New Generation

This is a 12306 ticket search server based on the Model Context Protocol (MCP).

Immediate Mode 3D Plotting

This is a project that unifies the management of LLM APIs. It can call multiple backend services through a unified API interface, convert them to the OpenAI format uniformly, and support load balancing. Currently supported backend services include: OpenAI, Anthropic, DeepBricks, OpenRouter, Gemini, Vertex, etc.

Convert Lark Doc to Markdown

[ICCV'23] Efficient Region-Aware Neural Radiance Fields for High-Fidelity Talking Portrait Synthesis

A browser-based desktop where AI Agent operates every app through natural language.

The Underclassmen Opportunities repository is a curated list of internships, programs and resources aimed at freshmen and sophomores in tech‐related majors. The README explains that many companies have early‑career programs that do not require prior experience, and this project aggregates those opportunities for easy discovery.

[ICML'26 & COLM'26] Agent0 Series: Self-Evolving Agents from Zero Data

Python SDK for local and cloud background removal (pip install withoutbg)

飞牛影视PC版

We present StableAvatar, the first end-to-end video diffusion transformer, which synthesizes infinite-length high-quality audio-driven avatar videos without any post-processing, conditioned on a reference image and audio.

💼 Your own AI-powered voice interviewer for hiring.

AI Inference Operator for Kubernetes. The easiest way to serve ML models in production. Supports VLMs, LLMs, embeddings, and speech-to-text.

A Web Interface for chatting with your local LLMs via the ollama API

Highly compatible N64 emulator

[CVPR 2024] Official implementation of "Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction"

Build emails with a delightful DX

A Flask API For StreamMusic.

[CVPR2024, Highlight] Official code for DragDiffusion

vFlow 是一款为 Android 平台设计的、强大且高度可扩展的自动化工具。它允许你通过图形化界面，将一系列“动作模块”自由组合成强大的“工作流”，从而自动完成各种日常的、重复性的屏幕操作任务。

A collection of formalized statements of conjectures in Lean.

A framework for comprehensive diagnosis and optimization of agents using simulated, realistic synthetic interactions

Export pinned Arc Browser tabs for importing bookmarks into other browsers

Prove your self

[TMLR 2024] Efficient Large Language Models: A Survey

A memory plugin for AI coding that turns engineering experience, repository knowledge, and your way of working into memory that remains useful in future tasks.

Create, Evaluate, and Connect AI Skills

JoyCaption is an image captioning Visual Language Model (VLM) being built from the ground up as a free, open, and uncensored model for the community to use in training Diffusion models.

[ECCV`24&ICLR`25] CityGaussian Series for High-quality Large-Scale Scene Reconstruction with Gaussians