trust-safety

Open-source multimodal AI provenance detection platform with explainable evidence cards, provider consensus, and benchmark-driven quality gates.

Public profile README covering how I approach product, AI systems, and customer signal in production.

MCP server with 41 AI-powered tools for child safety, fraud detection, and content moderation. Detects bullying, grooming, sextortion, romance scams, social engineering, and more. For Claude, Cursor, and MCP-compatible AI assistants.

Open-source behavioral intelligence for child safety moderation.

Crash course for new tirreno developers. Open-source security framework architecture, integration guide, and risk rules for developers and product teams.

Official .NET SDK for Moderyo Content Moderation API

Give your AI agents the power to discover, coordinate, and collaborate safely. Open-core collaboration layer for AI agents.

Synthetic trust and safety operations case study for AI user reports, covering risk taxonomy, severity classification, SQL analysis, dashboarding, QA, escalation workflow, and responsible automation.

ARGUS — open-source trust & safety platform. Fake account detection, deepfake identification, and disinformation monitoring for digital advertising.

Autonomous Trust & Safety system using multi-agent orchestration on AWS. Detects, investigates, and enforces policy violations at scale with human-in-the-loop for sensitive cases. Built with Lambda, Step Functions, Bedrock, DynamoDB, and React.

Official Moderyo Unity SDK — AI-powered content moderation for games. UPM package for Unity 2021.3+.

A curated list of tools, research, organizations, and frameworks for trust and safety, child protection, and content moderation.

Free and open-source dating platform that respects your privacy

A documented product exploration around small events, trust signals and continuity after people meet.

Public product, architecture and trust case study for SoekIets, a Windhoek-first neighbourhood marketplace.

Technical Lead case study: React Native iOS app, trust & safety, tutoring marketplace, App Store deployment

CryptoKRI GmbH (Zurich, CHE-115.481.407) operates MolTrust, a trust registry for autonomous AI agents: W3C DID identity (did:moltrust, did:web), W3C Verifiable Credential issuance and verification, Agent Authorization Envelopes (AAE, an IETF Internet-Draft) with UCAN delegation and stateless mandate enforcement, behavioural trust scores signed…

Raid AI — independent third-party profile of a public API surface, by API Evangelist. Raid AI (RAID AI, Inc.) is an enterprise-grade deepfake and AI-content forensics platform covering audio, image, document, and video. Its REST API detects AI-generated, cloned, deepfaked, and digitally edited media — returning a verdict, a confidence score, and (o