Library
85,762 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
huginn-0125
Modelstext generation model by tomg-group-umd · transformers
tomg-group-umd/huginn-0125 -
scientific-agent-skills
SkillsTurn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering biology, chemistry, medicine, and drug discovery. Compatible with Cursor, Claude Code, Codex, Pi, Antigravity, and the open Agent Skills standard.
git clone https://github.com/K-Dense-AI/scientific-agent-skills.git -
LakonLab
AI repositoriesOfficial implementation of AsymFlow, pi-Flow, GMFlow
git clone https://github.com/Lakonik/LakonLab.git -
TwIL-8B
Modelstext generation model by webAI-Official · transformers
webAI-Official/TwIL-8B -
Phi-4-reasoning-plus
Modelstext generation model by microsoft · transformers
microsoft/Phi-4-reasoning-plus -
gt4-decomp
Agents & frameworksMatching decompilation of the Gran Turismo 4 (PS2) engine, AI-assisted. No game data included.
git clone https://github.com/gustavocanepa/gt4-decomp.git -
xVerify
Datasets & benchmarksxVerify: Efficient Answer Verifier for Reasoning Model Evaluations
git clone https://github.com/IAAR-Shanghai/xVerify.git -
OpenMathReasoning
Datasets & benchmarksHugging Face dataset by nvidia
nvidia/OpenMathReasoning -
GLM-TTS
Modelstext to speech model by zai-org · glm-tts
zai-org/GLM-TTS -
DeepMath-103K
Datasets & benchmarksHugging Face dataset by zwhe99
zwhe99/DeepMath-103K -
iris-3b
Modelstext to image model by speridlabs · pytorch
speridlabs/iris-3b -
Dramabox
Modelstext to speech model by ResembleAI · ltx-audio-tts
ResembleAI/Dramabox -
matryca-plumber
AI repositoriesLocal-first AI daemon for Logseq OG: background semantic indexing, link hygiene, and agent-ready CLI/MCP — edits Markdown on disk (no cloud, no Logseq API). Karpathy LLM-Wiki inspired.
git clone https://github.com/MarcoPorcellato/matryca-plumber.git -
paseo-matt-workloop
SkillsPaseo 多 Agent workloop:整合 Matt Pocock skills,支持 npx 安装与更新。
git clone https://github.com/suntianc/paseo-matt-workloop.git -
fermat-mcp
MCP servers🚀 Fermat MCP: The Ultimate Math Engine - Unifying SymPy, NumPy & Matplotlib in one powerful server! Perfect for devs & researchers.
git clone https://github.com/abhiphile/fermat-mcp.git -
papergraph-mcp
MCP serversPaperGraph MCP turns math papers into evidence-grounded reading maps for AI agents: extract results, trace proof evidence, plan reading order, and review external dependencies without guessing.
git clone https://github.com/lotchuazzz-crypto/papergraph-mcp.git -
mate
Agents & frameworksProduction-ready multi-agent orchestration engine built on Google ADK. Database-driven agent config, 50+ LLM providers, MCP protocol, persistent memory, web dashboard, RBAC.
git clone https://github.com/antiv/mate.git -
chembench
Datasets & benchmarksHow good are LLMs at chemistry?
git clone https://github.com/lamalab-org/chembench.git -
H3-Dials
Modelsmodel by MATLOWAI · minimax-h3
MATLOWAI/H3-Dials -
OpenThoughts3-1.2M
Datasets & benchmarksHugging Face dataset by open-thoughts
open-thoughts/OpenThoughts3-1.2M -
material-expressive-skill
SkillsAn AI Agent Skill for designing, implementing, and reviewing production-ready interfaces with Material 3 Expressive across Android, Flutter, Web, and other platforms. Covers expressive design principles, theming, motion, adaptive layouts, accessibility, and platform-aware implementation.
git clone https://github.com/asimawdah/material-expressive-skill.git -
OneBox
Agents & frameworksA free AI agent & toolbox for Android | 一站式安卓 AI 智能体 & 工具箱
git clone https://github.com/wangzhishou/OneBox.git -
OpenMathInstruct-1
Datasets & benchmarksHugging Face dataset by nvidia
nvidia/OpenMathInstruct-1 -
MathVista
Datasets & benchmarksHugging Face dataset by AI4Math
AI4Math/MathVista
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.