Model Hubs & Serving

Sequitur

PyTorch library for sequence autoencoders in two lines of code

Status
UnmaintainedNo commits in 917 days.
Last checked
Aging · Sep 3, 2026
License
Open source
Pricing
Free tier · from $0
Visit Sequitur Compare with alternatives

What it is

Sequitur is a PyTorch-based library that simplifies the creation and training of sequence autoencoders, enabling developers to implement these models with minimal effort.

Sequitur stands out for its simplicity and ease of use in creating sequence autoencoders, making it ideal for rapid prototyping without sacrificing performance.

When it fits — and when it doesn’t

A good fit for

  • Researchers and developers who need to quickly prototype sequence autoencoder models

  • Teams working on time-series analysis that require efficient model training processes

Look elsewhere if

  • Projects requiring real-time inference with low latency requirements

  • Applications needing extensive customization beyond the provided library features

Known weaknesses

Each one links to the public issue, changelog or docs page it came from, where we have one.

  1. 01

    Limited integrations with other frameworks and tools

    Sequitur is tightly coupled with PyTorch, making integration with TensorFlow or other ML libraries difficult

  2. 02

    Small community and limited support

    GitHub issues are not always promptly addressed by maintainers; sparse documentation examples

What it does well

  • Simplifies sequence autoencoder creation with minimal code

  • Built on PyTorch, leveraging its ecosystem and performance

  • Open-source under MIT license

Pricing

Free tier
YesOpen source — free to use
Paid from
$0
Model
Flat rate
Enterprise plan
No

Pricing not independently confirmed — check the vendor’s page.

Performance benchmarks

How Fast Is It?

Set up Sequitur

Setup steps, common gotchas and what to check after 30 days.

Open the setup guide →