Library
85,762 resources from 11 public sources. 54 checked by hand; the rest are unreviewed.
Results
-
Vision-Agents
Agents & frameworksOpen Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.
git clone https://github.com/GetStream/Vision-Agents.git -
image text to text model by autotrust · transformers
autotrust/AutoTrust-Decider-Pro-Vision-27B -
mlx-vlm
AI repositoriesMLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
git clone https://github.com/Neywa-Labs/mlx-vlm.git -
VisionHOPE
Modelsimage classification model by PSRben
PSRben/VisionHOPE -
Phi-3-vision-128k-instruct
Modelstext generation model by microsoft · transformers
microsoft/Phi-3-vision-128k-instruct -
vision-arena
Tools & appsHugging Face space by WildVision
WildVision/vision-arena -
text classification model by autotrust · vllm
autotrust/AutoTrust-Decider-Pro-Vision-27B-v1.1 -
Phi-3.5-vision-instruct
Modelsimage text to text model by microsoft · transformers
microsoft/Phi-3.5-vision-instruct -
dsh-vision-toolkit
Skills[dsh]为纯文本模型设计更强大的视觉工具箱:一行安装使用、粘贴图片直接识别、多张图片问答、截图到前端UI 还原等|DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI.
git clone https://github.com/Anionex/dsh-vision-toolkit.git -
sparrow
AI repositoriesStructured data extraction, instruction calling and agentic workflows with ML, LLM and Vision LLM
git clone https://github.com/katanaml/sparrow.git -
Ui.Vision MCP
MCP serversMCP server for browser and desktop automation: OCR, image recognition, real mouse and keyboard input
uivision-mcp-bridge@1.7.18 -
computer-vision-course
AI repositoriesThis repo is the homebase of a community driven course on Computer Vision with Neural Networks. Feel free to join us on the Hugging Face discord: hf.co/join/discord
git clone https://github.com/huggingface/computer-vision-course.git -
Janus
AI repositoriesJanus-Series: Unified Multimodal Understanding and Generation Models
git clone https://github.com/deepseek-ai/Janus.git -
image text to text model by meta-llama · transformers
meta-llama/Llama-3.2-11B-Vision-Instruct -
Realistic_Vision_V2.0
Modelstext to image model by SG161222 · diffusers
SG161222/Realistic_Vision_V2.0 -
DeepSeek-V4-Flash-Vision-Exp
Modelsimage text to text model by deepseek-ai · transformers
deepseek-ai/DeepSeek-V4-Flash-Vision-Exp -
This repo lists relevant papers summarized in our survey paper: A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models.
git clone https://github.com/JindongGu/Awesome-Prompting-on-Vision-Language-Model.git -
skyvern
AI repositoriesAutomate browser based workflows with AI
git clone https://github.com/Skyvern-AI/skyvern.git -
Realistic_Vision_V1.4
Modelstext to image model by SG161222 · diffusers
SG161222/Realistic_Vision_V1.4 -
modlens
SkillsThe first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件,为 DeepSeek、GLM 等纯文本模型外挂视觉能力,粘贴图片即得结构化 JSON 证据(OCR、版面、语义)。
git clone https://github.com/liustack/modlens.git -
text to image model by SG161222 · diffusers
SG161222/Realistic_Vision_V6.0_B1_noVAE -
agent-vision-toolkit
Skills为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode
git clone https://github.com/Anionex/agent-vision-toolkit.git -
aya-vision-8b
Modelsimage text to text model by CohereLabs · transformers
CohereLabs/aya-vision-8b -
awesome-japanese-llm
AI repositories日本語LLMまとめ - Overview of Japanese LLMs
git clone https://github.com/llm-jp/awesome-japanese-llm.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.