Library
86,219 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
ultranix-mcp
MCP serversSecure Linux desktop automation - input, screen/OCR/vision, AT-SPI2 UI tree, window, clipboard
ghcr.io/jxoesneon/ultranix-mcp:1.4.0 -
text to image model by Fictiverse · diffusers
Fictiverse/Stable_Diffusion_PaperCut_Model -
HunyuanWorld-1
Modelsimage to 3d model by tencent · diffusion-single-file
tencent/HunyuanWorld-1 -
Qwen-Image-2.1-Lightning
Modelstext to image model by lightx2v · diffusers
lightx2v/Qwen-Image-2.1-Lightning -
dalle-mini
Modelstext to image model by dalle-mini · transformers
dalle-mini/dalle-mini -
FIBO
Modelstext to image model by briaai · diffusers
briaai/FIBO -
Anima-2.9B
Modelstext to image model by Gazingstars123 · diffusion-single-file
Gazingstars123/Anima-2.9B -
Lyra-2.0
Modelsimage to 3d model by nvidia · lyra-2.0
nvidia/Lyra-2.0 -
noobot
Tools & appsCheap Money-Saving Self-hosted AI agent workspace with tool calling, MCP, multi-model routing, sandboxed execution, multi-agent workflows, and LLM-authored 3D character animation rendered with Three.js.
git clone https://github.com/xiayu1987/noobot.git -
zero shot image classification model by laion · open_clip
laion/CLIP-ViT-H-14-laion2B-s32B-b79K -
GPU Server
MCP serversMCP server for GPU monitoring: nvidia-smi, VRAM, utilization, temperature
gpu-server@0.2.2 -
synthetic-dataset-1m-dalle3-high-quality-captions
Datasets & benchmarksHugging Face dataset by ProGamerGov
ProGamerGov/synthetic-dataset-1m-dalle3-high-quality-captions -
lingbot-world-base-cam
Modelsimage to video model by robbyant · diffusers
robbyant/lingbot-world-base-cam -
humanizer
Modelstext generation model by jialinyyzz · gguf
jialinyyzz/humanizer -
Wan2.2-I2V-A14B-GGUF
Modelsimage to video model by bullerwins
bullerwins/Wan2.2-I2V-A14B-GGUF -
LTX-2.3-Workflows
Modelsimage to video model by RuneXX · ltx
RuneXX/LTX-2.3-Workflows -
elden-ring-diffusion
Modelstext to image model by nitrosocke · diffusers
nitrosocke/elden-ring-diffusion -
controlnet-openpose-sdxl-1.0
Modelstext to image model by thibaud · diffusers
thibaud/controlnet-openpose-sdxl-1.0 -
image to image model by akhaliq · diffusers
akhaliq/Qwen-Image-2.1-Multiple-Angles-LoRA -
robo-diffusion
Modelstext to image model by nousr · diffusers
nousr/robo-diffusion -
MVisionPro Engineering Tools
MCP serversRead-only machine-vision calculations for optics, interfaces, line scan, sensors, and models.
-
EXTRA - Native Computer Use
MCP serversFlashless macOS & Windows native computer-use engine for AI vision, mouse & keyboard automation
extra-desktop@0.2.5 -
Screen Control
MCP serversSafety-gated computer use for AI agents: screen OCR and vision, mouse, keyboard, window control.
-
podium-mcp
MCP serversMobile E2E MCP (51 tools): iOS + Android, native UI + canvas/WebGL, no-vision, RN debug
podium-mcp@0.4.0
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.