See through synthetic text.
Detect AI-generated text. Transform it into natural writing. Compose polished drafts. A desktop app that runs on your machine — with MCP server integration for Claude workflows.
AI text is everywhere
ChatGPT, Claude, Gemini. Everyone uses them now. But AI-generated text has a signature: uniform sentence lengths, predictable transitions, hedging language, corporate jargon. No personality, no voice, no humanity.
Writers need to know if their drafts sound robotic. Editors need to spot AI-assisted submissions. Professionals need to polish AI-drafted content without sounding like a machine.
Detection that stays on your machine
PRISM analyzes text locally using a combination of heuristics and machine learning. Perplexity, burstiness, entropy, and pattern matching work together to produce an AI probability score. A sentence-level heatmap shows exactly which parts triggered detection and why.
Humanization transforms flagged text into three distinct styles: Natural, Creative, and Professional. Use the Claude API for the highest quality, or run local ONNX models for complete offline operation.
System architecture
PRISM is built with Tauri 2.0 — a lightweight Rust-based desktop framework. The React frontend handles the UI and state management through Zustand, while all analysis runs natively in Rust.
Text analysis combines ONNX-based machine learning inference with heuristic metrics: perplexity, burstiness, entropy, and pattern recognition. The Claude API provides humanization and compose capabilities when configured.
API keys are stored securely in the OS keychain — never in config files. Exports generate styled PDFs and structured JSON. Everything runs locally unless you explicitly enable cloud-based humanization.
Two modes
Detect
Analyze and humanize
- 1Paste text
- 2View AI probability score and metrics
- 3See heatmap highlighting AI-like sentences
- 4Click humanize for 3 style variations
- 5Export results as JSON or PDF
Compose
Draft and polish
- 1Write rough text in any language
- 2Select source and target language
- 3Get 3 polished versions: Natural, Creative, Professional
- 4Copy the one you like
- 5Repeat and refine
In practice
Detect mode with heatmap analysis, and Compose mode for polishing drafts.
Detect mode — AI probability score with sentence heatmap
Detect mode — detailed metrics and pattern analysis
Compose mode — three polished variations from rough text
Compose mode — multi-language support with style presets
What PRISM includes
Detection, humanization, composition, and export in a single desktop application.
Local ML detection (ONNX)
Trained classifier runs locally via ONNX Runtime. No internet required for detection.
Heuristic analysis
Perplexity, burstiness, and entropy metrics reveal AI writing patterns.
Pattern recognition
Detects filler words, hedging language, corporate jargon, and uniform sentence structures.
Sentence-level heatmap
Color-coded visualization shows which sentences triggered detection and why.
Three humanization styles
Natural, Creative, and Professional. Each rewrites AI text with a distinct voice.
Local humanization
ONNX-based text rewriting with Light, Balanced, and Accurate presets. No API needed.
Compose mode
Write rough text, select source and target language, get three polished variations.
Multi-language support
Detection and humanization in English, Italian, Spanish, and German.
PDF and JSON export
Export full analysis reports as styled PDFs or structured JSON data.
Secure API key storage
Anthropic API key stored in your OS keychain. Never in config files, never logged.
How PRISM compares
The only open-source, local-first AI text detection tool.
| PRISM | GPTZero | Originality.ai | ZeroGPT | |
|---|---|---|---|---|
| Runs locally | true | false | false | false |
| Works offline | true | false | false | false |
| Open source | MIT | false | false | false |
| Humanization | Built-in (3 styles) | false | false | false |
| Compose mode | true | false | false | false |
| Sentence heatmap | true | true | Partial | false |
| Export (PDF/JSON) | true | Paid | Paid | false |
| Price | Free | ~$10/mo | ~$15/mo | Freemium |
| Data privacy | Your machine only | Cloud | Cloud | Cloud |
Stack
Built with Tauri 2.0 and Rust for native performance and small binary size.
- Desktop
- Tauri 2.0
- Frontend
- React 19 + TypeScript + Tailwind
- Analysis engine
- Rust (heuristics + ONNX ML)
- AI integration
- Claude API or local ONNX
- Export
- genpdf (PDF) + serde_json (JSON)
- Languages
- EN, IT, ES, DE
Get started
Clone, install, and run. Requires Node.js 20+ and Rust 1.70+.
# Clone and build PRISM
git clone https://github.com/formray/prism.git
cd prism
npm install
# Run in development mode
npm run tauri:dev
# Build for production
npm run tauri:buildThe name
PRISM — PRISM — Pattern Recognition for Identifying Synthetic Messages.
Like a prism splits light into its components, PRISM breaks down text to reveal its true nature. Not anti-AI. Pro authenticity.
Pricing
PRISM is MIT licensed and free to use. Support tiers for teams and organizations.
Community
Free
Individual use
Pro
Contact us
Teams and professionals
Enterprise
Contact us
Organizations
All prices per organization. Annual billing.
Open source
MIT licensed. Use it, fork it, improve it. The more tools for authentic writing, the better.
Try PRISM.
Clone the repo, build the app, paste some text. See what your writing looks like through a prism.