skills. The documented differences are surfaces, config files, rules format and plan packaging.

Sources