Library
87,608 resources from 11 public sources. 54 checked by hand. The rest are indexed automatically and not reviewed.
Results
Looks like a goal we have a starting path for: I want to research potential clients
-
AssetOpsBench
MCP serversAssetOpsBench - Industry 4.0: A unified benchmark and framework for building, orchestrating, and evaluating domain-specific AI agents for Industry 4.0 asset operations and maintenance, with 460+ scenarios, 5 specialist agents (IoT, FMSR, TSFM, Work Order,...), and multi-agent orchestration blueprints (MetaAgent, AgentHive) over MCP.
Source for AssetOpsBench (opens github.com) git clone https://github.com/IBM/AssetOpsBench.git -
image text to text model by meta-models · transformers
Source for Muse-Spark-Open-816B-A42B-NVFP4 (opens huggingface.co) meta-models/Muse-Spark-Open-816B-A42B-NVFP4 -
fire-your-seo-agency
SkillsFire your SEO·GEO agency 🔥 A Claude Code skill that audits and optimizes SEO·AEO·GEO·LLMO·NEO(Naver) by itself — 월 50~350만 원짜리 'AI 검색 최적화' 대행, AI 에이전트가 대체합니다
Source for fire-your-seo-agency (opens github.com) git clone https://github.com/leopard627/fire-your-seo-agency.git -
WritingBench
Datasets & benchmarksWritingBench: A Comprehensive Benchmark for Generative Writing
Source for WritingBench (opens github.com) git clone https://github.com/X-PLUG/WritingBench.git -
ping_pong_bench
Datasets & benchmarksA benchmark for role-playing language models
Source for ping_pong_bench (opens github.com) git clone https://github.com/IlyaGusev/ping_pong_bench.git -
Adelie
Agents & frameworksA local-first multi-agent app development platform, built on PenguinHarness
Source for Adelie (opens github.com) git clone https://github.com/lmliheng/Adelie.git -
image text to text model by nvidia · Model Optimizer
Source for DeepSeek-V4.1-Flash-1017-NVFP4 (opens huggingface.co) nvidia/DeepSeek-V4.1-Flash-1017-NVFP4 -
concierge
MCP servers🚀 Universal SDK for building next-gen MCP servers
Source for concierge (opens github.com) git clone https://github.com/concierge-hq/concierge.git -
langfuse-java
Prompts🪢 Auto-generated Java Client for Langfuse API
Source for langfuse-java (opens github.com) git clone https://github.com/langfuse/langfuse-java.git -
HiMe
Agents & frameworksOne-Stop Personal Health AI Agent "Say Hi to Healthy Me"
Source for HiMe (opens github.com) git clone https://github.com/thinkwee/HiMe.git -
dsh-cost-meter
AI repositoriesCost tracking for DeepSeek Harness: session and model costs, token usage, budgets, provider balances, and coding-plan quotas. Bilingual English/Chinese UI.
Source for dsh-cost-meter (opens github.com) git clone https://github.com/Han-1413141/dsh-cost-meter.git -
mirage
Modelsimage text to text model by Cactus-Compute · cactus-compute
Source for mirage (opens huggingface.co) Cactus-Compute/mirage -
LoopArena
Datasets & benchmarksBenchmarking models as runtime Controllers for Loop Engineering
Source for LoopArena (opens github.com) git clone https://github.com/AMAP-ML/LoopArena.git -
flow-like
Tools & appsFlow-Like: Strongly Typed Enterprise Scale Workflows. Built for scalability, speed, seamless AI integration and rich customization.
Source for flow-like (opens github.com) git clone https://github.com/Rheosoph/flow-like.git -
EDDI
Agents & frameworksConfig-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 19+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus.
Source for EDDI (opens github.com) git clone https://github.com/labsai/EDDI.git -
comark
AI repositoriesComark is an open-source Markdown parser and renderer with components, attributes and plugins. It streams AI output to React, Vue, Svelte, Angular, HTML and the terminal.
Source for comark (opens github.com) git clone https://github.com/comarkdown/comark.git -
agents
Tools & appsAI agent tooling for data engineering workflows.
Source for agents (opens github.com) git clone https://github.com/astronomer/agents.git -
tossinvest-cli
MCP servers공식 API에 없는 30+ 기능까지, 터미널과 AI에서 쓰세요. 토스증권 비공식 CLI·MCP.
Source for tossinvest-cli (opens github.com) git clone https://github.com/JungHoonGhae/tossinvest-cli.git -
Awesome-Scientific-LLM-Benchmarks
Datasets & benchmarksA curated, accuracy-first list of benchmarks for evaluating LLMs on scientific reasoning and discovery — math, physics, chemistry, materials, biology, and agentic science.
Source for Awesome-Scientific-LLM-Benchmarks (opens github.com) git clone https://github.com/subinium/Awesome-Scientific-LLM-Benchmarks.git -
benchmark-qed
AI repositoriesAutomated benchmarking of Retrieval-Augmented Generation (RAG) systems
Source for benchmark-qed (opens github.com) git clone https://github.com/microsoft/benchmark-qed.git -
mcp-hub
MCP serversA centralized manager for Model Context Protocol (MCP) servers with dynamic server management and monitoring
Source for mcp-hub (opens github.com) git clone https://github.com/ravitemer/mcp-hub.git -
OpenRath
MCP serversAn open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.
Source for OpenRath (opens github.com) git clone https://github.com/Rath-Team/OpenRath.git -
Cradle
AI repositoriesThe Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.
Source for Cradle (opens github.com) git clone https://github.com/BAAI-Agents/Cradle.git -
graphlit-mcp-server
MCP serversModel Context Protocol (MCP) Server for Graphlit Platform
Source for graphlit-mcp-server (opens github.com) git clone https://github.com/graphlit/graphlit-mcp-server.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.