slopo
The missing piece in AI‑assisted development
Open-source CLI tool for detecting non-exact code duplication separated across the codebase. A kind of problem frequently introduced by AI agents and difficult for them to detect.
How detection works
It uses embedding models for semantic code duplication detection, surfacing similar code that's written differently. Distance in the codebase influences the final score. The further away similar code is, the higher its priority.
Supported languages
Python, TypeScript, JavaScript, Java, Kotlin, C#, Go, Rust
Installation
This command uses uv (installing uv), a Python package manager, to install Slopo from PyPI in an isolated virtual environment. No need to get Python separately.
Why agents need help here
Source of duplication
Without rigor, a clear architecture design, and a specification available to it, an AI agent tends to implement logic that already exists elsewhere. It isn't a copy of the code, it's a new implementation of the same solution.
Why it hurts
Duplicated code confuses AI, making it less reliable when deciding where to add new related logic or which existing code to edit. It may update one copy while the others drift out of sync. This problem isn't unique to AI, but AI creates chaos faster than humans do.
The blind spot
AI agents struggle with one specific kind of duplicate. They can find shared names, trace how code is called and referenced, or reason about the part of the system they are working in. But they can't load the whole codebase into context at once, so they miss distant functions that do the same thing in a different form.
Slopo works with your agent
Before involving your agent, exclude obvious noise like test files.
Filter out non-duplicates
Not every code duplication is unwanted, and not all semantically similar code is a duplicate. They make up much of your early results but are easily filtered out by your AI agent. Once added to the ignore list, they won't reappear until the related code changes.
Let your agent refactor
Once the results are clear of the duplicates we don't want to act on, we can focus on the actual fixes. Now an AI agent can look deeper into a single group of similar code, assess it again, and analyze its scope and impact. With more information, we can decide to refactor the group or skip it.
Documentation
Full documentation is on GitHub, with installation, configuration options, and detailed usage.