Automate the obvious and investigate the ambiguous. High-performance safety rules engine for real-time event processing at scale.
-
Updated
Apr 4, 2026 - Python
Automate the obvious and investigate the ambiguous. High-performance safety rules engine for real-time event processing at scale.
Directory of open source tools for online safety
Making open safety AI models accessible and beneficial to the safety community
Software and Resources for Mitigating Online Gender Based Violence in India
ActivityPub Trust and Safety Taskforce
Review and moderation, your way. Online safety dashboard, queues, routing and automatic enforcement rules, and integrations.
A trust and safety agent that interacts with Osprey for investigation, real-time analysis, and prevention implementations
Self-hosted Trust & Safety policy engine with A/B testing, replay, and full audit trails
Documentation and policies for the ROOST organization and open source community. File non-technical or ROOST-wide issues here.
Your third-party safety layer for verified, transparent, and scam-free online transactions.
A .NET implementation of the PDQ hashing algorithm to make integrating Trust and Safety tools for digital service providers easier.
OpenSiteTrust is an open, explainable, and reusable website scoring ecosystem
A Reflection on Truth, Power, and the Misdiagnosis of Awareness
ls -la for MCP servers. See tools, resources, and risky capabilities before you connect or trust a server.
🤝 Using large language models to seamlessly help content moderators make better decisions, faster.
Combat fake news with cryptographic image verification. Origin Lens analyzes C2PA Content Credentials and EXIF metadata to detect AI-generated content, verify digital signatures, and reveal complete edit history. Privacy-first open source iOS app with on-device verification. (arXiv:2602.03423)
Production-ready Multimodal Lip Sync Detection & Deepfake Detection System. Detects audio-video synchronization mismatches using deep learning (PyTorch) with a scalable FastAPI-based inference pipeline. Optimized for real-time processing,low false positives, and robust performance on noisy speech segments. Built for video forensics,synthetic media
A Python Client for the Athena CSAM detection service
Desktop app for detecting inappropriate or unsafe messages using PyQt6, OCR, and NLP (rule-based + DistilBERT).
Add a description, image, and links to the trust-and-safety topic page so that developers can more easily learn about it.
To associate your repository with the trust-and-safety topic, visit your repo's landing page and select "manage topics."