humanizer social preview
agent-framework71,713MIT

humanizer

Agent skill that removes signs of AI-generated writing from text

Updated Nov 21, 2026
Platforms
Pricing
free-open-source
Status
active
License
MIT

What it does

Core capabilities at a glance

  • Agent Skills
  • AI Humanizer
  • AI Writing
  • Chatgpt
  • Claude
  • Claude Code
  • Codex
  • Cursor

Deep dive

The full breakdown - performance, comparisons, and setup

humanizerLink to this section

humanizer is an agent framework - Agent skill that removes signs of AI-generated writing from text.

OverviewLink to this section

Humanizer makes AI-written text sound like a person wrote it, without changing what it says. It is built on Wikipedia's Signs of AI writing, the guide Wikipedia editors use to catch AI-generated text, and it works in Claude Code, Codex, and any other agent that supports skills.

In a blind test, judges preferred Humanizer's rewrite over the original AI text 16 times out of 16 (#229).

Humanizer edits for human readers. Getting past AI detectors is not a goal, and detectors still flag most of its output.

  1. Not X but Y: "It's not just a feature, it's a shift." 2. One-line closers: "Let that sink in." 3. Sayings that sound deep: "At its core, what really matters is..." 4. A staged run-up: "Here's the thing." "Honestly?" 5. Arguing with no one: "I'm not saying X, but..."

The plugin answers to '/humanizer:humanizer'. It needs Claude Code 2.1.142 or newer; on older versions, use 'npx skills add blader/humanizer --global --agent claude-code'.

Download this repository as a ZIP (Code → Download ZIP) and upload it as a skill in Settings.

humanizer is open-source, written primarily in Python, with 71,713 GitHub stars under the MIT license. The latest release is v3.1.0 (2026-09-28).

Key capabilitiesLink to this section

From the project's documentation:

  • WikiProject AI Cleanup maintains the page.

How it fits a local-AI stackLink to this section

humanizer runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related agent frameworks in the directory:

SourcesLink to this section

Stats from GitHub, 2026-10-01.

From the community

What users are saying

“This is a de-AI-izer, not a "humanizer". It removes AI tics, it doesn't add human voice. This tool appears primarily designed to produce text that's clearer and more concise, not to produce text that fools someone into thinking a human wrote it.”

“I'm guessing this "humanizer" actually does two things: * grep to remove em dashes and emojis * re-run through another llm with a prompt to remove excessive sycophantry and invalid url citations”

“Fair point. It removes AI tics and makes text clearer. It does not add a voice, and it does not try to fool a detector. "Humanizer" is the name of the skill it builds on (blader/humanizer), so I kept it.”

Frequently asked

Quick answers to common questions

What is humanizer?

humanizer is a agent-framework tool for local AI workloads. Agent skill that removes signs of AI-generated writing from text

Is humanizer free and open source?

Yes, humanizer has 71,713 GitHub stars and is licensed under MIT. You can self-host it for free on .

What hardware do I need for humanizer?

The hardware requirements depend on which models you run. Check our hardware directory for compatible GPUs and systems. humanizer has 71,713 GitHub stars and an active community.

Does humanizer support GPU acceleration?

humanizer's GPU support depends on your specific setup. Check the documentation for details. For the best performance, pair it with an NVIDIA RTX 4090 or 5090.

What are the best alternatives to humanizer?

Popular alternatives include other agent-framework tools in our directory. Browse our full collection at /tool for comparisons, community reviews, and benchmark data to find the right fit for your workflow.

How much does humanizer cost?

humanizer is free-open-source. It is completely free and open source to self-host.

Pairs well with

Complementary tools, models, and hardware