Library
85,766 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
whisper-large-v2
Modelsautomatic speech recognition model by openai · transformers
openai/whisper-large-v2 -
mobilegym
Datasets & benchmarks[EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted Android Simulator · Verifiable Evaluation · Scalable Online RL Training
git clone https://github.com/Purewhiter/mobilegym.git -
CozyClay
Agents & frameworksOpen source previs software in the browser: block a scene, pose characters, author camera moves and cuts, then take the same shots to an AI video model.
git clone https://github.com/HaD0Yun/CozyClay.git -
Qwen3-Next-80B-A3B-Instruct
Modelstext generation model by Qwen · transformers
Qwen/Qwen3-Next-80B-A3B-Instruct -
mobile-actions
Datasets & benchmarksHugging Face dataset by google
google/mobile-actions -
ZAYA1-8B
Modelsmodel by Zyphra
Zyphra/ZAYA1-8B -
StableBeluga2
Modelstext generation model by stabilityai · transformers
stabilityai/StableBeluga2 -
mcp
MCP serversBrowser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
git clone https://github.com/BrowserMCP/mcp.git -
stride-gpt
AI repositoriesAn AI-powered threat modeling tool that leverages OpenAI's GPT models to generate threat models for a given application based on the STRIDE methodology.
git clone https://github.com/mrwadams/stride-gpt.git -
Nanonets-OCR-s
Modelsimage text to text model by nanonets · transformers
nanonets/Nanonets-OCR-s -
mojo-dllm
AI repositoriesLocal inference for diffusion language models (LLaDA, Dream), written in Mojo
git clone https://github.com/vladimirrott/mojo-dllm.git -
Jev-Omni
Modelstext classification model by akhilaaa3 · transformers
akhilaaa3/Jev-Omni -
Flux-uncensored
Modelsmodel by kenerateai
kenerateai/Flux-uncensored -
shou_xin
Modelstext to image model by Datou1111 · diffusers
Datou1111/shou_xin -
gemma-4-26B-A4B-it-GGUF
Modelsimage text to text model by unsloth
unsloth/gemma-4-26B-A4B-it-GGUF -
cognee
SkillsCognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory with small models for free
git clone https://github.com/topoteretes/cognee.git -
Qwen3.5-9B-GGUF
Modelsimage text to text model by unsloth · transformers
unsloth/Qwen3.5-9B-GGUF -
text generation model by Qwen · transformers
Qwen/Qwen3-235B-A22B-Thinking-2507 -
open-science
SkillsThe open-source AI research workbench for scientific research and agent workflows. Local-first, model-agnostic desktop app with extensible skills, MCP tools and connectors, Python/R execution and traceable artifacts for reproducible research on macOS, Windows and Linux.
git clone https://github.com/aipoch/open-science.git -
IndexTTS-2
Modelstext to speech model by IndexTeam
IndexTeam/IndexTTS-2 -
mcp-unity
MCP serversModel Context Protocol (MCP) plugin to connect with Unity Editor — designed for Cursor, Claude Code, Codex, Windsurf and other IDEs
git clone https://github.com/CoderGamester/mcp-unity.git -
bge-reranker-large
Modelsfeature extraction model by BAAI · transformers
BAAI/bge-reranker-large -
nomic-embed-text-v1
Modelssentence similarity model by nomic-ai · sentence-transformers
nomic-ai/nomic-embed-text-v1 -
Douyin_TikTok_Download_API
MCP servers🚀 自托管的抖音、TikTok、B 站数据采集与无水印视频下载 API,支持 AI agent 通过 MCP 调用与离线语音转文字,Docker 一键部署。| Self-hosted TikTok, Douyin & Bilibili scraper and no-watermark video downloader — async REST API, MCP server for AI agents, CLI and web console, plus offline speech-to-text for downloaded videos. Self-healing identity pool, PostgreSQL archive, one docker compose up.
git clone https://github.com/Evil0ctal/Douyin_TikTok_Download_API.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.