Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
www-project-agent-memory-guard
MCP serversRuntime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.
git clone https://github.com/OWASP/www-project-agent-memory-guard.git -
guardana
MCP serversOpen-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for release decisions.
git clone https://github.com/guardana/guardana.git -
storyboard-scavenger
SkillsAI 视频分镜与提示词生成 Skill:创意转七要素分镜,提供 Kling/Seedance 工作流和运镜参考。AI video storyboard and prompt-writing skill.
git clone https://github.com/ouxxyy/storyboard-scavenger.git -
sam3.1
Modelsmask generation model by unsloth · transformers
unsloth/sam3.1 -
Intent-Router
PromptsIntent compiler for AI agents — converges vague requests into typed IntentSpec contracts (probe, ask, or halt before routing), the input layer for routers and typed-decision models like Jev & Laya
git clone https://github.com/angel291592/Intent-Router.git -
yu-ai-agent
AI repositories编程导航 AI 开发实战新项目,基于 Spring Boot 3 + Java 21 + Spring AI 构建 AI 恋爱大师应用和 ReAct 模式自主规划智能体YuManus,覆盖 AI 大模型接入、Spring AI 核心特性、Prompt 工程和优化、RAG 检索增强、向量数据库、Tool Calling 工具调用、MCP 模型上下文协议、AI Agent 开发(Manas Java 实现)、Cursor AI 工具等核心知识。用一套教程将程序员必知必会的 AI 技术一网打尽,帮你成为 AI 时代企业的香饽饽,给你的简历和求职大幅增加竞争力。
git clone https://github.com/liyupi/yu-ai-agent.git -
unslop
PromptsMake AI output sound human. Strips AI-isms (sycophancy, stock vocab, hedging stacks, em-dash pileups), preserves code/URLs/headings. Plugin for Claude Code, Cursor, Windsurf, Codex, Cline, Copilot, Gemini.
git clone https://github.com/MohamedAbdallah-14/unslop.git -
atelier
SkillsAn atelier for your Agent: spec-driven workflows, deep thinking, and code quality.
git clone https://github.com/martinffx/atelier.git -
attention-control
SkillsAir traffic control discipline for agent output. Written for a reader with ADHD.
git clone https://github.com/aaddrick/attention-control.git -
AI-paper-reviewer
PromptsAI Paper Reviewer: LLM-based tool for academic paper review
git clone https://github.com/FanBroWell/AI-paper-reviewer.git -
ai-bot-groupmate
PromptsEstrella Bot · QQ 群 AI 群友机器人。把 QQ 小号接给任意 OpenAI 兼容模型(本机 / DeepSeek / 智谱 / 通义),让 AI 像群友一样插话、接梗、潜水。OneBot v11 + NapCat,零构建网页控制台。Apache-2.0
git clone https://github.com/Canvixel-Eloweny/ai-bot-groupmate.git -
ospec
MCP serversSpec-driven, agentic workflow framework for AI coding agents. Turn a request into a verifiable goal loop — plan, act, verify — with durable specs and evidence in your repo. Works with Claude Code, Codex, Gemini, OpenCode, and plain CLI.
git clone https://github.com/clawplays/ospec.git -
codex-factory
Agents & frameworksMulti-agent engineering framework: evidence packs, runtime validation, task decomposition, cross-window worker execution, and CI artifact verification for Codex.
git clone https://github.com/yueheng-rgb/codex-factory.git -
motionvideo.xyz
SkillsA directory of AI-powered motion videos, prompts, and skills that teach coding agents motion design/graphics
git clone https://github.com/motionvideohq/motionvideo.xyz.git -
humanities-writing-companion
SkillsEnd-to-end humanities writing assistant — an Agent Skill (open SKILL.md format). 11 modes from Socratic research-question sharpening through AI-use disclosure. Bilingual (EN/中文), discipline-aware (literature/history/philosophy/art/religion/linguistics + cross-disciplinary). Four-layer critique, calibratable devils advocate, voice preservation.
git clone https://github.com/tizzy916/humanities-writing-companion.git -
agent-skills
PromptsMethod-driven agent skills for knowledge work: strategy, research, critical thinking, data analysis, docs, slides. Works with Claude Code, Codex, Cursor and any agentskills.io-compatible agent.
git clone https://github.com/tronghieu/agent-skills.git -
token-optimizer-mcp
MCP servers91.5% fewer tokens on tool output on Headroom's own benchmark, where Headroom removes 61.4%. Separately, the same SWE-bench tasks resolved at 0.71x the cost of plain Claude Code. Plus memory across sessions and subscription quota pacing. Claude Code, Codex, Copilot, Gemini and 12 more. Local, MIT.
git clone https://github.com/ooples/token-optimizer-mcp.git -
AI-Engineer-Interview-Questions
PromptsInterview questions and prep for AI Engineer, LLM Engineer, and Applied AI roles. Built for software engineers breaking into AI and ML practitioners levelling up: company-specific question sets, role-based study maps, worked answers, and from-scratch coding challenges.
git clone https://github.com/ombharatiya/AI-Engineer-Interview-Questions.git -
bang-film
SkillsAgent skill that designs AI live-action video — vertical microdrama series, short films, single scenes — and writes the prompts: concept, cast bible, shot list, character sheets, video prompts for any AI video model.
git clone https://github.com/bangtutorial/bang-film.git -
llmslim
MCP serversLong-term memory for AI agents with no LLM call: an MCP server and Claude Code plugin, plus local-first context compression for LLM apps.
git clone https://github.com/Thanatos9404/llmslim.git -
q-claude-skills
SkillsA collection of Claude skills organized by how I think, decide, research and build.
git clone https://github.com/kju4q/q-claude-skills.git -
DreamLayer-Eval
AI repositoriesDreamLayer Eval: open-source benchmarking for image and video diffusion models. Automate prompts, seeds, and metrics for reproducible results. A research project from DreamLayer AI (dreamlayer.io).
git clone https://github.com/TheDesignFounder/DreamLayer-Eval.git -
ChatGPT-Prompts
AI repositoriesChatGPT and Bing AI prompt curation
git clone https://github.com/yokoffing/ChatGPT-Prompts.git -
skill-optimizer
SkillsAgent Skills lifecycle toolkit: mine repeated coding-agent workflows, audit and personalize skills, and generalize personal skills for public release.
git clone https://github.com/hqhq1025/skill-optimizer.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.