Open Interpreter is an open-source tool that provides a natural-language interface for interacting with your computer. It lets large language models (LLMs) run code locally (Python, JavaScript, shell, etc.), enabling you to ask your computer to do tasks like data analysis, file manipulation, browsing, etc. in human terms (“chat with your computer”), with safeguards. Runs locally or via configured remote LLM servers/inference backends, giving flexibility to use models you trust or have locally. It prompts you to approve code before executing, and supports both online LLM models and local inference servers. It seeks to combine convenience (like ChatGPT’s code interpreter) with control and flexibility by running on your own machine.
Features
- Supports command-execution in multiple languages (Python, JavaScript, Shell etc.) via natural language instructions
- Runs locally or via configured remote LLM servers / inference backends, giving flexibility to use models you trust or have locally
- Chat-style interface from terminal; history of messages; ability to stream outputs or interactively approve actions
- Ability to handle media / files: create or edit PDFs, videos, images; data plotting, cleaning, analysis etcetera
- Supports optional voice interface, experimental “safe mode” to limit risk, confirmation prompts before executing potentially unsafe actions
- Profiles / configuration (yaml) to adjust behavior (which model, auto-run, context windows etc.), and ability to run via different environments (local, remote, Android via Termux etc.)