Open Interpreter
Let language models run code on your computer from a terminal.
Overview
Open Interpreter gives an LLM a code-execution environment on your machine, letting it accomplish tasks by writing and running Python, shell and JavaScript. It works with your own API keys or local models via LiteLLM.
- Local code execution
- Natural-language computer control
- Safe mode
- Local model support
Our verdict
What we like
- Powerful automation from chat
- Model-agnostic
Watch out for
- Running generated code carries risk
Works with these providers
Keys from these providers work in this app. Usage is billed by the provider at its list price.
BYOK Key Safety Score
Key handling in Open Interpreter
Grade A
Your key is stored on your device and requests go directly to the provider.
- Key storage40/40
Key stays on your device; requests go direct to the provider.
- Auditable code25/25
Open source: anyone can verify how keys are handled.
- Self-hosting8/15
Runs as a local app, but not as a self-hosted service.
- Offline option10/10
Supports local models, so no key is needed at all for private work.
- Provider choice10/10
9 provider options, which lets you pick the provider whose data terms you trust.
Whatever the score, give each app its own key, set a monthly spend limit with your provider, and revoke keys you no longer use. Read the key-safety checklist.
Open Interpreter FAQ
- Does Open Interpreter support bring your own key?
- Yes. Open Interpreter accepts your own API key from OpenAI, Anthropic, Google Gemini, OpenRouter, Groq, Ollama, LM Studio, Azure OpenAI and OpenAI-compatible. Usage is billed by the provider at its API rates.
- Where does Open Interpreter store my API key?
- On your device. Requests go directly from Open Interpreter to the provider. Its BYOK Tools Key Safety Score is 93/100.
- Is Open Interpreter free?
- Open source: Free & open source. API usage is billed separately by your model provider.
- Is Open Interpreter open source?
- Yes. The source code is at https://github.com/openinterpreter/open-interpreter.
- Can Open Interpreter run local models?
- Yes. It can connect to local runtimes such as Ollama or LM Studio, so no API key is needed for private or offline use.
- Which platforms does Open Interpreter support?
- CLI, macOS, Windows, Linux.
Community reviews
No reviews yet.
Alternatives to Open Interpreter
All command line →Fabric
Command Line
Open-source framework of crowdsourced AI prompts for the CLI.
AIChat
Command Line
All-in-one LLM CLI with chat REPL, RAG, agents and a local server.
LLM (Simon Willison)
Command Line
CLI and Python library for interacting with any LLM.
gptme
Command Line
Personal AI agent in your terminal with code execution.
Mods
Command Line
AI on the command line from Charm, built for pipelines.
Wave Terminal
Command Line
Open-source terminal with inline AI chat and graphical widgets.