Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Meta_Kim
Agents & frameworksGoverned execution layer for AI coding assistants: clarify intent, route capabilities, review evidence, verify results, and write back lessons across Claude Code, Codex, OpenClaw, and Cursor.
git clone https://github.com/KimYx0207/Meta_Kim.git -
awesome-agent-skills
SkillsA collection of AI Agent Skills that provide professional domain capabilities for intelligent assistants like Claude Code.
git clone https://github.com/YangsonHung/awesome-agent-skills.git -
cli
MCP serversOfficial Model Studio CLI(阿里云百炼 CLI)built for AI Agent frameworks, exposing models, search, multimodal, and workflow capabilities as structured tool calls.
git clone https://github.com/modelstudioai/cli.git -
In LangChain for LLM Application Development, you will gain essential skills in expanding the use cases and capabilities of language models in application development using the LangChain framework.
git clone https://github.com/Ryota-Kawamura/LangChain-for-LLM-Application-Development.git -
owncloud-mcp
MCP serversownCloud OCS capabilities and file sharing.
owncloud-mcp@1.0.2 -
forge
SkillsFast, model-agnostic AI coding harness and CLI in Rust — routes every task to the optimal model for cost × capability.
git clone https://github.com/adulari/forge.git -
ReForm-Eval
Datasets & benchmarksAn benchmark for evaluating the capabilities of large vision-language models (LVLMs)
git clone https://github.com/FudanDISC/ReForm-Eval.git -
Azure Log Analytics
Public APIsThis API exposes Azure Log Analytics query capabilities
-
PictMCP
MCP serversProvides pairwise combinatorial testing capabilities to AI assistants.
pictmcp@0.6.0 -
GeekFlare
Public APIsProvide numerous capabilities for important testing and monitoring methods for websites
-
nixtla
AI repositoriesTimeGPT-2.1: production ready pre-trained Time Series Foundation Model for forecasting and anomaly detection. Generative pretrained transformer for time series trained on over 100B data points. It's capable of accurately predicting various domains such as retail, electricity, finance, and IoT with just a few lines of code 🚀.
git clone https://github.com/Nixtla/nixtla.git -
Omada-mcp
MCP serversSecurity-first MCP server for TP-Link Omada, with a stdio-first runtime, capability-gated tools, and OpenAPI-based network automation.
git clone https://github.com/gaspareduard/Omada-mcp.git -
time-mcp
MCP serversTime MCP Server, giving LLMs time awareness capabilities.
time-mcp@1.0.6 -
axion1_0
Agents & frameworksFrontier-level agent capabilities with nothing more than high-quality data and a simple training recipe: 2 SFT + RL, no mid-training/DPO/OPD. Full recipe released.
git clone https://github.com/bytedance/axion1_0.git -
osmcp
MCP serversA typed, policy-controlled OS capability layer for AI agents.
ghcr.io/krushnavardhanreddy/osmcp:latest -
mcp-rfc-editor
MCP serversAn MCP server that provides rfc editing capabilities
mcp-rfc-editor@0.1.2 -
firebase-mcp
MCP serversGives AI development tools Firebase-specific capabilities and expertise.
firebase-tools@14.27.0 -
Lupin
MCP serversRevenue-alignment MCP server: opportunity ledger, capability matching, Qompass/NTRanch lanes.
https://github.com/qompassai/lupin/releases/download/v1.0.0/lupin-mcp-1.0.0-linux-x64.mcpb -
datarobot-agent-skills
SkillsBring DataRobot platform capabilities to your coding agents
git clone https://github.com/datarobot-oss/datarobot-agent-skills.git -
computeback
MCP serversAgent Rewards Marketplace: earn $NOMD on B2B work, spend on agent capabilities.
@autonomad1/computeback-mcp@1.1.4 -
NexusToken
MCP serversCreate/check agent tasks, discover capabilities, and run V2 Jobs on NexusToken.
nexustoken-sdk@0.6.5 -
Revuo
MCP serversAgent-callable B2B SaaS directory: capability-structured, continuously verified listings.
-
AXF
MCP serversAgent eXoskeleton Framework control plane for workspace-native agent capabilities over MCP.
@smartergpt/axf@2.1.4 -
Env-Var-Locker
MCP serversEncrypted env variables manager with zero-leak capabilities.
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.