DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to use Benzi: what you can do with it

What is Benzi? Benzi is a compiler that parses a codebase into a queryable map of calls, data flow, control flow and class hierarchy, which coding agents then use to read, explain, run, edit and verify code.

How do I use it? Run pip install benzi; then run benzi-login --login [email protected], then type the one-time code emailed to you; run claude mcp add --scope user benzi -- benzi-mcp to register the server with Claude Code. Full steps below.

Trended earlier

View repo on GitHub

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer

What do you want to do?

4 use cases

  • Answer questions about a repo inside Claude Code

    Give Claude Code a compiled map of your repo so it answers callers, hierarchy and definition questions from the index.

    View prompt
    Using the Benzi MCP tools on the repo at <repo path>, list every call site that reaches the function <function name> and the resolved base classes of <class name>. Expected output: a list of caller locations and a hierarchy list. Verify that each listed location exists in the file it names.

  • Trace a wrong value back to where it came from

    Use Benzi's backflow and trace_path tools to find the origin of a bad value without opening every caller.

    View prompt
    In the repo at <repo path>, use Benzi to trace where the wrong value in <symptom or variable name> originates. Expected output: the origin file and line plus the call chain that carried the value. Verify the origin by checking that the cited line produces the value when the repro runs.

  • Run a headless Benzi fix on a failing test

    Run benzi-headless from a terminal or CI job to attempt a fix, with syntax-checked edits and one-step rollback.

    View prompt
    Run `benzi-headless . "fix the failing test in <test file>"` in the repo at <repo path>. Expected output: edited files plus a summary of the change. Verify by running the test suite and confirming the target test passes and no other test newly fails.

  • Build a new app from scratch in one VS Code session

    Use the Benzi VS Code extension to greenfield a project through a single chat session.

    View prompt
    In VS Code with Benzi running on an empty folder at <project path>, ask Benzi to build <short app description>. Expected output: a project with frontend, backend and any prompt files. Verify by running the app locally and checking that the main flow works end to end.

Quick start with Benzi

  1. Check you have what it needs: Python 3.11 to 3.14 on Windows, macOS or Linux, for the pip install; An email address for the one-time login code; An API key from Anthropic or a non-Anthropic provider (DeepSeek, Groq, Kimi and others) for the Benzi agent, or an existing MCP-capable agent such as Claude Code or Cursor for the MCP server.
  2. Open oooscoos/Benzi on GitHub and read the README and license.
  3. Run pip install benzi.
  4. Run benzi-login --login [email protected], then type the one-time code emailed to you.
  5. Run claude mcp add --scope user benzi -- benzi-mcp to register the server with Claude Code.
  6. Open Claude Code in your repo folder and ask it who calls a function you name, for example which call sites reach a given function.

These steps come from our top use case, Answer questions about a repo inside Claude Code, which also has a copy-paste agent prompt.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for oooscoos/Benzi

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Benzi alternatives · Best AI repos for Software and DevOps

About this repo

  • Who it is forDevelopers and teams who use coding agents on real repos and want the agent to answer from a precise code map instead of grepped source, with Benzi free to use during beta.
  • Why it is hot170 stars, launched 89 days ago
  • LanguageHTML
  • Sourcegithub.com/oooscoos/Benzi · Back to Hot repos

Requirements

  • Python 3.11 to 3.14 on Windows, macOS or Linux, for the pip install
  • An email address for the one-time login code
  • An API key from Anthropic or a non-Anthropic provider (DeepSeek, Groq, Kimi and others) for the Benzi agent, or an existing MCP-capable agent such as Claude Code or Cursor for the MCP server

Add this badge to your README

Maintain Benzi? Show readers where to find these use cases. Use cases on Deduped

Markdown 

[![Use cases on Deduped](https://dedupedai.com/badge/oooscoos/Benzi.svg)](https://dedupedai.com/use-cases/oooscoos-benzi/?utm_source=github&utm_medium=badge&utm_campaign=oooscoos-Benzi)

HTML 

<a href="https://dedupedai.com/use-cases/oooscoos-benzi/?utm_source=github&amp;utm_medium=badge&amp;utm_campaign=oooscoos-Benzi"><img src="https://dedupedai.com/badge/oooscoos/Benzi.svg" alt="Use cases on Deduped" height="20"></a>

A static image, no tracking script. About the badge

Questions about Benzi

What is Benzi?

Benzi is a compiler that parses a codebase into a queryable map of calls, data flow, control flow and class hierarchy, which coding agents then use to read, explain, run, edit and verify code. It is an open-source project on GitHub: https://github.com/oooscoos/Benzi.

How do I use Benzi?

Run pip install benzi; then run benzi-login --login [email protected], then type the one-time code emailed to you; run claude mcp add --scope user benzi -- benzi-mcp to register the server with Claude Code. The use cases on this page give the full steps and a copy-paste agent prompt for each job.

Who is Benzi for?

Developers and teams who use coding agents on real repos and want the agent to answer from a precise code map instead of grepped source, with Benzi free to use during beta.

What can I do with Benzi?

4 use cases so far, for example: Answer questions about a repo inside Claude Code; Trace a wrong value back to where it came from; Run a headless Benzi fix on a failing test. Each has steps and a copy-paste agent prompt.

What do I need to run Benzi?

Python 3.11 to 3.14 on Windows, macOS or Linux, for the pip install; An email address for the one-time login code; An API key from Anthropic or a non-Anthropic provider (DeepSeek, Groq, Kimi and others) for the Benzi agent, or an existing MCP-capable agent such as Claude Code or Cursor for the MCP server.

What are alternatives to Benzi?

Other hot AI repos in Software and DevOps: Deep Infer, Harness2, Orca, Opencode, Graphify.

Is Benzi safe to run?

Deduped does not own, audit or vouch for it. Read the README and license, run it on your own systems first and review every command before you run it.