HumanMark

vinpatel/HumanMark

Open source AI content detection. Detect AI-generated text, images, audio, video. Self-hosted, offline, zero dependencies.

Go

8

0

🤔 The Problem

#

Every AI detection service requires you to upload your content to their servers. That’s a dealbreaker for:

HumanMark runs entirely on YOUR infrastructure. Your data never leaves your network. Period.

⚡ Quick Start

#

Get running in under 30 seconds:

docker run -p 8080:8080 humanmark/humanmark

go install github.com/vinpatel/humanmark/cmd/api@latest
humanmark

git clone https://github.com/vinpatel/humanmark.git
cd humanmark && make run

Then detect AI content:

curl -X POST http://localhost:8080/verify \
  -H "Content-Type: application/json" \
  -d '{"text": "Your content here"}'

Response:

{
  "id": "hm_abc123",
  "verdict": "human",
  "confidence": 0.87,
  "signals": {
    "sentence_variance": 0.42,
    "vocabulary_richness": 0.78,
    "contraction_ratio": 0.15
  }
}

🏆 Why HumanMark?

#

Feature Comparison

#

🔬 How It Works

#

HumanMark uses statistical forensics—no ML models, no GPU required, instant results.

💼 Use Cases

#

1. Enterprise Compliance

   HIPAA/GDPR

   Healthcare, Finance, Legal

   Organizations that cannot send data to third-party APIs. HumanMark runs on-premise—patient records, legal documents, and financial data never leave your network.
2. Education at Scale

   100K+ Students

   Universities & Districts

   Process millions of assignments without per-document fees. Self-hosted = unlimited usage at fixed infrastructure costs. Often 90%+ savings vs. commercial alternatives.
3. Developer Integration

   REST API

   Content Platforms & Apps

   Integrate AI detection into your product: content moderation, hiring tools, CMS plugins, browser extensions. Full REST API with SDKs coming soon.
4. Government & Defense

   Air-Gapped

   Classified Environments

   Deploy in air-gapped networks with zero internet connectivity. Essential for classified environments, secure facilities, and critical infrastructure.

📊 Performance

#

Benchmarked on AWS c5.xlarge (4 vCPU, 8GB RAM):

🗺️ Roadmap

#

• Text detection (statistical analysis)
• Image detection (EXIF + forensics)
• Audio detection (metadata)
• Video detection (container analysis)
• Docker support
• Prometheus metrics
• 🔜 Browser extension
• 🔜 VS Code extension
• 🔜 WordPress plugin
• 🔜 Python & JavaScript SDKs
• 🔜 Admin dashboard

🔗 Links

#

📜 License

#

Built with ❤️ by Vin Patel