R_REDDYX.XYZ

Vision: open-source projects on GitHub

17 repositories on Vision, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.

// RELATED TOPICS

Multimodal 143Agent 547MCP 1601Openai 690LLM 2094Anthropic 452Deepseek 229Gemini 348VLM 50RAG 533Dsh Plugin 82AWS 39Azure 35Chatgpt 314
LibreChat-AI/LibreChat

LIBRECHAT: POWERFUL OPEN SOURCE AI CHAT

LibreChat is an advanced ChatGPT clone supporting agents, MCP, and numerous models. It allows switching models on the fly, using artifacts, code interpreter, and secure s

★ 47,135 · TypeScript
danny-avila/LibreChat

Enhanced GPT Chat

LibreChat — an open-source chatbot supporting many AI models, agents, message search, Code Interpreter, and secure multi‑user authentication.

★ 36,891 · TypeScript
bytedance/UI-TARS-desktop

Multimodal AI Stack

Open multimodal AI agent stack that unites cutting‑edge models and infrastructure for building autonomous agents.

★ 33,596 · TypeScript
Skyvern-AI/skyvern

Automate Web Tasks with AI

Skyvern-AI automates browser workflows using artificial intelligence.

★ 21,640 · Python
StarTrail-org/PixelRAG

PixelRAG: Pixel Search

PixelRAG replaces traditional web parsing with direct search in the pixel representation of pages, providing scalable and accurate data extraction.

★ 10,946 · Python
aiming-lab/SimpleMem

MEMORY FOR AI AGENTS

SimpleMem — efficient long-term memory for LLM agents with support for text and multimodal data.

★ 3,878 · Python
valentinfrlch/ha-llmvision

Visual Intelligence for Home

ha-llmvision brings visual intelligence to your home, enabling real‑time object, face and activity recognition for smarter automation.

★ 1,531 · Python
ysr666/dsh-vision-router

dsh-vision-router - VISION FOR AGENTS

Free vision chain for DeepSeek Harness agents: Q&A, grounding, OCR, and more. Single-command install, no Python, work with images like a regular tool.

★ 1,274 · JavaScript
Anionex/agent-vision-toolkit

Visual Toolkit for LLM

A library for text models that lets them 'see' images: recognize content, answer questions, restore UI, automate GUI, and integrate with agents.

★ 1,262 · Python
OpenMOSS/MOSS-VL

MOSS-VL: 11B MODEL FOR VIDEO

The open-weight MOSS-VL series of 11-billion-parameter models is designed for understanding long-form and streaming video in real time. It supports multimodal input and e

★ 833 · Python
mostafasadeghi97/design2code

DESIGN2CODE - Turn Screenshot to Code

Automatically converts any web design screenshot into clean HTML and CSS code using TypeScript.

★ 687 · TypeScript
SAOS-3624/dsh-see-now

Smart Screen Streaming to AI

Capture and stream screen content to AI efficiently by filtering unchanged frames and combining multiple frames into single images, minimizing token usage.

★ 644 · JavaScript
v-modal/vmodal_sdk_robotics

VMODAL SDK FOR ROBOTICS

vmodal_sdk_robotics — Python‑SDK for multimodal vision in robotics. It combines camera, LiDAR and IMU data into a single stream. Supports training models on synthetic and

★ 434 · Python
ALEEEHU/World-Simulator

WORLD SIMULATION IN AI

Large-scale survey of multimodal generative models for real-world simulation. 381 stars, IEEE TPAMI 2026.

★ 397
BBC-Esq/VectorDB-Plugin

VECTORDB-PLUGIN: DOCUMENT SEARCH

Ask questions about your documents, audio, and video — get instant answers thanks to vector search in Python.

★ 372 · Python
OpenRaiser/PaperFit

PAPERFIT — AI Agent for Article Typesetting

Automatically compiles, renders, and fixes errors in LaTeX typesetting of scientific articles using AI.

★ 337 · TeX
gonemedia/aipointer

AI ASSISTANT ON SCREEN

Hold the hotkey, ask the AI about screen content — get an instant answer. Supports OpenRouter, Claude, OpenAI, Gemini, locally with no telemetry.

★ 246 · TypeScript

New projects on this topic in Telegram

Telegram →
Vision — 17 open-source GitHub projects | REDDYX AI