Cette page est affichée en anglais. Une traduction française est en cours.
SkillsApr 2, 2026·3 min de lecture

Open Interpreter — AI That Runs Code on You

Natural language interface that executes Python, JS, and shell commands on your computer. Local-first, model-agnostic. 63K+ stars.

Introduction

Open Interpreter is a natural language interface that executes code on your computer. Tell it what you want in plain English, and it writes and runs Python, JavaScript, or shell commands to accomplish the task — from data analysis to file management to web automation.

Core capabilities:

  • Natural Language → Code — Describe tasks in words, get working code executed automatically. "Resize all images in this folder to 800px" just works
  • Multi-Language Execution — Runs Python, JavaScript, Shell, and AppleScript. Picks the right language for each task
  • File System Access — Read, write, organize, and transform files on your computer. Process spreadsheets, images, PDFs, and more
  • Data Analysis — Load CSVs, query databases, generate visualizations, and create reports interactively
  • System Control — Manage processes, install packages, configure settings, and automate repetitive system tasks
  • Model Agnostic — Works with OpenAI, Anthropic, Google, Ollama (local), and any LiteLLM-compatible provider
  • Safety Controls — Asks for confirmation before executing code. Sandboxed execution mode available

63,000+ GitHub stars. Used by developers, data scientists, and power users for hands-free computer automation.

FAQ

Q: Is it safe to let AI run code on my computer? A: Open Interpreter asks for confirmation before executing each code block by default. You can review what it's about to run. For extra safety, use --safe_mode which restricts file system and network access.

Q: How does it compare to Claude Code? A: Claude Code is specialized for software development (editing files, git, tests). Open Interpreter is more general — it can do data analysis, system administration, file management, and any task that can be solved with code. They're complementary tools.

Q: Can I use it with local models (no API key)? A: Yes. Use interpreter --model ollama/llama3.2 or any local model via Ollama. Quality depends on model capability — larger models handle complex tasks better.

Q: What operating systems does it support? A: macOS, Linux, and Windows. Some system-specific features (like AppleScript) are platform-dependent.

Works With

  • OpenAI / Anthropic / Google / Ollama / any LiteLLM provider
  • Python / JavaScript / Shell / AppleScript runtimes
  • Jupyter notebooks (can generate and run cells)
  • Any file format your system can process
  • macOS / Linux / Windows
🙏

Source et remerciements

Thanks to Killian Lucas and the Open Interpreter team for creating the most intuitive way to control your computer with natural language, bridging the gap between AI and real-world computing tasks.

Discussion

Connectez-vous pour rejoindre la discussion.
Aucun commentaire pour l'instant. Soyez le premier à partager votre avis.