巧匠Developer Cheatsheet

Open Interpreter CLI Cheatsheet - Terminal AI Coding Agent Full Reference

Open Interpreter turns an LLM into a terminal agent that reads files, edits code, and runs commands, working with cloud models like OpenAI or Anthropic as well as local models. It targets developers who want an AI agent inside their local workflow without leaving the terminal, and reviews changes before applying them. This sheet covers install, run modes, safety flags, and interactive commands so you can start on real projects immediately.

AI CLI·22 commands·Last updated 2026-09-10
open-interpreterinterpreteraiagentcoding-agentclilocal-model

Install and Launch 5

pip install open-interpreter
Install Open Interpreter via pip
pipx install open-interpreter
Isolated install via pipx (recommended)
interpreter
Start an interactive session in the cwd
interpreter --version
Print the installed version
interpreter --help
List all commands and flags

Run Modes and Flags 7

interpreter --local
Run with a local model (no cloud key)
interpreter --model gpt-4o
Select a cloud model
interpreter -y
Auto-accept all actions (use with care)
interpreter --os
Allow the agent to control the OS
interpreter --api_base https://api.openai.com/v1
Point at a custom OpenAI-compatible endpoint
interpreter --api_key sk-xxxx
Pass the API key directly
interpreter --profile coding
Use a named profile config

Safety and Interaction 7

interpreter --safe_mode
Enable safe mode to limit risky actions
interpreter --server
Start a CDP server for the web UI
interpreter resume --last
Resume the most recent session
/model
Switch model during a session
/help
Show interactive help
/clear
Clear the current conversation
/exit
Quit the interpreter

Advanced 3

vim ~/.interpreter/profile.yaml
Edit profile to set default model and behavior
interpreter --verbose
Print verbose debug output
python -c "from interpreter import interpreter; interpreter.chat('refactor utils')"
Call it programmatically from Python

Tips

  • Open Interpreter plans first and asks you to review; treat -y as an automation switch, not a daily default, to avoid unintended edits.
  • Use --local with an OpenAI-compatible endpoint from LM Studio or Ollama to run fully offline.
  • Switch models mid-session with /model without restarting the conversation.

FAQ

How is Open Interpreter different from chat-style Q and A?

It reads, edits, and runs commands on your project in the terminal and reviews changes with you before applying; plain Q and A only returns text.

Must I use a cloud API?

No. --local uses a local model, or point --api_base at any OpenAI-compatible endpoint including self-hosted ones.

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