Library
85,340 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
sentence similarity model by sentence-transformers · sentence-transformers
sentence-transformers/paraphrase-multilingual-mpnet-base-v2 -
embeddinggemma-2-coreml
Modelsfeature extraction model by FluidInference · coreml
FluidInference/embeddinggemma-2-coreml -
jina-embeddings-v4
Modelsvisual document retrieval model by jinaai · transformers
jinaai/jina-embeddings-v4 -
brightdata-mcp
MCP serversBright Data's Web MCP server enabling AI agents to search, extract & navigate the web
@brightdata/mcp@4.8.0 -
firecrawl-mcp-server
MCP serversOfficial Firecrawl MCP server, the context API for AI agents: search, scrape, and interact with the web, plus parse, crawl, map, Agent and Monitor, from any MCP client.
git clone https://github.com/firecrawl/firecrawl-mcp-server.git -
Audio8-TTS-Preview-0.6b
Modelstext to speech model by Edge0 · transformers
Edge0/Audio8-TTS-Preview-0.6b -
google-maps-scraper-kit
SkillsFree, open-source Google Maps scraper for lead generation (Python, no API key, no Docker). Exports name, phone, email, website, rating and Instagram/Facebook/LinkedIn/TikTok/YouTube/X links to CSV. 100 places with emails in 44 s; --grid beats Google's 120 cap. MX email check, ad-pixel detection. Skill for Claude Code, Codex and Cursor.
git clone https://github.com/Mahanaicoach/google-maps-scraper-kit.git -
gte-multilingual-base
Modelssentence similarity model by Alibaba-NLP · sentence-transformers
Alibaba-NLP/gte-multilingual-base -
squad
Datasets & benchmarksHugging Face dataset by rajpurkar
rajpurkar/squad -
automatic speech recognition model by nvidia · nemo
nvidia/nemotron-speech-streaming-en-0.6b -
instructor-xl
Modelssentence similarity model by hkunlp · sentence-transformers
hkunlp/instructor-xl -
pdfmux
MCP serversPDF-to-Markdown extraction that audits its own output and flags any extractor's silent drops.
pdfmux@1.8.7 -
blink-8M
Modelsfeature extraction model by minishlab · model2vec
minishlab/blink-8M -
hacker-news
Datasets & benchmarksHugging Face dataset by open-index
open-index/hacker-news -
instructor-large
Modelssentence similarity model by hkunlp · sentence-transformers
hkunlp/instructor-large -
pdf-mcp
AI repositoriesAgentic RAG over one PDF or a whole folder, with page-level evidence to check every answer: hybrid search, selective page reads, tables, OCR, charts, and CJK layouts.
git clone https://github.com/jztan/pdf-mcp.git -
graphrag-rs
AI repositoriesGraphRAG-rs is a high-performance, state-of-the-art Rust implementation of GraphRAG (Graph-based Retrieval Augmented Generation) that builds knowledge graphs from documents and enables natural language querying with configurable entity extraction and local LLM integration
git clone https://github.com/automataIA/graphrag-rs.git -
Agent skills for LandingAI's Agentic Document Extraction (ADE) — production-ready document AI for agentic coding assistants
git clone https://github.com/landing-ai/ade-document-processing-skills.git -
OpenOrca
Datasets & benchmarksHugging Face dataset by Open-Orca
Open-Orca/OpenOrca -
graphlit-mcp-server
MCP serversModel Context Protocol (MCP) Server for Graphlit Platform
git clone https://github.com/graphlit/graphlit-mcp-server.git -
Fizgig
AI repositoriesFizgig — LoRA & Fine-tune Studio for Klein 9B, Krea 2, MiniMax H3, Qwen Image 2.1, Anima & Z-Image Turbo and Ace-Step XL: train, fine-tune, profile, repair and extract LoRAs & LoKR for Image, Video & Music Models
git clone https://github.com/shootthesound/Fizgig.git -
vela3-fast
Modelszero shot classification model by vllm-sr · transformers
vllm-sr/vela3-fast -
office_oxide
AI repositoriesThe fastest Office document library for Python, Rust, Go, JS/TS, C# and WASM. DOCX, XLSX, PPTX, DOC, XLS, PPT. Up to 100× faster than python-docx/openpyxl/python-pptx. 100% pass rate on valid Office files. MIT/Apache-2.0.
git clone https://github.com/yfedoseev/office_oxide.git -
hermes-function-calling-v1
Datasets & benchmarksHugging Face dataset by NousResearch
NousResearch/hermes-function-calling-v1
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.