巧匠Developer Cheatsheet

GPT Engineer CLI Cheatsheet - gpte Code Generation Full Reference

GPT Engineer generates an entire codebase from a natural-language prompt and can improve existing code. gpte (or gpt-engineer) is its CLI: write a prompt file, run the command, review the generated code. This sheet covers create, improve, model, and flags so you can bootstrap a small project from scratch.

AI CLI·20 commands·Last updated 2026-09-10
gpt-engineergpteaicode-generationcliagentscaffold

Install and Create 4

pip install gpt-engineer
Install GPT Engineer
gpt-engineer projects/my-new-project
Generate a new project from prompt
gpte projects/my-new-project
Generate via the gpte alias (better UX)
gpt-engineer --help
Show all flags

Improve and Feedback 4

gpt-engineer -i projects/my-old-project
Improve an existing codebase
gpt-engineer --steps use_feedback
Iterate with feedback
gpt-engineer --use-custom-preprompts
Use project custom preprompts
gpt-engineer projects/x -i
Improve inside a project dir

Model and Flags 12

gpt-engineer projects/x --model gpt-4o
Select the generation model
gpt-engineer projects/x --model anthropic/claude-3-5-sonnet
Use an Anthropic model
gpt-engineer projects/x --temperature 0.1
Set generation randomness
gpt-engineer projects/x --steps tdd
Test-driven workflow
gpt-engineer projects/x --steps clarify
Clarify before coding
gpt-engineer projects/x --steps simple
Minimal steps for quick prototype
gpt-engineer projects/x -s default
Default workflow (short -s)
gpt-engineer projects/x --steps evaluate
Evaluate an existing implementation
gpt-engineer projects/x --verbose
Verbose logs
gpt-engineer projects/x -v
Short verbose logs
export OPENAI_API_KEY=sk-xxxx
Set the API key
gpt-engineer --version
Show version

Tips

  • Put a prompt file (no extension) named prompt in the project dir; the command only needs the directory path.
  • Improve mode (-i) lets you pick files for context, controlling scope precisely.
  • --steps sets the workflow: tdd, clarify, simple, or use_feedback, by task complexity.

FAQ

How is GPT Engineer different from IDE tools like Cursor?

It generates a whole codebase into a workspace dir, biased toward bootstrapping projects; IDE tools assist incrementally inside the editor.

Is OpenAI the only option?

OpenAI by default, but also Azure OpenAI, Anthropic, and local open models via --model and config.

Related Cheatsheets

6 related cheatsheets

Claude Code CLI Cheatsheet - Anthropic AI Coding Agent Full ReferenceFull command reference for Claude Code, Anthropic terminal AI coding agent: install & auth, -p print mode and session resume, --permission-mode/--worktree, dev slash commands, MCP server management, and @ file references, all flags matching official docs.Codex CLI Cheatsheet - OpenAI Terminal Coding Agent Full ReferenceCommand reference for OpenAI Codex CLI, the Rust-built terminal coding agent: install & auth, interactive and non-interactive codex exec, session management, model & config, sandbox and approval modes, MCP, and Codex Cloud.Gemini CLI Cheatsheet - Google Terminal AI Agent Full ReferenceCommand reference for Gemini CLI, Google open-source (Apache 2.0) terminal AI agent: install & auth, run modes and global flags, session slash commands, MCP/extension management, and GEMINI.md project memory, with a 2M context.Cursor Editor CLI Cheatsheet - AI Editor Command Line & Agent FlagsCommand-line and Cursor Agent reference for Cursor, the VS Code-based AI editor: opening files/folders, window management, diff compare, extension management, rendering & performance, remote dev, debugging, cursor-agent non-interactive calls, and git core.editor integration.Aider Cheatsheet - Open-Source Terminal AI Pair Programming Full ReferenceCommand reference for Aider, the open-source Apache 2.0 terminal AI pair programmer (100+ models, auto git commits): install, model & reasoning, files & context, chat modes, Git & run, session tools, and advanced usage.OpenCode CLI Cheatsheet - Open-Source TUI AI Coding Agent Full ReferenceCommand reference for OpenCode, the open-source Claude Code-style TUI terminal AI coding agent: launch & resume, CLI flags, session and subcommands (agent/auth/github/mcp/run/serve/web), and interactive slash commands.

Official References

Each command links to its official documentation below, so you can verify the latest usage and read deeper.

Maintained by LaoHand

Publicly updated on Sep 10, 2026, continuously proofread against official docs.

Contact Us

Wrong command or description? Send us corrections, business inquiries or product feedback by email.

Contact Us