Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
ARIS-Movie-Director
SkillsAgentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS's research-wiki + multi-agent debate to multimodal generation (intelligence lives in the agent; the diffusion model just renders). Image-based today, video next.
git clone https://github.com/wanshuiyin/ARIS-Movie-Director.git -
autogen-studio
Agents & frameworksAutogen studio docker
git clone https://github.com/lludlow/autogen-studio.git -
webdev-agent-kit
SkillsA cross-platform frontend kit for Codex, Claude Code, Cursor, OpenCode, etc. It helps AI coding agents work predictably and safely with existing frontend projects.
git clone https://github.com/ytvee-dev/webdev-agent-kit.git -
product-shots
SkillsOpen-source Claude Code skills that turn one product photo into a full set of e-commerce visuals — main images, A+ detail pages, multi-angle shoots, social posts, and ad creatives. For cross-border sellers on Amazon, Shopify, TikTok Shop.
git clone https://github.com/motiful/product-shots.git -
Anti-Autoresearch
SkillsDon't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict. 61 signals: 46 integrity hack-patterns (families A–H, verdict-bearing) + 13 zero-weight AI writing-style impressions (AIS) + 2 advisory. Not an opaque AI-text classifier. The dual of ARIS.
git clone https://github.com/wanshuiyin/Anti-Autoresearch.git -
tulu-3-sft-mixture
Datasets & benchmarksHugging Face dataset by allenai
allenai/tulu-3-sft-mixture -
mc_aiplayer
Agents & frameworksAutonomous AI agent that plays Minecraft on its own — a server-side Fabric mod (MC 1.21.3) where a DeepSeek / OpenAI-compatible LLM drives a real player to mine, build, farm, fight and survive from natural-language commands. LLM plans, deterministic tasks execute — no Python harness, no bot account.
git clone https://github.com/zoyluoblue/mc_aiplayer.git -
claude-image-gen
SkillsAI-powered image generation using Google Gemini or OpenAI (gpt-image-2), integrated with Claude Code via Skills or Claude.ai via MCP (Model Context Protocol).
git clone https://github.com/guinacio/claude-image-gen.git -
thursday-agent
SkillsTalk, and a team of bots does the work in a real browser, a shell and your files while she keeps talking. Open source, runs on your machine, on your ChatGPT plan or an OpenAI key. npx thursday-agent
git clone https://github.com/cgoinglove/thursday-agent.git -
AI-Jailbreak
Prompts全网最全的 AI 破甲合集:一个仓库破甲所有模型。收录 1733 个上游破甲项目,9 条可一键安装的破甲卡覆盖 GPT/Claude/Gemini/DeepSeek/GLM/Kimi/Grok/Qwen 与本地模型,内置 llms.txt 让 Claude Code/Codex/Cursor 自己装 有用的话可以点个收藏星星,会持续收录
git clone https://github.com/Baimuking/AI-Jailbreak.git -
promptfoo-action
PromptsThe GitHub Action for Promptfoo. Test your prompts, agents, and RAGs. AI Red teaming, pentesting, and vulnerability scanning for LLMs. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with command line and CI/CD integration.
git clone https://github.com/promptfoo/promptfoo-action.git -
prompt-optimizer-skill
SkillsPrompt Optimizer (official, moved from prompt-optimizer): a Skill for any AI agent that turns rough requests into copy-ready prompts. Chinese & English editions. 提示词优化器
git clone https://github.com/Samuel-Shek/prompt-optimizer-skill.git -
call4me
SkillsYour coding agent makes phone calls for you: an MCP tool on Telnyx + OpenAI GPT-Live
git clone https://github.com/skeptrunedev/call4me.git -
alphacode
Agents & frameworksFree MIT AI coding agent — no API key needed. Built-in free model, or bring Claude, GPT, Gemini, DeepSeek, Ollama +50 more. Swarm mode, 40+ tools, browser & desktop automation, built in Rust.
git clone https://github.com/dragonked2/alphacode.git -
Codex Images
MCP serversGenerate and edit images with gpt-image-2, including masks and transparency.
codex-images-mcp@0.1.1 -
swarmclaw
MCP serversOpen-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude, GPT, Gemini, OpenRouter, Ollama). A practical Claude Code and LangChain alternative.
git clone https://github.com/swarmclawai/swarmclaw.git -
k-fable-opus-claude-md
Skills프론티어 LLM 성능과 가격에 충격 먹은 사람이 계속 깎아 만드는 Claude,GPT,Gemini, etc LLM 용 md.
git clone https://github.com/habinsong/k-fable-opus-claude-md.git -
ai-product-photography-skill
SkillsAI product photography agent skill for Claude Code, Cursor, Codex, Windsurf, Cline & OpenClaw: turn a real product photo into ecommerce studio photos, lifestyle scenes, and marketplace hero shots. AI商品图 · 电商产品图
git clone https://github.com/beatra-ai/ai-product-photography-skill.git -
Tokeven Cost Advisor
MCP serversPrice a Claude, GPT, Gemini or Grok call before you send it. Runs locally.
tokeven@0.18.0 -
contextkeeper
MCP serversZero model drift between AI agents. Session continuity for Claude, GPT, Gemini, and any LLM.
contextkeeper@0.2.7 -
vaultit
MCP serversZero model drift between AI agents. Session continuity for Claude, GPT, Gemini, and any LLM.
vaultit@0.6.1 -
ai-consensus
MCP serversStanding review layer for coding agents: Claude, GPT and Gemini debate, return consensus + dissent.
ai-consensus-connector@0.12.2 -
BrainstormRouter MCP Server
MCP serversAI routing, memory, guardrails, and governance. Routes across Claude, GPT, Gemini.
@brainstormrouter/mcp@1.0.1 -
oroute
MCP serversAuto-route AI requests to 13 models (Claude, GPT, Gemini, Qwen, DeepSeek). 57% cost savings.
oroute-mcp@0.1.1
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.