Ray is a unified framework for scaling Python and AI applications from a laptop to a cluster, with a distributed runtime and AI libraries.
modal-labs/modal-client
Official SDKs for Modal, a serverless cloud platform for running Python code, Sandboxes and deployed functions.
- Stars
- 527
- Forks
- 138
- Open issues
- 33
- Last commit
- 14 hours ago
What is it?
This repository holds the source code for the official Modal SDKs. The Python package is the main one: it lets you deploy serverless applications to Modal and interact with the platform from code, and it ships the `modal` command-line tool. The JavaScript/TypeScript and Go SDKs focus on using Modal Sandboxes, invoking deployed Modal Functions, and working with some platform resources.
The SDKs are aimed at developers who want to run workloads such as AI model inference, data processing or batch jobs on cloud infrastructure without managing servers. The Python package is installed with uv or pip, and the CLI can also be installed as a standalone tool.
The repository also provides an official skill for coding agents, which can be installed through the `modal` CLI or via `npx skills`.
Key features
- 01Deploy Python serverless applications to Modal from code.
- 02Ships the `modal` CLI, installable with uv or pip.
- 03JavaScript/TypeScript and Go SDKs for Sandboxes and invoking deployed Functions.
- 04Official skill for coding agents, with version-aligned docs when installed via the CLI.
Use cases
- Running AI model inference or GPU workloads on serverless cloud infrastructure.
- Launching isolated Sandboxes from a Node.js or Go service.
- Calling deployed Modal Functions from an existing application.
Quick start
- 1
Install the Python SDK and CLI with uv
uv pip install modal - 2
Or install the standalone modal CLI using the official install script from the README
Topics
FAQ
- What is modal-client?
- Official SDKs for Modal, a serverless cloud platform for running Python code, Sandboxes and deployed functions. This repository holds the source code for the official Modal SDKs. The Python package is the main one: it lets you deploy serverless applications to Modal and interact with the platform from code, and it ships the `modal` command-line tool. The JavaScript/TypeScript and Go SDKs focus on using Modal Sandboxes, invoking deployed Modal Functions, and working with some platform resources.
- Is modal-client free to use? What license does it have?
- modal-client is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is modal-client still maintained?
- Actively maintained. The last commit to modal-client was on Oct 21, 2026.
- What can I use modal-client for?
- Running AI model inference or GPU workloads on serverless cloud infrastructure. Launching isolated Sandboxes from a Node.js or Go service. Calling deployed Modal Functions from an existing application.
- How do I install modal-client?
- Install the Python SDK and CLI with uv: uv pip install modal Or install the standalone modal CLI using the official install script from the README
- Where can I get modal-client?
- The source code and installation instructions are on GitHub: https://github.com/modal-labs/modal-client
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open-source Go and Python runtime for serverless AI workloads, covering GPU inference endpoints, sandboxes, and background tasks.
Open-source infrastructure for running AI-generated code in isolated cloud sandboxes, with JavaScript and Python SDKs.
A runtime interface that lets AI agents run shell commands in sandboxed environments, locally or on cloud platforms like Docker, AWS, and Modal.
An LLM agent framework from Microsoft that automates data-driven R&D tasks such as reading papers, implementing models and factors, and running Kaggle-style experiments.
An end-to-end open source platform for building and deploying machine learning models, with Python and C++ APIs.