Skip to main content

SassyShell (sassysh)

PyPI version Downloads Build Status Python Version License Hacktoberfest

Your sassy, command-line tutor that remembers the commands you keep forgetting.


Why I Built This

Like a lot of developers, I found myself constantly switching contexts to ask an LLM for the same simple shell commands over and over. tar flags, find syntax, awk one-liners... I wasn't learning them, I was just outsourcing my memory. It felt like a bad habit.

Instead of just trying to memorize everything, I thought: what if a tool could track my bad habits and help me internalize the patterns?

So, I built SassyShell. It's not just another "GPT in the terminal." It's a CLI sidekick that:

  1. Uses a local TF-IDF search to find similar commands you've asked for in the past.
  2. Feeds that history to an LLM to provide context-aware answers.
  3. Gives you the command you need, along with a bit of sarcastic feedback based on how often you forget it.

It's a project born from turning my own laziness into data. It's designed to mock you into getting better.

Features

  • Personalized Memory: Remembers the types of commands you struggle with and uses that history to inform its responses.
  • Sassy Feedback: The more you ask for the same thing, the more it will gently (or not so gently) remind you.
  • Platform Aware: Automatically detects if you're on Linux, macOS, or Windows and asks the LLM for the correct shell syntax (bash/zsh vs. PowerShell).
  • Lightweight & Fast: Uses a fast local similarity search before ever calling an LLM.
Sassyshell Demo

Installation

The recommended way to install SassyShell is with pipx or uvx. This installs it in an isolated environment so it doesn't clutter your global packages.

pipx install sassyshell

You can install pipx using:

pip install --user pipx

Or, if you use uvx:

uvx sassyshell

Quickstart

1. One-Time Setup

Before you can use the tool, you need to run the setup wizard to configure your LLM provider and API key. Your credentials are saved locally in ~/.config/sassyshell/.env.

sassysh setup

You'll be guided through selecting a provider (OpenAI, Google, etc.) and entering your API key.

2. Ask a Question

Use the ask command to ask for help.

sassysh ask "how to find all files modified in the last 24 hours"

Example Interaction:

$ sassysh ask "how to add changes to my last git commit without a new one"

Looks like you're having trouble with your Git commits again! You can add your new changes using:

git commit --amend --no-edit

Contributing

We welcome contributions! Please read our CONTRIBUTING.md guide to get started. It covers setup, development, and how to submit changes.

License

This project is licensed under the MIT License.

Metadata

Release files for sassyshell 0.1.6

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for sassyshell 0.1.6
File Size Uploaded Provenance Actions
sassyshell-0.1.6.tar.gz 10.2 kB With provenance Details for sassyshell-0.1.6.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for sassyshell 0.1.6
File Interpreter ABI Platform Actions
sassyshell-0.1.6-py3-none-any.whl Python 3 none any Details for sassyshell-0.1.6-py3-none-any.whl

Total release size: 20.1 kB

Release files / sassyshell-0.1.6.tar.gz

Download URL sassyshell-0.1.6.tar.gz
Size 10.2 kB
Tags Source
SHA-256 checksum
How to use checksums
4d237250220e24d0ed1f01e5886135c7deccb10022ac9d9fad93e8e73258c8e8
BLAKE2b-256 checksum
How to use checksums
2c550b79db688954dd6889334cc492b4d83df0aa2c656e9bb9114838389978f0
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 21, 2025.

Transparency log

Release files / sassyshell-0.1.6-py3-none-any.whl

Download URL sassyshell-0.1.6-py3-none-any.whl
Size 9.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
cd903dacac3ab458da1007506e5267b656342eb25f74c4613b2d9ae36ce3890d
BLAKE2b-256 checksum
How to use checksums
93c0e84c6fbe606f6ffcb2ae7ab3dc8359fe62e547bf86ca01c6e6601b605d14
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.1.0 CPython/3.13.7

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 21, 2025.

Transparency log

Security for sassyshell 0.1.6

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

Both files in this release have been uploaded with provenance metadata.

Select from 2 files

Attestation for sassyshell-0.1.6.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Oct 21, 2025.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page