Collection of scripts to aggregate image data for the purposes of training an NSFW Image Classifier
-
Updated
Jan 21, 2024 - Shell
#
content-moderation
Here are 694 public repositories matching this topic...
Deep learning based content moderation from text, audio, video & image input modalities.
profanity-detection nudity-detection genre-classification explainable-ai violence-detection multimodal-deep-learning movie-trailer nsfw-recognition content-moderation content-ratings movie-content-filter violence-classification
-
Updated
Jul 13, 2026
🤬 🚫 Blasp is a profanity filter package for Laravel that helps detect and mask profane words in a given sentence. It offers a robust set of features for handling variations of offensive language, including substitutions, obscured characters, and doubled letters.
php laravel profanity-validator profanity-detection profanityfilter profanity-filter content-moderation profanity-library profanity-check
-
Updated
May 1, 2026 - PHP
The world's largest social media toxicity dataset.
-
Updated
Jun 10, 2022
Self-hosted content moderation API that outperforms Amazon Comprehend. 100% offline, your data never leaves your server. Text + Image moderation.
docker machine-learning privacy offline-first self-hosted spam-detection image-moderation content-moderation fastapi pii-detection toxicity-detection nsfw-detection prompt-injection llm-security
-
Updated
Apr 11, 2026 - Python
The Open Source Firewall for LLMs. A self-hosted gateway to secure and control AI applications with powerful guardrails.
self-hosted ai-safety content-moderation pii-redaction prompt-injection llm-security ai-gateway llm-firewall llm-guardrails
-
Updated
Jun 25, 2025 - Python
Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface
python security benchmark machine-learning ai jailbreak evaluation santander alignment ai-safety red-teaming content-moderation guardrails responsible-ai llm prompt-injection llm-safety autoresearch
-
Updated
Sep 1, 2026 - Python
中文敏感词/违禁词检测 MCP Server | 支持小红书/抖音/快手/B站 | 风险分级+安全替换建议 | 微信: chenganp | 邮箱: 345048305@qq.com
nlp mcp chinese bilibili compliance cursor text-detection claude kuaishou douyin xiaohongshu content-moderation sensitive-words mcp-server openclaw qclaw
-
Updated
Mar 15, 2026 - JavaScript
A fast accurate API for detecting NSFW images.
python api open-source machine-learning ai tensorflow image-processing image-classification content-moderation nsfw-detection
-
Updated
May 31, 2024 - Python
基于 LLM 的 Telegram 群聊智能管理机器人 — 智能决策、知识库 RAG、内容审查、贴纸学习、联网搜索、多层记忆架构
-
Updated
Sep 5, 2026 - Python
High-performance, self-hosted NSFW detection API powered by NSFWJS.
api docker machine-learning typescript computer-vision tensorflow docker-image self-hosted nsfw hono tensorflowjs deno content-moderation nsfw-detection image-classication
-
Updated
May 24, 2026 - TypeScript
Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII filtering, secret redaction, tool permissions, and async guardrails. Built on pydantic-ai's native capabilities API.
python async rate-limiting openai middlewares type-safe input-validation ai-safety ai-agents content-moderation pydantic guardrails pii-redaction llm anthropic ai-guardrails pydantic-ai vstorm
-
Updated
Sep 21, 2026 - Python
自媒体视频发布前违规风险审核。检查画面/声音/文字/封面/评论/带货信息/资质/引流，输出 Pass→Blocker 五级风险报告。覆盖抖音/小红书/视频号/B站/快手+千川低质素材。Claude Code、codex、workbuddy、hermes skill
skills risk-assessment ai-agents social-media-tool content-moderation compliance-check content-creation social-media-tools ai-agent claude-code-skills e-commerce-compliance
-
Updated
Sep 21, 2026 - Python
多智能体文本内容审核系统，提供结构化审核、证据链与复核路由，适用于内容安全与合规治理。
-
Updated
May 4, 2026 - Python
TEKNOFEST 2026 NSosyal İnovasyon — Explainable recommendations, semantic context cards and Turkish AI moderation.
nlp machine-learning nextjs explainable-ai content-moderation teknofest fastapi turkish-nlp teknofest2026
-
Updated
Aug 24, 2026 - Python
Multi-Agent DPO Data Synthesis Factory — 多智能体偏好训练数据自动合成框架 | 红队攻击 → 多persona审核 → 终审裁决 → DPO偏好对
multi-agent data-quality synthetic-data preference-learning red-teaming content-moderation dpo pydantic llm rlhf
-
Updated
Apr 11, 2026 - Python
Open-source ML-powered profanity filter with TensorFlow.js toxicity detection, leetspeak & Unicode obfuscation resistance. 21M+ ops/sec, 23 languages, React hooks, LRU caching. npm & PyPI.
javascript python chat open-source npm machine-learning privacy typescript npm-package profanity-filter tensorflow-js content-moderation react-hooks toxicity-detection glincker glin-profanity
-
Updated
Sep 23, 2026 - TypeScript
自媒体发布审核 Skill｜Pre-publish audit for Douyin, Xiaohongshu, Weixin Video Accounts & Kuaishou.
codex short-video kuaishou douyin xiaohongshu content-moderation creator-tools content-audit aigc content-localization agent-skills claude-code content-review china-social-media content-compliance creator-compliance weixin-video-accounts livestream-commerce overseas-creators
-
Updated
Jul 22, 2026 - Python
Ultra-fast multi-language profanity filter, designed Turkish-first and extensible to any language. Catches leet speak, agglutination & evasion patterns. Zero deps, TypeScript, 35 KB.
nodejs javascript typescript regex moderation turkish extensible censor zero-dependency multi-language profanity-detection nsfw bad-words profanity-filter chat-filter agglutination word-filter edge-computing text-filter content-moderation
-
Updated
Sep 25, 2026 - TypeScript
Software and Datasets for Mitigating Online Gender Based Violence in India
nlp machine-learning ml browser-extension india social-impact sdg indic-languages indic indian-languages trust-and-safety gender-based-violence extension-chrome content-moderation ogbv sdg-10 sdg-5
-
Updated
Sep 11, 2026 - JavaScript
Add this topic to your repo
To associate your repository with the content-moderation topic, visit your repo's landing page and select "manage topics."