git404hub

what is reverseloom fr?

kuichi-x/reverseloom — explained in plain English

Analysis updated 2026-05-18

25PythonAudience · developerComplexity · 4/5LicenseSetup · hard

tl;dr

An AI-driven browser agent that watches how a website talks to its own backend, works out how to reproduce hidden signatures and tokens, and writes a standalone crawler that runs without a browser.

vibe map

mindmap
  root((reverseloom))
    What it does
      Watches browser traffic
      Reverses signed tokens
      Writes standalone crawler
    Capabilities
      Browser automation
      CDP breakpoints
      Vision for captchas
      Human hand off
    Tech stack
      Python
      Node sandbox
      Chromium
    Setup
      Windows executable
      Install from source
      Model API key
    Use cases
      Bypass bot detection
      Scrape without browser

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

what do people make with this?

VIBE 1

Reverse engineer a website's hidden API so you can scrape it without running a browser

VIBE 2

Automatically figure out how a site generates signed or encrypted request tokens

VIBE 3

Build a browser-free crawler for a site protected by bot detection systems

VIBE 4

Compare data across multiple websites by having the agent drive each one and report back

what's the stack?

PythonChrome DevTools ProtocolChromiumJavaScriptNode.js

how it stacks up fr

kuichi-x/reverseloomalexrosbach/replibookarlandaren/proagents
Stars252525
LanguagePythonPythonPython
Setup difficultyhardeasyeasy
Complexity4/52/51/5
Audiencedeveloperops devopsvibe coder

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

how do i run it?

Difficulty · hard time til it works · 1h+

Needs a Chromium-based browser already installed plus an API key for a model that supports image input and streaming.

Use, modify, and distribute freely, including for commercial purposes, as long as you keep the license and attribution notices.

in plain english

reverseloom is an AI browser agent built to figure out how a website's backend API works, then write a standalone script that talks to that API directly, without needing a browser running at all. The idea is that many websites protect their data with bot detection systems, signed or encrypted request parameters, and other barriers. Instead of a person manually studying obfuscated JavaScript for a day to reverse engineer one of these systems, an AI model drives a real browser, watches the page's network traffic and JavaScript debugger, and works out how a signature or token is generated. It then reproduces that logic in a small JavaScript sandbox and tests it repeatedly to confirm it works from a cold start, before writing a plain Python crawler that reproduces the same requests without a browser attached. The README walks through a real example against a site protected by Akamai Bot Manager: the agent notices a missing header causes a 403 error, sets breakpoints on the relevant JavaScript function, pulls out the two scripts responsible for generating that header, rebuilds the logic in its sandbox, and ships a working crawler that pulled 64 price records and passed five out of five repeated cold-start tests. The tool includes over 30 capabilities grouped into browser automation (clicking, typing, scrolling, dragging), JavaScript reverse engineering through Chrome DevTools Protocol breakpoints and network inspection, a vision tool for locating things like captchas on the page, and a way to hand off control to a human when a login or captcha needs manual input. It works with any Chromium-based browser already installed on the machine (Chrome, Edge, Chromium, or Brave) and does not download its own browser. Setup on Windows is a downloadable executable with its own bundled Python runtime, on macOS, Linux, or for developers, it installs from source with pip and runs as a desktop app or a local web server. Configuration happens through a settings screen or a .env file, where the user picks a model provider (OpenAI, Anthropic, Gemini, DeepSeek, or a local Ollama model) that supports both image input and streaming output. The README warns plainly that one of its tools runs arbitrary shell commands, so it should only be pointed at trusted code paths. The project is licensed under Apache 2.0 and is currently marked alpha status.

prompts (copy fr)

prompt 1
Have this agent write me a price crawler for this website that doesn't need a browser to run
prompt 2
Help me set up reverseloom with an OpenAI or Anthropic model that supports image input and streaming
prompt 3
Walk me through configuring the .env file for reverseloom on macOS or Linux
prompt 4
Explain how reverseloom uses CDP breakpoints to trace a website's token generation logic
prompt 5
Show me how to hand off control to reverseloom when a site shows a login wall or captcha

Frequently asked questions

what is reverseloom fr?

An AI-driven browser agent that watches how a website talks to its own backend, works out how to reproduce hidden signatures and tokens, and writes a standalone crawler that runs without a browser.

What language is reverseloom written in?

Mainly Python. The stack also includes Python, Chrome DevTools Protocol, Chromium.

What license does reverseloom use?

Use, modify, and distribute freely, including for commercial purposes, as long as you keep the license and attribution notices.

How hard is reverseloom to set up?

Setup difficulty is rated hard, with roughly 1h+ to a first successful run.

Who is reverseloom for?

Mainly developer.

peek the repo → explain another one

This repo across BitVibe Labs

double-check against the repo, no cap.