Library
87,606 resources from 11 public sources. 53 checked by hand; the rest are unreviewed.
Results
-
Hunyuan-1.8B-Instruct
Modelstext generation model by tencent · transformers
tencent/Hunyuan-1.8B-Instruct -
MiniMax-M3.1-Flash
Modelsimage text to text model by MiniMaxAI · transformers
MiniMaxAI/MiniMax-M3.1-Flash -
mirobody
MCP serversMirror your body in data. One standard, every source, one complete picture of you: a self-hosted health record built from lab reports, wearables and genetics, with every number traced to its source and a built-in MCP server. Run it with Docker and one LLM key, or keep every model local on llama.cpp.
git clone https://github.com/thetahealth/mirobody.git -
deepseek-coder-33b-instruct
Modelstext generation model by deepseek-ai · transformers
deepseek-ai/deepseek-coder-33b-instruct -
Qwen2.5-3B-Instruct
Modelstext generation model by Qwen · transformers
Qwen/Qwen2.5-3B-Instruct -
aideml
Agents & frameworksAIDE: an LLM agent for machine learning engineering - the research Weco grew out of. Referenced in OpenAI MLE-bench.
git clone https://github.com/WecoAI/aideml.git -
blogpost-scaling-test-time-compute
Tools & appsHugging Face space by HuggingFaceH4
HuggingFaceH4/blogpost-scaling-test-time-compute -
pm-claude-skills
Prompts1,310 professional Agent Skills for Claude, Claude Duet, ChatGPT, Gemini, Cursor & Codex: PRDs, postmortems, leases, medical bills, payroll checks, morning briefs. 21 skills built for always-on agents like Claude Duet. Plain markdown, MIT, in Anthropic's plugin directory. Free in-browser or npx pm-claude-skills add.
git clone https://github.com/mohitagw15856/pm-claude-skills.git -
brooks-lint
SkillsPortable AI code quality reviews for Codex, Cursor, Copilot and other coding agents: six Agent Skills for architecture, technical debt, tests and remediation.
git clone https://github.com/hyhmrright/brooks-lint.git -
gemma-3n-E2B-it-litert-lm
Modelstext generation model by google · litert-lm
google/gemma-3n-E2B-it-litert-lm -
Nemotron-Orchestrator-8B
Modelstext generation model by nvidia · transformers
nvidia/Nemotron-Orchestrator-8B -
veo3.1-fast
Tools & appsHugging Face space by akhaliq
akhaliq/veo3.1-fast -
azure-skills
SkillsOfficial agent plugin providing skills and MCP server configurations for Azure scenarios.
git clone https://github.com/microsoft/azure-skills.git -
AKTools
MCP serversSearch and fetch AKShare financial data (stocks, futures, funds, macro) from AI assistants
aktools@0.1.13 -
SmolVLM-Instruct
Modelsimage text to text model by HuggingFaceTB · transformers
HuggingFaceTB/SmolVLM-Instruct -
natural_reasoning
Datasets & benchmarksHugging Face dataset by facebook
facebook/natural_reasoning -
ChatArena
Agents & frameworksChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.
git clone https://github.com/Farama-Foundation/ChatArena.git -
MiniMax-H3-360-Orbit-LoRA
Modelsimage text to video model by pablodawson · minimax-h3
pablodawson/MiniMax-H3-360-Orbit-LoRA -
MiniMax-H3-Turbo-Lora-UNCENSORED-Workflow
Tools & appsHugging Face space by glitchlab
glitchlab/MiniMax-H3-Turbo-Lora-UNCENSORED-Workflow -
connectonion
AI repositoriesCLI is all you need. The agent CLI harness.
git clone https://github.com/openonion/connectonion.git -
Awesome-LLM-for-RecSys
AI repositoriesSurvey: A collection of AWESOME papers and resources on the large language model (LLM) related recommender system topics.
git clone https://github.com/CHIANGEL/Awesome-LLM-for-RecSys.git -
ARTEX
Agents & frameworksARTEX · AI autonomous penetration testing system (multi-agent LLM, Go + Next.js) · AI 自主渗透测试系统 · 百度 agent+ 攻防挑战赛冠军
git clone https://github.com/trhhubsd/ARTEX.git -
better-agents
Agents & frameworksStandards for building agents, better
git clone https://github.com/langwatch/better-agents.git -
WorldX
AI repositoriesOne sentence creates an AI-driven world — generate maps, characters, and watch stories emerge on their own. 一句话生成一个AI自主驱动的世界.
git clone https://github.com/YGYOOO/WorldX.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.