#vision Repositories
Discover 35 active open source GitHub repositories tagged with #vision, accumulating 252,035 total stars (averaging 7,201 stars per project). Leading this topic is LibreChat-AI/LibreChat with 47,384 stars.
35 repositories total
Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active
Xray, Penetrates Everything. Also the best v2ray-core. Where the magic happens. An open platform for various uses.
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/
The 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).
[ICML'26] SimpleMem: Efficient Lifelong Memory for LLM Agents โ Text & Multimodal
Open source hardware and software platform to build a small scale self driving car.
[CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.
Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.
Design a better vision toolkit and skills for text-only models to "see" images, supporting multi-image understanding, image Q&A, frontend UI restoration, GUI automation, etc., with optional seamless integration with multiple mainstream agents, and direct recognition of pasted images | A vision toolkit and skill designed for text-only LLMs โ 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
Shiping: Screenshot + AI to understand anything on your screen. Code, error messages, problems, charts, and foreign-language materialsโtake a screenshot with a keyboard shortcut and get an answer. Run it in the background as a desktop tool and select any area for instant recognition. In conversation mode, it understands questions in real time and provides key points for an answer. Use it as a desktop tool, interview assistant, exam assistant, or study practice assistant.
๐ MLKit is a powerful and easy-to-use toolkit. With ML Kit, you can easily implement features such as text recognition, barcode recognition, image labeling, face detection, object detection, etc.
CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks
A curated collection of iOS, ML, AR resources sprinkled with some UI additions.
3DMatch - a 3D ConvNet-based local geometric descriptor for aligning 3D meshes and point clouds.
This application can translate text captured from any application running on your computer.
๐ฐ A curated list of machine learning resources, preferably CoreML
Let AI see your screen in real time: filter frames by how much they change and combine multiple frames into one image, so static scenes use almost no tokens.
APCA (Accessible Perceptual Contrast Algorithm) is a new method for predicting contrast for use in emerging web standards (WCAG 3) for determining readability contrast. APCA is derived form the SAPC (S-LUV Advanced Predictive Color) which is an accessibility-oriented color appearance model designed for self-illuminated displays.
LLaVA-Mini is a unified large multimodal model (LMM) that can support the understanding of images, high-resolution images, and videos in an efficient manner.
Frequently Asked Questions
What is the most popular #vision repository on GitHub?
The top ranked open source #vision project on GitHub is LibreChat-AI/LibreChat with 47,384 stars. Enhanced ChatGPT Clone: Features Agents, MCP, Skills, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting. Active
Which programming languages are most used in #vision repositories?
Among the top ranked #vision projects on GitHub, the most common programming languages are Python, TypeScript, C++, JavaScript.
How is the #vision repository ranking calculated?
We track 35 active open source repositories tagged with #vision (500+ stars), totaling 252,035 stars with an average of 7,201 stars per repository. Rankings update daily from the GitHub API.