# AI Text Detection with DeBertaV3

> AI Text Detection with DeBertaV3 — houtini-ai-ai-detect. Use this tool when you need to detect AI-generated text in a document or passage, as it solves the problem of identifying potentially machine-written content by scoring writing sentence by sentence. It takes in text input and outputs a detection score, allowing for offline analysis without requiring an API key or upload. Ideal for use cases where privacy and cost-effectiveness are crucial, such as academic or journalistic research.

Canonical page: https://skillsregistry.net/skills/houtini-ai-ai-detect  
JSON: https://api.skillsregistry.net/v1/skills/houtini-ai-ai-detect

## Description

ai-detect is a free AI text detector that runs entirely on your own hardware. It scores writing sentence by sentence using desklib/ai-text-detector-v1.01, a 304-million-parameter DeBERTa-v3-large model that ranks first on the RAID detection benchmark. No API key, no per-word pricing and no upload: after a one-off 1.7 GB model download it just works offline. by Houtini

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** iot-hardware
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/f6sul7vbvb)
- **Repository:** <https://github.com/houtini-ai/ai-detect>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "houtini-ai-ai-detect"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/houtini-ai-ai-detect` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/houtini-ai-ai-detect/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt