Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
Looks like a goal we have a starting path for: I want to connect AI to my tools
-
zeroscope
Tools & appsHugging Face space by fffiloni
fffiloni/zeroscope -
onedrive-cli
MCP serversCommand line interface and MCP for OneDrive
git clone https://github.com/lionello/onedrive-cli.git -
SongPrep
Tools & appsHugging Face space by tencent
tencent/SongPrep -
Omost
Tools & appsHugging Face space by lllyasviel
lllyasviel/Omost -
official-mcp-servers
MCP serversA curated directory of 390+ official MCP servers from the companies behind the products. No unofficial forks, no abandoned projects.
git clone https://github.com/VoltAgent/official-mcp-servers.git -
design-studio
Agents & frameworksAn open source prototype sandbox for designers and product managers who build.
git clone https://github.com/itspatmorgan/design-studio.git -
face-swap
Tools & appsHugging Face space by tonyassi
tonyassi/face-swap -
llm-wiki
Tools & appsBuild Karpathy's LLM Wiki with Claude Code. L1/L2 cache architecture. Logseq + Obsidian support.
git clone https://github.com/MehmetGoekce/llm-wiki.git -
Florence-2
Tools & appsHugging Face space by gokaygokay
gokaygokay/Florence-2 -
Ilaria_RVC
Tools & appsHugging Face space by TheStinger
TheStinger/Ilaria_RVC -
spring-boot-skills
SkillsProduction-grade Claude Code and Codex skills for Spring Boot developers
git clone https://github.com/rrezartprebreza/spring-boot-skills.git -
agent-skills
SkillsNobody ships AI slop on purpose. These skills make sure you don’t.
git clone https://github.com/mblode/agent-skills.git -
notebook-intelligence
SkillsA JupyterLab extension supporting Claude Code, Copilot, Ollama, and OpenAI-compatible LLMs, with MCP, skills, plugins, and notebook agents.
git clone https://github.com/plmbr/notebook-intelligence.git -
aislop
Tools & appsCatch and fix the code-quality issues AI coding agents leave behind - dead code, unsafe casts, swallowed errors, duplication, security risks, and more. 50+ deterministic rules across 10 language targets, with CLI, CI, and GitHub Actions. No LLM at runtime. MIT.
git clone https://github.com/scanaislop/aislop.git -
vicoa
Agents & frameworksVicoa is the agentic IDE for running a team of coding agents from desktop, mobile, VPS. Open-source, self-hostable.
git clone https://github.com/vicoa-ai/vicoa.git -
ResolveLab
Agents & frameworksFault-injected tool environments with side-effect grading for evaluating and post-training LLM agents
git clone https://github.com/Ta0p1/ResolveLab.git -
FireRed-Image-Edit-1.0-Fast
Tools & appsHugging Face space by prithivMLmods
prithivMLmods/FireRed-Image-Edit-1.0-Fast -
cydonia
Tools & appsAgent control panel for Claude Code, Codex, OpenCode, Pi and 40+ agents with articles and boards supported
git clone https://github.com/crabtalk/cydonia.git -
ChatGPT-Workflows
PromptsChatGPT 与 Codex 的可验证工作流、断点交接、网页增强和本地工具
git clone https://github.com/RongNianXin/ChatGPT-Workflows.git -
styletts2
Tools & appsHugging Face space by styletts2
styletts2/styletts2 -
claude-debugs-for-you
MCP serversEnable any LLM (e.g. Claude) to interactively debug any language for you via MCP and a VS Code Extension
git clone https://github.com/jasonjmcghee/claude-debugs-for-you.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 -
claude-telegram-supercharged
MCP serversRun Claude Code 24/7 from Telegram. Drop-in upgrade for the official plugin: voice notes both ways, a self-healing daemon, memory across restarts, and Agentic Mode (watch every tool call live). One-line install.
git clone https://github.com/k1p1l0/claude-telegram-supercharged.git -
llm-wiki
Tools & appsLLM-powered knowledge base from your Claude Code, Codex CLI, Copilot, Cursor & Gemini sessions. Karpathy's LLM Wiki pattern — implemented and shipped.
git clone https://github.com/Pratiyush/llm-wiki.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.