Modal review

Q: Is Modal free and open source?

Yes. Modal's source code is on GitHub (modal-labs/modal-client) under the Apache 2.0 license, so you can use it for free. Its website also links to a pricing page (https://modal.com/pricing) for any paid plans.

Q: How do I install Modal?

Run uv pip install modal. The modal package needs Python 3.10 or newer, below 3.16. The install section above has the other options from the project's README.

Q: Is Modal still maintained?

Yes. The modal-labs/modal-client repository was last updated on Oct 21, 2026, and the latest release, modal 1.6.2 on PyPI, came out on Oct 16, 2026.

Q: How popular is Modal?

Modal has 531 GitHub stars as of Nov 1, 2026. It gained 3 new stars in the week of Oct 25–31, 2026, against a 12-week average of 3 a week. Its main package had 11.1M downloads that week, +2% against its own 4-week average. That made it #10 among AI sandboxes and runtimes on the Devtoolwatch Board.

Q: What are the best alternatives to Modal?

Other AI sandboxes and runtimes on the Devtoolwatch Board in the week of Oct 25–31, 2026, by momentum: OpenSandbox (#1), microsandbox (#2), E2B (#3), Agent Sandbox (#4), Trigger.dev (#5). The alternatives table above has their numbers.

Q: What is Modal used for?

Modal is used to run compute-intensive code in a serverless cloud. Its documentation names generative AI models, large-scale batch workflows, job queues, LLM serving, and coding agents in Sandboxes as use cases.

Q: Which languages does Modal support?

Modal has official SDKs for Python, JavaScript/TypeScript, and Go. The Python SDK deploys applications. The JS and Go SDKs use Sandboxes, invoke deployed Functions, and interact with some platform resources.

Q: How do I get support for Modal?

Modal's README directs usage questions and other support requests to the Modal Slack community. The online documentation includes a user guide and example applications.

Q: Can coding agents use Modal?

Yes. Modal distributes an official skill for coding agents. Install it with modal skills install to get version-aligned reference documentation.

Modal is a serverless cloud platform with official Python, JavaScript/TypeScript, and Go SDKs for running compute-intensive code and AI workloads.

Updated Nov 1, 2026. Review written Oct 22, 2026 from the project's own sources; usage data refreshed every Monday.

TL;DR

Modal is a serverless cloud for engineers and researchers who want to build compute-intensive applications without managing infrastructure. Its Python SDK deploys serverless applications, and its JS and Go SDKs work with Sandboxes and deployed Functions. Modal also ships an official skill that helps coding agents use its features.

531GitHub stars
+3new stars, week of Oct 25
11.1Mdownloads a week, +2% vs 4-week avg
#10in Sandboxes and runtimes this week

Modal at a glance

Category: Sandboxes and runtimes
Maintained by: Modal Labs (organization, @modal-labs on GitHub)
License: Apache 2.0
Language: Python, Go, TypeScript
Repository: github.com/modal-labs/modal-client
Website: modal.com/docs
PyPI package: modal 1.6.2
Latest release: modal 1.6.2 on PyPI, Oct 16, 2026
First published: Oct 18, 2022

What Modal does

Modal's Python SDK deploys serverless applications and lets you interact with the Modal platform programmatically.
Modal runs generative AI models, large-scale batch workflows, and job queues in its serverless cloud.
Modal's JavaScript/TypeScript and Go SDKs use Modal Sandboxes, invoke deployed Modal Functions, and interact with some platform resources.
Modal Sandboxes can run coding agents at scale, according to the featured examples.
Modal's documentation includes examples for serving an OpenAI-compatible LLM service.
Modal includes a `modal` CLI with the Python package. The CLI also installs an official skill for coding agents.

How it works

Modal is used through its SDKs and CLI. You install the Python package, which includes the `modal` CLI, and write code that deploys to Modal's serverless cloud. JS and Go SDKs connect to Sandboxes and deployed Functions. A Playground lets you run serverless cloud functions from the browser.

How to install and start using Modal

With uv

uv pip install modal

Standalone CLI

curl -LsSf uvx.sh/modal/install.sh | sh

Agent skill via npx

npx skills add modal-labs/modal-client

Requirements

Python >=3.10 and <3.16 for the Python SDK.
A Modal account. The documentation site offers sign-up and log-in.

First steps

Install the Python package with `uv pip install modal`. The package includes the `modal` CLI.
Sign up for a Modal account from the documentation site.
Follow the user guide or try the interactive Playground tutorials to run your first serverless function.
Optionally run `modal skills install` to give coding agents version-aligned Modal documentation.

Who Modal is for

Engineers and researchers building compute-intensive applications without managing infrastructure.
Teams serving LLMs, diffusion models, or batch inference workloads.
Developers running AI coding agents in isolated Sandboxes at scale.

Limitations to know

Modal's JS and Go SDKs cover Sandboxes, Function invocation, and only some platform resources. Deploying applications is described for the Python SDK.
Modal's skill installed via `npx skills` does not include versioning or reference documentation.
Modal runs code on its own hosted cloud platform, so you need a Modal account to use it.

Is Modal growing? Usage data

In the week of Oct 25–31, 2026, Modal ranked #281 on the Devtoolwatch Board and #10 in Sandboxes and runtimes, with a momentum score of 34 out of 100. Its main package had 11.1M downloads that week, +2% against its own 4-week average.

New GitHub stars per week for the last 12 weeks, from GitHub's stargazer history (today's stargazers by the week they starred).

Show the weekly numbers

New GitHub stars per week for Modal
Week of	New stars
Aug 9, 2026	4
Aug 16, 2026	6
Aug 23, 2026	2
Aug 30, 2026	3
Sep 6, 2026	2
Sep 13, 2026	1
Sep 20, 2026	4
Sep 27, 2026	5
Oct 4, 2026	1
Oct 11, 2026	2
Oct 18, 2026	3
Oct 25, 2026	3

On Hacker News

DoppelBot: Replace Your CEO with an LLM, 232 points and 117 comments (Feb 4, 2025)
The Missing Nvidia GPU Glossary, 230 points and 70 comments (Jan 12, 2025)
'I paid for the whole GPU, I am going to use the whole GPU', 154 points and 45 comments (May 7, 2025)
Keeping 20k GPUs healthy, 134 points and 62 comments (Jan 18, 2026)
We reverse-engineered Flash Attention 4, 134 points and 48 comments (Sep 27, 2025)

The Board ranks tools by four signals each week: new stars, new stars for the repo's size, added downloads and download growth beyond the market. How the ranking works.

Modal alternatives

Other AI sandboxes and runtimes on the Board in the week of Oct 25–31, 2026, by momentum:

Sandboxes and runtimes ranked by momentum, the week of Oct 25–31, 2026
Rank	Tool	Stars	Downloads/wk
#1	OpenSandboxOpenSandbox is a sandbox runtime that gives AI agents isolated environments to run code, commands, files, browsers, and desktops on your…	16.3k	328.9k
#2	microsandboxmicrosandbox is a local-first microVM runtime and library for running untrusted workloads like AI agents, user code, and CI jobs in…	8.9k	26.8k
#3	E2BE2B is open-source infrastructure for running AI-generated code in secure, isolated cloud sandboxes, controlled through JavaScript and…	14.6k	5M
#4	Agent Sandboxagent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes and…	4.5k	–
#5	Trigger.devTrigger.dev is an open-source TypeScript platform for building and deploying durable AI agents, workflows, and long-running background…	16.7k	1.7M
#6	InngestInngest is a workflow orchestration platform for running durable step functions, background jobs, and AI workflows on serverless,…	6k	3.7M

All AI sandboxes and runtimes, ranked

Modal FAQ

Is Modal free and open source?

Yes. Modal's source code is on GitHub (modal-labs/modal-client) under the Apache 2.0 license, so you can use it for free. Its website also links to a pricing page (https://modal.com/pricing) for any paid plans.

How do I install Modal?

Run uv pip install modal. The modal package needs Python 3.10 or newer, below 3.16. The install section above has the other options from the project's README.

Is Modal still maintained?

Yes. The modal-labs/modal-client repository was last updated on Oct 21, 2026, and the latest release, modal 1.6.2 on PyPI, came out on Oct 16, 2026.

How popular is Modal?

Modal has 531 GitHub stars as of Nov 1, 2026. It gained 3 new stars in the week of Oct 25–31, 2026, against a 12-week average of 3 a week. Its main package had 11.1M downloads that week, +2% against its own 4-week average. That made it #10 among AI sandboxes and runtimes on the Devtoolwatch Board.

What are the best alternatives to Modal?

Other AI sandboxes and runtimes on the Devtoolwatch Board in the week of Oct 25–31, 2026, by momentum: OpenSandbox (#1), microsandbox (#2), E2B (#3), Agent Sandbox (#4), Trigger.dev (#5). The alternatives table above has their numbers.

What is Modal used for?

Modal is used to run compute-intensive code in a serverless cloud. Its documentation names generative AI models, large-scale batch workflows, job queues, LLM serving, and coding agents in Sandboxes as use cases.

Which languages does Modal support?

Modal has official SDKs for Python, JavaScript/TypeScript, and Go. The Python SDK deploys applications. The JS and Go SDKs use Sandboxes, invoke deployed Functions, and interact with some platform resources.

How do I get support for Modal?

Modal's README directs usage questions and other support requests to the Modal Slack community. The online documentation includes a user guide and example applications.

Can coding agents use Modal?

Yes. Modal distributes an official skill for coding agents. Install it with modal skills install to get version-aligned reference documentation.

Sources

Modal README badge

Maintainers can show the tool's weekly Board rank in their README:

[![Devtoolwatch](https://index.devtoolwatch.com/badge/modal.svg)](https://index.devtoolwatch.com/tools/modal/)

How this page is made: Devtoolwatch writes each review from the project's README, releases, package metadata and website, with an AI model, then checks every claim against the source it cites and drops what the sources don't support. The numbers come from Devtoolwatch's daily GitHub snapshots, GitHub's stargazer history, and the npm and PyPI download APIs. Spotted an error? Email [email protected].