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
-
labelhub-platform
MCP servers面向 LLM 训练数据生产的可信工作台:AI 提供证据、人类裁决,append-only 账本、可复现导出、评测关卡与 MCP Server。
Source for labelhub-platform (opens github.com) git clone https://github.com/Iceberg86-gb/labelhub-platform.git -
Groot-19B-A3B-261023
Modelsimage text to text model by GrootTeam · transformers
Source for Groot-19B-A3B-261023 (opens huggingface.co) GrootTeam/Groot-19B-A3B-261023 -
Ultra-FineWeb-L3
Datasets & benchmarksHugging Face dataset by openbmb
Source for Ultra-FineWeb-L3 (opens huggingface.co) openbmb/Ultra-FineWeb-L3 -
PhantomCrowd-Simulacra
Agents & frameworksPhantomCrowd AI Marketing Simulator 2026: Content Spread Forecasting with Local LLM
Source for PhantomCrowd-Simulacra (opens github.com) git clone https://github.com/charan820/PhantomCrowd-Simulacra.git -
SkillAlchemy
Agents & frameworksFrom thought to skill. From signal to structure.
Source for SkillAlchemy (opens github.com) git clone https://github.com/agentsope/SkillAlchemy.git -
open-intelligent-ui
AI repositoriesAn open-source take on ChatGPT's Intelligent UI: answers stream as interactive UI (maps, photos, charts, drawings and working tools). Built with OpenUI.
Source for open-intelligent-ui (opens github.com) git clone https://github.com/thesysdev/open-intelligent-ui.git -
curvine
AI repositoriesAI-native, cloud-native file system in Rust. Full POSIX on object storage with a multi-tier distributed cache, for AI training, inference, and agents. CNCF Sandbox project.
Source for curvine (opens github.com) git clone https://github.com/CurvineIO/curvine.git -
walkerOS
MCP serversOpen-source tag manager for developers and agents
Source for walkerOS (opens github.com) git clone https://github.com/elbwalker/walkerOS.git -
promptolution
PromptsA unified, modular framework for prompt optimization
Source for promptolution (opens github.com) git clone https://github.com/gepromptet/promptolution.git -
stoneforge
Agents & frameworksA web dashboard and runtime for orchestrating AI coding agents
Source for stoneforge (opens github.com) git clone https://github.com/stoneforge-ai/stoneforge.git -
UnrealGenAISupport
MCP serversUnreal Engine plugin for LLM/GenAI models & MCP UE5 server. OpenAI GPT-5, Deepseek R1, Claude Opus/Sonnet, Gemini 3, Grok 4, Alibaba Qwen, Kimi, ElevenLabs TTS, Inworld, OpenRouter, Groq, GLM, Ollama, Local, Meshy, Tripo, Hunyuan3D, Rodin, fal, Dashscope, Seedream. NPC AI, agentic, chat, 3D gen, TTS, multimodal, image gen. UnrealMCP/UnrealClaude
Source for UnrealGenAISupport (opens github.com) git clone https://github.com/prajwalshettydev/UnrealGenAISupport.git -
SGI-Bench
Datasets & benchmarksProbing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows
Source for SGI-Bench (opens github.com) git clone https://github.com/InternScience/SGI-Bench.git -
starling
AI repositoriesLocal AI in .NET, with no Python sidecar and no API key: embeddings, entity extraction, image and video search and chat on ONNX Runtime (CPU/CUDA), through Microsoft.Extensions.AI.
Source for starling (opens github.com) git clone https://github.com/starlinghq/starling.git -
doc-scraper
MCP serversGo web crawler to scrape documentation sites and convert content to clean Markdown for LLM ingestion (RAG, training data)
Source for doc-scraper (opens github.com) git clone https://github.com/Sriram-PR/doc-scraper.git -
CASSIA
PromptsCASSIA: A Multi-Agent LLM-Based Single-Cell Cell Type Annotation Framework
Source for CASSIA (opens github.com) git clone https://github.com/ElliotXie/CASSIA.git -
claude-prompts-mcp
PromptsMCP server for reusable prompt templates, multi-step workflow chains, and quality gates. Compose agentic workflows with an operator syntax; export as native skills to Claude Code, Cursor, OpenCode, and Gemini CLI.
Source for claude-prompts-mcp (opens github.com) git clone https://github.com/minipuft/claude-prompts-mcp.git -
GLiDE-27B
Modelsimage text to text model by fastino · transformers
Source for GLiDE-27B (opens huggingface.co) fastino/GLiDE-27B -
yzma
AI repositoriesGo with your own intelligence - Write Go applications that directly integrate llama.cpp for local inference using hardware acceleration on Linux, macOS, Windows, & WebAssembly.
Source for yzma (opens github.com) git clone https://github.com/hybridgroup/yzma.git -
Nemotron-3.5-Parse
Modelsimage text to text model by nvidia · transformers
Source for Nemotron-3.5-Parse (opens huggingface.co) nvidia/Nemotron-3.5-Parse -
text generation model by nvidia · transformers
Source for NVIDIA-Nemotron-Labs-Dory1.0-4B-GGUF (opens huggingface.co) nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4B-GGUF -
KohakuTerrarium
AI repositoriesKohakuTerrarium is a general-purpose AI agent framework and batteries-included app for building, running, and composing self-contained agents and multi-agent teams, with built-in tools, sub-agents, persistent sessions, TUI, and web UI.
Source for KohakuTerrarium (opens github.com) git clone https://github.com/Kohaku-Lab/KohakuTerrarium.git -
claude-reflect-system
SkillsContinual Learning & Self-improving skills system for Claude Code - learn from corrections, never repeat mistakes
Source for claude-reflect-system (opens github.com) git clone https://github.com/haddock-development/claude-reflect-system.git -
Cyrene-Agent
MCP servers一款开源、基于昔涟开发的桌面 AI 智能体/An open-source desktop AI agent based on Cyrene.
Source for Cyrene-Agent (opens github.com) git clone https://github.com/Playa-Cyrene/Cyrene-Agent.git -
AnyCrawl
AI repositoriesAnyCrawl 🚀: A Node.js/TypeScript crawler that turns websites into LLM-ready data and extracts structured SERP results from Google/Bing/Baidu/etc. Native multi-threading for bulk processing.
Source for AnyCrawl (opens github.com) git clone https://github.com/any4ai/AnyCrawl.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.