The repo is finally unlocked. enjoy the party! The fastest repo in history to surpass 100K stars ⭐. Join Discord: https://discord.gg/5TUQKqFWd Built in Rust using oh-my-codex.

The open source coding agent.

Awesome papers & datasets specifically focused on long-term videos.

This repository contains the toolkit for replicating results from our technical report.

The Ultimate Google Docs, Sheets, Drive, Gmail, & Google Calendar MCP Server. This MCP (primarily for use in Claude Desktop) gains full access to your google suite and lets claude do its thing.

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

MomentSeg: Moment-Centric Sampling for Enhanced Video Pixel Understanding

Virtual whiteboard for sketching hand-drawn like diagrams

✨✨Latest Advances on Multimodal Large Language Models

High-performance Inference and Deployment Toolkit for LLMs and VLMs based on PaddlePaddle

A gallery that showcases on-device ML/GenAI use cases and allows people to try and use models locally.

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

An open-source AI agent that lives in your terminal.

A curated list of Awesome-LLM-Ensemble papers for the survey "Harnessing Multiple Large Language Models: A Survey on LLM Ensemble"

Model Context Protocol Servers

The official Python SDK for Model Context Protocol servers and clients

[ICCV2025] DeRIS: Decoupling Perception and Cognition for Enhanced Referring Image Segmentation through Loopback Synergy

The official repository for ERNIE 4.5 and ERNIEKit – its industrial-grade development toolkit based on PaddlePaddle.

All the open source AI Agents hosted on the oTTomator Live Agent Studio platform!

An open-source AI agent that brings the power of Gemini directly into your terminal.

利用HuggingFace的官方下载工具从镜像网站进行高速下载。

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.

D2 is a modern diagram scripting language that turns text to diagrams.

Pocket Flow Project Template: Agentic Coding for Python

[AAAI2025 selected as oral] - Multi-task Visual Grounding with Coarse-to-Fine Consistency Constraints

Best practices & guides on how to write distributed pytorch training code

Lightweight coding agent that runs in your terminal

mindmap, mcp server, artifact

A curated list of Model Context Protocol (MCP) servers