Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
EgoPro
Datasets & benchmarksHugging Face dataset by LightwheelAI
LightwheelAI/EgoPro -
Post-OCR-Correction
Datasets & benchmarksHugging Face dataset by PleIAs
PleIAs/Post-OCR-Correction -
opus5-5-doctor-patient-conversations-all-human-diseases
Datasets & benchmarksHugging Face dataset by nisten
nisten/opus5-5-doctor-patient-conversations-all-human-diseases -
AIRTBench-Code
Datasets & benchmarksCode Repository for: AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models
git clone https://github.com/dreadnode/AIRTBench-Code.git -
awesome-llm-apps
AI repositories100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git -
AutoMathText
Datasets & benchmarksHugging Face dataset by math-ai
math-ai/AutoMathText -
datachain
Agents & frameworksThe Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure
git clone https://github.com/datachain-ai/datachain.git -
10Kh-RealOmin-OpenData
Datasets & benchmarksHugging Face dataset by genrobot2025
genrobot2025/10Kh-RealOmin-OpenData -
dialogstudio
Datasets & benchmarksHugging Face dataset by Salesforce
Salesforce/dialogstudio -
fineweb-2
Datasets & benchmarksHugging Face dataset by HuggingFaceFW
HuggingFaceFW/fineweb-2 -
hacker-news
Datasets & benchmarksHugging Face dataset by open-index
open-index/hacker-news -
scroll-craft
SkillsAn agent skill for building premium, immersive, scroll-driven websites. Works with Codex, Claude Code, and other coding agents. Also available as a Claude Code plugin.
git clone https://github.com/nateherkai/scroll-craft.git -
oil-ui
SkillsUI design skill for Claude Code, Codex and other AI agents: explore distinct directions, compare them side by side, refine against real screenshots. 给 AI Agent 用的 UI 设计 Skill。
git clone https://github.com/oil-oil/oil-ui.git -
hass-mcp
MCP serversControl and query Home Assistant from Claude and other LLMs — a Model Context Protocol (MCP) server.
git clone https://github.com/voska/hass-mcp.git -
TrustLLM
Datasets & benchmarks[ICML 2024] TrustLLM: LLM trustworthiness evaluation across truthfulness, safety, fairness, robustness, privacy and ethics. Python/CLI toolkit for local models, compatible APIs and AI agent orchestration.
git clone https://github.com/HowieHwong/TrustLLM.git -
skills
SkillsReusable AI agent skills for software factories: explore ideas, write specs, implement, review, and run autonomous research. Works with Claude Code, Codex, and other skill-compatible agents.
git clone https://github.com/dzhng/skills.git -
yahoo-finance-data
Datasets & benchmarksHugging Face dataset by defeatbeta
defeatbeta/yahoo-finance-data -
LLaVA-Video-178K
Datasets & benchmarksHugging Face dataset by lmms-lab
lmms-lab/LLaVA-Video-178K -
Geographic API
Public APIsThe Geographic API extends the Semantic API, using a linked data approach to enhance location concepts used in The New York Times' controlled vocabulary and data resources which combine them with the GeoNames database, an authoritative and free to use database of global geographical places, names and features.
-
pile-of-law
Datasets & benchmarksHugging Face dataset by pile-of-law
pile-of-law/pile-of-law -
claude-protein-binder-design
Datasets & benchmarksHugging Face dataset by Anthropic
Anthropic/claude-protein-binder-design -
skrl
Agents & frameworksModular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments
git clone https://github.com/Toni-SM/skrl.git -
LongBench
Datasets & benchmarksHugging Face dataset by zai-org
zai-org/LongBench -
power-platform-skills
SkillsA plugin marketplace for GitHub Copilot and other AI agents that provides Power Platform development plugins, including reusable skills, agents, and commands for building and deploying solutions.
git clone https://github.com/microsoft/power-platform-skills.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.