ohmyharness
Harness Active Closed source

Cursor

AI code editor whose agent plans, edits, and reviews changes across the codebase and in the cloud.

Visit website ↗ Compare Add to a tier list
Get Cursor Install
Download ↗ opens in a new tab
Download macOSLinuxWindows
Pricing Freemium See pricing ↗

Free plan includes limited agent usage; paid plans from $8/mo (Plus) to $200/mo (Ultra).

  • Free Free Limited AI usage
  • Plus $8/mo Shared usage pool; Grok models only
  • Premium $30/mo 4x more usage than Plus
  • Teams $30/mo Per user; 4-50x Plus usage, pooled
  • Super $100/mo 15x more usage than Plus
  • Ultra $200/mo 50x more usage than Plus
  • Enterprise Contact sales Custom pricing; contact sales

Prices as listed on 19 Oct 2026.

AboutAnysphere

Cursor is an AI-native code editor that runs agent sessions against local or cloud workspaces. It includes tab completion, an agent with browser and terminal tools, subagents, hooks, skills, and a web dashboard for remote agents.

Features Verified 20/20 ✓ yes ✗ no ? not verified What do these mean?

Agents

5/5 verified
✓
Multi-provider
Runs agents from several providers side by side?
yes
✓
ACP
Speaks the Agent Client Protocol?
yes
✓
Parallel agents
Runs several agent sessions at the same time?
yes
✓
Subagents
Can an agent delegate work to child agents?
yes
✓
Custom agents
Can you define your own agent roles?
yes

Workflow

6/6 verified
✓
Plan mode
Has an explicit plan / approve-before-edit step?
yes
✓
Worktrees
Keeps parallel work in separate git worktrees?
yes
✗
Checkpoints
Can you rewind code and chat to an earlier turn?
no
✓
Diff review
Includes a built-in diff or review screen?
yes
✓
PR integration
Opens and tracks pull requests from the session?
yes
✓
Automations
Can it start agent runs on a schedule or event?
yes

Integrations

5/5 verified
✓
MCP
Connects to MCP servers and their tools?
yes
✓
Skills
Can you add reusable skills or commands?
yes
✓
Hooks
Can your own scripts run on agent events?
yes
✓
Issue tracker
Can it pull work from GitHub or Linear issues?
yes
✓
Browser preview
Can the agent open and drive a web browser?
yes

Access & safety

4/4 verified
✓
Remote access
Can you follow or control sessions from another device?
yes
✓
Cloud sandbox
Runs work in a hosted sandbox rather than on your machine?
yes
✓
Local sandbox
Does it sandbox what agents can do locally?
yes
✓
Headless / API
Can you run it from scripts, CI, or your own code?
yes
Other harnessesSee all
Aider Amazon Q Developer CLI Amp Augment Code