P
🤖AutomatisationBeginner6 steps

Cursor 3: the AI-native IDE with parallel agents on git worktrees

Cursor 3 crossed $500M ARR and became the reference AI IDE among developers. It's a VS Code fork designed around AI: ultra-fast tab completion, agent mode, composer for multi-file refactors. The v3 headline: parallel agents. Up to 8 agents can run concurrently on different parts of your codebase via git worktrees, avoiding conflicts and parallelizing independent tasks (e.g., one agent on tests, one on docs, one on a back-end refactor). Cursor remains the go-to tool for developers who want to stay in a classic IDE while leveraging the latest models (Claude Sonnet, GPT, Gemini) with fine-grained orchestration.

idecoding-agentcursorvscode-forkparallel-agentsgit-worktreescomposer

For who

Front-end/back-end developers and product teams who want an AI IDE with parallel agents and an easy VS Code migration path.

Input

Type: text
Format: libre

Prompts en langage naturel, code existant dans l'IDE, references a des fichiers et symboles.

steps (6)

1

Install Cursor 3

info

Download Cursor from cursor.com for macOS, Linux or Windows. Import of your VS Code config is offered on first launch.

2

Pick your models

info

Configure LLMs (Claude Sonnet, GPT, Gemini) based on speed/quality/cost preferences.

3

Use tab completions

info

Start coding: Cursor continuously suggests code anticipating your intentions.

4

Switch to agent mode

info

For broader tasks, open the agent panel and describe the goal in plain English (e.g., "add a REST endpoint to delete a user").

5

Launch parallel agents

info

In the Cursor 3 panel, trigger multiple agents simultaneously on different parts of the codebase via git worktrees.

6

Review the diffs

info

Consolidate agent work by reviewing diffs, merging worktrees, and running tests.

Output

Type: text
Format: code

Diffs de code, PR, suggestions tab completion, refactors multi-fichiers executes via composer.

Example

Input

In the agent panel: "Migrate all our Express routes to Hono, add tests for each new handler, and update the OpenAPI doc."

Output

Cursor 3 launches 3 parallel agents: one on /api/users, one on /api/orders, one on /api/billing, each in its worktree. Each agent lands commits and 10+ tests. You merge the three worktrees and run CI.

Customization

ParameterDescriptionDefault
Modele principalLLM utilise par defaut par les agents (Claude Sonnet, GPT, Gemini).Claude Sonnet
Nombre d'agents parallelesNombre maximum d'agents simultanes (jusqu'a 8).3
Mode privacyActiver le Privacy Mode pour ne pas envoyer le code aux fournisseurs LLM au-dela de l'inference.Active

Technical Notes

Available on macOS, Linux, Windows. Plans from $20/mo to $200/mo based on usage. Privacy Mode for sensitive enterprises.