Back to directory

Slopo

A command-line tool that uses code-embedding models to find near-duplicate implementations across a codebase, catching similar-but-not-identical logic that coding agents and reviewers tend to miss.

Slopo

Slopo uses embedding models, the kind normally used to match differently worded text with similar meaning, applied instead to source code, to find the hardest-to-detect kind of duplication: a different implementation of the same logic rather than copy-pasted code. It can compare a recent set of Git changes against the rest of the codebase, or analyze an entire codebase at once, and supports Python, TypeScript, TSX, JavaScript, Java, Kotlin, C, C++, C#, Go, Rust, PHP, Elixir, Ruby, and Swift.

The problem grows with scale: a coding agent working on a small, well-organized change can usually spot related code through references and naming, but on a large change in a messy codebase it is more likely to reimplement something that already exists. Feeding an agent a report of already-found duplicates ahead of time avoids spending its own tokens rediscovering them.

It is a command-line tool written in Python.

More in Code quality

See all 94
  • Critic

    critic.run

    A code-change viewer, backed by Y Combinator, built for reviewing work written by coding agents, presenting a plain-language narrative of each change alongside the diff and a running conversation with the agent.

  • GitIntel

    hoangsonww.github.io

    An MCP server that computes git repository analytics such as hotspots, churn, temporal coupling, knowledge maps and risk scoring entirely from local commit history, for AI coding agents like Claude Code and Codex.

  • Axint

    axint.ai

    A verification layer for AI coding agents working on Apple projects: it runs real Xcode builds and tests against the Swift an agent wrote, reconciles static analysis findings against that evidence, and returns a signed proof with the exact repairs still needed.