gitwtfhub

wtf is nowreck?

astralxvoid/nowreck — explained in plain English

Analysis updated 2026-05-18

1PythonAudience · developerComplexity · 2/5Setup · moderate

TL;DR

A command line tool that checks whether an AI coding assistant's description of a code change matches what actually happened in the code, using structural analysis instead of another AI's opinion.

Mindmap

mindmap
  root((repo))
    What it does
      Verifies AI claims
      Compares diff to explanation
      Flags contradictions
    Tech stack
      Python
      AST parsing
    Use cases
      Pre merge checks
      CI verification
    Audience
      Developers
      AI tool users

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Why would anyone build with this?

REASON 1

Verify that an AI assistant's explanation of a code change matches the actual diff before merging it.

REASON 2

Catch hallucinated functions or fake internal calls that an AI claims to have added.

REASON 3

Run structural verification checks in a CI pipeline using the JSON output mode.

What's in the stack?

Python

How it stacks up

astralxvoid/nowreck0xustaz/streamgatea-bissell/unleash-lite
Stars111
LanguagePythonPythonPython
Setup difficultymoderatehardhard
Complexity2/54/54/5
Audiencedeveloperdeveloperresearcher

Figures from each repo's GitHub metadata at analysis time.

How do you spin it up?

Difficulty · moderate Time to first run · 30min

Requires an OpenAI-compatible API key and Python 3.10 or later.

Wtf does this do

NoWreck is a command line tool that checks whether an AI coding assistant's explanation of a code change actually matches what happened in the code. When an AI tool edits your files and describes what it did, NoWreck compares that description against a structural analysis of the real changes, rather than asking another AI to judge the work. The tool works in three steps. First it scans all Python files in a before and after snapshot of a project and parses them to build a list of every function, class, and method. Second, it compares the two scans to detect what actually changed, such as functions or classes being added or removed, new files appearing, or new function calls showing up. This comparison becomes the single record of truth that the rest of the tool relies on. Third, it checks each claim the AI made against that record. If a claim matches a detected change, it is marked confirmed. If a claim contradicts what was detected, for example the AI says something was added when it was actually removed, it is marked contradicted. If nothing matches either way, the claim is marked unverifiable rather than guessed at. NoWreck currently supports only Python projects, since it relies on parsing Python's abstract syntax tree. It can be installed from a cloned copy of the repository using pipx and requires Python 3.10 or later. It works with any OpenAI-compatible model endpoint, including Groq, DeepSeek, Ollama, LM Studio, OpenRouter, and OpenAI itself, so a user can plug in their own AI provider and API key. There are two main ways to use it. In prompt mode, you describe a change in plain language and NoWreck calls the configured model, gets back a set of claims, and verifies them automatically. In pre and post mode, you supply two folder snapshots directly, which is useful for checking a change that already happened. Output can be shown as colored terminal text or as structured JSON for use in automated pipelines. The project is upfront that static analysis has real limits. It cannot see through dynamic behavior such as exec, eval, dynamic imports, or getattr calls, since these are not visible to a plain structural scan.

Yoink these prompts

Prompt 1
Set up NoWreck with my Groq API key and verify the last change an AI assistant made to my auth.py file.
Prompt 2
Write a script that runs nowreck fix in JSON mode as part of my CI pipeline and fails the build on any CONTRADICTED claims.
Prompt 3
Explain how NoWreck's pre and post scan mode could catch an AI assistant that claims to have added a function it never actually added.
Prompt 4
Show me how to configure NoWreck to use a local Ollama model instead of an OpenAI-compatible cloud endpoint.

Frequently asked questions

wtf is nowreck?

A command line tool that checks whether an AI coding assistant's description of a code change matches what actually happened in the code, using structural analysis instead of another AI's opinion.

What language is nowreck written in?

Mainly Python. The stack also includes Python.

How hard is nowreck to set up?

Setup difficulty is rated moderate, with roughly 30min to a first successful run.

Who is nowreck for?

Mainly developer.

View the repo → Decode another repo

This repo across BitVibe Labs

Don't trust strangers blindly. Verify against the repo.