[PR #406] [CLOSED] Add LocalMod - Prompt Injection & Content Safety Tool #13713

Closed
opened 2026-07-11 19:16:26 -05:00 by GiteaMirror · 0 comments
Owner

📋 Pull Request Information

Original PR: https://github.com/Shubhamsaboo/awesome-llm-apps/pull/406
Author: @KOKOSde
Created: 1/1/2026
Status: ❌ Closed

Base: main ← Head: add-localmod


📝 Commits (1)

  • 78e55e5 Add LocalMod to LLM Optimization Tools

📊 Changes

1 file changed (+1 additions, -0 deletions)

View changed files

📝 README.md (+1 -0)

📄 Description

What is LocalMod?

LocalMod is a self-hosted content moderation API designed for LLM applications.

Why it's useful for LLM developers

  • 🛡️ Prompt Injection Detection: Detects jailbreak attempts like 'Ignore all instructions...' using DeBERTa model
  • 🔥 Toxicity Filtering: Filter toxic inputs/outputs from LLMs (weighted ensemble achieving 0.75 balanced accuracy)
  • 🔒 PII Detection: Detect and mask sensitive data (emails, SSNs, credit cards) before sending to LLMs
  • 📧 Spam Detection: Filter spam content from LLM inputs
  • 🔞 NSFW Detection: Block inappropriate content (text and images)

Key Features

  • 100% Offline: Download models once, run forever without internet
  • FastAPI: High-performance async endpoints
  • Benchmarked: Outperforms Amazon Comprehend on toxicity detection
  • MIT Licensed: Free for commercial use

Links

Added under 'LLM Optimization Tools' as it helps optimize LLM safety and security.


🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.

## 📋 Pull Request Information **Original PR:** https://github.com/Shubhamsaboo/awesome-llm-apps/pull/406 **Author:** [@KOKOSde](https://github.com/KOKOSde) **Created:** 1/1/2026 **Status:** ❌ Closed **Base:** `main` ← **Head:** `add-localmod` --- ### 📝 Commits (1) - [`78e55e5`](https://github.com/Shubhamsaboo/awesome-llm-apps/commit/78e55e59402774494ca23189f248d052b668950b) Add LocalMod to LLM Optimization Tools ### 📊 Changes **1 file changed** (+1 additions, -0 deletions) <details> <summary>View changed files</summary> 📝 `README.md` (+1 -0) </details> ### 📄 Description ## What is LocalMod? [LocalMod](https://github.com/KOKOSde/localmod) is a self-hosted content moderation API designed for LLM applications. ### Why it's useful for LLM developers - **🛡️ Prompt Injection Detection**: Detects jailbreak attempts like 'Ignore all instructions...' using DeBERTa model - **🔥 Toxicity Filtering**: Filter toxic inputs/outputs from LLMs (weighted ensemble achieving 0.75 balanced accuracy) - **🔒 PII Detection**: Detect and mask sensitive data (emails, SSNs, credit cards) before sending to LLMs - **📧 Spam Detection**: Filter spam content from LLM inputs - **🔞 NSFW Detection**: Block inappropriate content (text and images) ### Key Features - **100% Offline**: Download models once, run forever without internet - **FastAPI**: High-performance async endpoints - **Benchmarked**: Outperforms Amazon Comprehend on toxicity detection - **MIT Licensed**: Free for commercial use ### Links - GitHub: https://github.com/KOKOSde/localmod - Release: v0.1.0 Added under 'LLM Optimization Tools' as it helps optimize LLM safety and security. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>
GiteaMirror added the pull-request label 2026-07-11 19:16:26 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/awesome-llm-apps#13713