open-interpreter
Let language models run code
Decision gist · record as of 2026-08-14
Yes, with conditions. Install if you want a natural-language interface to local code execution and can accept the security model (user approval before each command). However, the package is dormant (no releases in 657 days), carries an unclear license, and depends on 32 libraries—audit the license and dependencies before use in production or proprietary work. Not suitable if you need active maintenance or a stable, well-documented API.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires Python 3.9 or later.
- An LLM API key (OpenAI, Claude, or compatible local server) must be configured; the package does not work offline without additional setup.
- Low install friction with a pure-Python wheel.
License · maintenance · safety
(unclear) — License treatment is unclear—no SPDX identifier or raw license text is available in the metadata. Verify the actual license before using in proprietary or commercial contexts.
last release 2024-10-26 (657 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 222,360 downloads/mo, #9,265 on PyPI
Alternatives
Verify before relying
pip install open-interpreter
from interpreter import interpreter
interpreter.chat("Plot AAPL and META's normalized stock prices")- Whether dormant status (657 days since release) indicates active maintenance or abandonment
- Actual license identifier and terms (metadata shows 'unclear')
- Security implications of 32 runtime dependencies, especially selenium and webdriver-manager
- Whether all 32 dependencies are truly required at runtime or if some are optional
What it is and what it does
Open Interpreter is a Python package that bridges language models and your local machine by letting an LLM write and execute code (Python, JavaScript, Shell, and more) in response to natural-language requests. You interact with it through a ChatGPT-like terminal interface or programmatically via Python; before any code runs, you must approve it. This gives an LLM access to your computer's general capabilities—file manipulation, browser automation via Chrome, data analysis, image and video editing—without uploading data to a hosted service.
The package depends on 32 runtime libraries including nltk, pydantic, litellm (for multi-LLM support), selenium and webdriver-manager (for browser control), matplotlib (for plotting), and jupyter-client (for code execution). It supports Python 3.9 through 3.12 and can run against OpenAI, Anthropic, or any OpenAI-compatible local inference server. The main trade-off is that you grant the LLM significant local execution privileges, mitigated only by the approval step.
Use it for
- Automate data cleaning and analysis by describing the task in natural language instead of writing Python
- Control a web browser to scrape, research, or fill forms without writing Selenium code directly
- Generate and edit media files (photos, videos, PDFs) by describing the desired output
- Prototype and debug code interactively by chatting with an LLM that can run and iterate on your scripts
- Run computationally intensive tasks locally without uploading sensitive data to a cloud API
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, with conditions.
Install if you want a natural-language interface to local code execution and can accept the security model (user approval before each command). However, the package is dormant (no releases in 657 days), carries an unclear license, and depends on 32 libraries—audit the license and dependencies before use in production or proprietary work. Not suitable if you need active maintenance or a stable, well-documented API.
Install
open-interpreter on PyPI
Before you install
Low install friction with a pure-Python wheel. The package is dormant (657 days since last release) and carries 32 runtime dependencies including heavy libraries like selenium, matplotlib, and jupyter-client, which may slow initial setup and increase the attack surface.
Requires Python 3.9 or later. An LLM API key (OpenAI, Claude, or compatible local server) must be configured; the package does not work offline without additional setup.
License in practice
License treatment is unclear—no SPDX identifier or raw license text is available in the metadata. Verify the actual license before using in proprietary or commercial contexts.
Quickstart
pip install open-interpreter
from interpreter import interpreter
interpreter.chat("Plot AAPL and META's normalized stock prices")Verify before relying
- Whether dormant status (657 days since release) indicates active maintenance or abandonment
- Actual license identifier and terms (metadata shows 'unclear')
- Security implications of 32 runtime dependencies, especially selenium and webdriver-manager
- Whether all 32 dependencies are truly required at runtime or if some are optional
Package facts
| License | Not declared unclear |
| Python support | Supports the current Python release <4,>=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 32 packagesnltksetuptoolsastorgit-pythoninquirerpyyamlrichsixtokentrimwgetpsutilpyreadline3html2imagesend2trashipykerneljupyter-clientmatplotlibtomltiktokenplatformdirspydanticgoogle-generativeaipyperclipyaspinshortuuidlitellmstarlettehtml2textseleniumwebdriver-manager |
| Maintenance | Dormant 657 days since the last release |
| First released | |
| Downloads | 222,360 / month, #9,265 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Programming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.9 |
Evidence: open_interpreter-0.4.3-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “llm code execution local”
- open-interpreterOpen Interpreter lets language models execute code (Python,…
- npmai-agentsAutonomous AI agent framework that executes plain-English tasks…
- e2b-code-interpreterRuns AI-generated or arbitrary Python code in isolated cloud…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also llama-index-llms-openai · llm · regopy · lmstudio · unclecode-litellm · open-webui · litellm-enterprise · ollama · pandasai