Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
Humanizer
SkillsEdits AI-written text so it reads like a person wrote it, based on Wikipedia's guide to the signs of AI writing.
-
humanlayer
AI repositoriesThe best way to get AI coding agents to solve hard problems in complex codebases.
git clone https://github.com/humanlayer/humanlayer.git -
humanizer
Modelstext generation model by jialinyyzz · gguf
jialinyyzz/humanizer -
OutfitAnyone
Tools & appsHugging Face space by HumanAIGC
HumanAIGC/OutfitAnyone -
human-writing
Skills让 AI 写的中文读起来像一个具体的人在说话。通用创作与改稿 Skill,开箱即用。
git clone https://github.com/KKKKhazix/human-writing.git -
sam-3d-body-dinov3
Modelsmodel by facebook · sam-3d-body
facebook/sam-3d-body-dinov3 -
AutoSwarm-Shadow-Adapter
AI repositoriesZero-modification Human-in-the-Loop adapter for OpenOPC's agentic DAG runtime.
git clone https://github.com/AhmadHassan-BTed/AutoSwarm-Shadow-Adapter.git -
awesome-human-distillation
SkillsA curated catalog of human distillliation agent skills
git clone https://github.com/mliu98/awesome-human-distillation.git -
humanize
SkillsBest static AI text humanizer. Two research-grounded LLM-agnostic skills that make AI writing sound human and relatable. Nine levers, 50+ peer-reviewed sources, 2024-2026 detection literature.
git clone https://github.com/harshaneel/humanize.git -
speak-human-tw
Skills「說人話」:繁體中文的去 AI 味改寫 skill。抓 38 種 AI 寫作痕跡,順手校正中國用語與半形標點,給 Claude Code / Codex / Cursor 用。
git clone https://github.com/Raymondhou0917/speak-human-tw.git -
Human-Like-DPO-Dataset
Datasets & benchmarksHugging Face dataset by HumanLLMs
HumanLLMs/Human-Like-DPO-Dataset -
ste80-humanizer
SkillsSTE80 Humanizer: agent skill that removes AI tells and rewrites text 80% of the way to ASD-STE100 (Simplified Technical English), the method Andrej Karpathy shared.
git clone https://github.com/Dodaios/ste80-humanizer.git -
im-not-ai
SkillsAI가 쓴 한글을 사람 글처럼 윤문하는 Claude 스킬 — Korean AI-text humanizer: detects and rewrites translationese, mechanical parallelism, and 71 other AI tells
git clone https://github.com/epoko77-ai/im-not-ai.git -
Streamer-Sales
AI repositoriesStreamer-Sales 销冠 —— 卖货主播 LLM 大模型🛒🎁,一个能够根据给定的商品特点从激发用户购买意愿角度出发进行商品解说的卖货主播大模型。🚀⭐内含详细的数据生成流程❗ 📦另外还集成了 LMDeploy 加速推理🚀、RAG检索增强生成 📚、TTS文字转语音🔊、数字人生成 🦸、 Agent 使用网络查询实时信息🌐、ASR 语音转文字🎙️、Vue 生态搭建前端🍍、FastAPI 搭建后端🗝️、Docker-compose 打包部署🐋
git clone https://github.com/PeterH0323/Streamer-Sales.git -
patina
PromptsAI-writing humanizer for KO/EN/ZH/JA
git clone https://github.com/devswha/patina.git -
Orpheus-TTS
AI repositoriesTowards Human-Sounding Speech
git clone https://github.com/canopyai/Orpheus-TTS.git -
hh-rlhf
Datasets & benchmarksHugging Face dataset by Anthropic
Anthropic/hh-rlhf -
humanizer-ru
Skillshumanizer-ru: редактура русского текста для AI-агентов. Убирает канцелярит и шаблонные обороты, сверяет смысл и факты. 67 признаков, 21 жёсткий запрет, сканер, CLI, MCP и расширение Chrome. | Russian text editing for AI agents: removes bureaucratese and template phrasing, checks facts.
git clone https://github.com/ilyautov/humanizer-ru.git -
CyberVerse
Agents & frameworksSelf hosted, real-time digital human agent platform. Build voice-first AI agents with WebRTC, persona memory, tools, RAG, and optional digital-human video.
git clone https://github.com/Lynpoint/CyberVerse.git -
hive
Agents & frameworksMulti-Agent Harness for Production AI
git clone https://github.com/aden-hive/hive.git -
humanize
Agents & frameworksThe agent flow system for token maxxing.
git clone https://github.com/humanfia/humanize.git -
humanizer-de
PromptsDeutscher Text-Humanizer für Claude Code & Codex. Redigiert KI-Floskeln, schützt deine Schreibstimme und prüft 72 deutsche Muster quellentreu.
git clone https://github.com/marmbiz/humanizer-de.git -
text generation model by LessThanThreeAI · gguf
LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-GGUF -
free4chat
Agents & frameworksTemporary rooms for Humans and AI Agents — run, supervise and steer Agent Tasks without a permanent workspace.
git clone https://github.com/i365dev/free4chat.git
Indexed entries aren't reviewed or tested by InnerVault. Details come straight from each source. Anything that can reach your accounts, files or browser can do damage, so read the source before you install it.