git404hub

what is hermes-pulpie fr?

kachook/hermes-pulpie — explained in plain English

Analysis updated 2026-05-18

5PythonAudience · developerComplexity · 2/5LicenseSetup · easy

tl;dr

A local plugin for the Hermes AI agent that strips ads, navigation, and clutter from web pages using a small offline model, no API key required.

vibe map

mindmap
  root((Hermes Pulpie))
    What it does
      Cleans web pages
      Removes ads and nav
      Local model only
    Tech stack
      Python
      httpx
      Playwright
      html2text
    Use cases
      Web extraction for agents
      Token savings
      JS heavy page rendering
    Audience
      Developers
      AI agent builders
    Setup
      pip install
      Hermes plugin system
      GPU auto detect

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

Give a Hermes Agent a way to extract clean article text from web pages without an API key.

VIBE 2

Cut down on tokens sent to an LLM by stripping ads and navigation from fetched pages.

VIBE 3

Render and clean JavaScript-heavy pages like news sites using the bundled Playwright script.

VIBE 4

Run web content extraction fully offline once the model is downloaded.

what's the stack?

PythonhttpxPlaywrighthtml2text

how it stacks up fr

kachook/hermes-pulpie1ncendium/aibusteraaronmayeux/ha-hurricane-tracker
Stars555
LanguagePythonPythonPython
Setup difficultyeasymoderateeasy
Complexity2/53/52/5
Audiencedeveloperops devopsgeneral

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

how do i run it?

Difficulty · easy time til it works · 5min

Requires the Hermes Agent already set up, JS-heavy page support needs Playwright and Chromium installed separately.

The plugin code is MIT and the Pulpie library is Apache 2.0, both free to use commercially, but the model weights are CC BY-NC 4.0, which does not allow commercial use.

in plain english

Hermes Pulpie is a plugin that gives the Hermes Agent's web_extract tool a way to clean up web pages before handing them to an AI. When Hermes fetches a page, this tool strips out navigation bars, ads, sidebars, and footers, leaving just the actual content, and it does all of this locally using a small 210 million parameter model rather than calling an external API, so no API key is needed. According to the README, the model matches the quality of a comparable tool called Dripper while being about a third of the size, and it typically cuts the number of tokens needed to represent a page by around 80 percent, which saves cost and context space when the cleaned page is passed to a language model. It automatically detects and uses a GPU (CUDA or Apple's MPS) if one is available, and falls back to the CPU otherwise. Installation is a single pip command that also registers the plugin with Hermes automatically, or it can be installed through Hermes's own plugin installer with a couple of manual dependency steps. Once installed and configured, running a Hermes chat command that extracts a URL will show a footer noting how many characters were saved by the cleanup. Under the hood, the pipeline fetches the page with httpx, runs the Pulpie encoder model to classify each HTML block as content or boilerplate in a single pass, keeps only the content blocks, and converts the result to Markdown with html2text. For pages that rely heavily on JavaScript, like single-page apps or news sites, a separate bundled script uses Playwright to render the page in a headless Chromium browser first, then runs the same cleanup pipeline on the resulting page. The README also documents a full uninstall process covering the different install paths, removing the browser script, freeing the roughly 421 megabyte model cache, and removing the project if it was checked out as a git submodule. The plugin code is released under MIT, the Pulpie library under Apache 2.0, and the model weights under a non-commercial CC BY-NC 4.0 license.

prompts (copy fr)

prompt 1
Help me install hermes-pulpie and configure Hermes to use it as the web extract backend.
prompt 2
Explain how the Pulpie encoder model decides which HTML blocks are content versus boilerplate.
prompt 3
Show me how to use the pulpie-browser script to extract content from a JavaScript-heavy page.
prompt 4
Walk me through fully uninstalling hermes-pulpie, including the cached model weights.

Frequently asked questions

what is hermes-pulpie fr?

A local plugin for the Hermes AI agent that strips ads, navigation, and clutter from web pages using a small offline model, no API key required.

What language is hermes-pulpie written in?

Mainly Python. The stack also includes Python, httpx, Playwright.

What license does hermes-pulpie use?

The plugin code is MIT and the Pulpie library is Apache 2.0, both free to use commercially, but the model weights are CC BY-NC 4.0, which does not allow commercial use.

How hard is hermes-pulpie to set up?

Setup difficulty is rated easy, with roughly 5min to a first successful run.

Who is hermes-pulpie for?

Mainly developer.

peek the repo → explain another one

This repo across BitVibe Labs

double-check against the repo, no cap.