Gaunt Sloth

AI-powered assistant

Practical AI for code review, CI/CD workflows, and DIY builds

A configurable CLI for reviews,
pipelines, chat, and hands-on DIY project work.

Who loves GSloth?

Software developers
DIY enthusiasts

When use GSloth?

When you need to review pull request with context focused on this PR, guideline and it's requirements.
When you want quickly connect to MCP server via Terminal (supports OAuth).
Make GSloth generate some code from command line when use of full IDE is not appropriate.
Chat with GSloth to call some functions.
Run it from build pipeline, for example GitHub Actions.

What GSloth does?

Reviews code
Suggests bug fixes
Explains provided code
Reviews Diffs provided with pipe (|)
You can ask GSloth to review your own code before committing (git --no-pager diff | gsloth review)
Reviews Pull Requests (PRs) (gsloth pr 42)
Fetches descriptions (requirements) from Github issue or Jira (gsloth pr 42 12)
Answers questions about provided code
Writes code
Connects to MCP server (including remote MCP with OAuth)
Saves all responses in .md file in the project directory
Logs time spended into timesheets (in two different ways: via MCP and static way)
Anything else you need, when combined with other command line tools

Why GSloth?

Features

There are many Open Source command line AI assistants available; there are great non-open source options such as Claude Code. Gaunt Sloth does not intend to be your "Daily Driver" and is not aiming to replace your Cursor. What it promises is that it is small, extendable, cross-platform and can itself be a dependency in your project. The GSloth was initially built as a code review tool, fetching PR contents and Jira contents before feeding them to the LLM, but we ourselves found many more use cases which we initially did not anticipate; for example, we may have it as a dependency in an MCP project, allowing us to quickly spin it up to simulate or test some use cases.

Commands Overview

To make GSloth work,

you need an API key from some AI provider, such as:

OpenRouter
Groq
DeepSeek
Google AI Studio and Google Vertex AI
Anthropic
OpenAI (and other providers using OpenAI format, such as Inception)
Ollama with JS config (some of the models, see #107 )
xAI

* Any other provider supported by LangChain.JS should also work with JS config .

The promise of Gaunt Sloth:

Minimum dependencies. Ideally, we aim to only have CommanderJS and some packages from LangChainJS and LangGraphJS.
Extensibility. Feel free to write some JS and create your Tool, Provider or connect to the MCP server of your choice.
No vendor lock-in. Just BYO API keys.
Easy installation via NPM.
All prompts are editable via markdown files.
No UI. Command Line only, with intent to be used in build pipeline, or as a dependency to help in nodejs projects.