Skills for Real Engineers. Straight from my .claude directory.

Open-source LLM knowledge platform: turn raw documents into a queryable RAG, an autonomous reasoning agent, and a self-maintaining Wiki.

SoulX-Podcast is an inference codebase by the Soul AI team for generating high-fidelity podcasts from text.

🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!

Minimal reproduction of OneRec

React Flow | Svelte Flow - Powerful open source libraries for building node-based UIs with React (https://reactflow.dev) or Svelte (https://svelteflow.dev). Ready out-of-the-box and infinitely cust…

A tool&lib that can automatically convert OpenAPI documents into Higress remote MCP server configurations.

Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.

The open-source CapCut alternative

This project is the official implementation of 'DreamOmni2: Multimodal Instruction-based Editing and Generation (CVPR2026 Highlight)''

Zero-Config Code Flow for Claude code & Codex

The best ChatGPT that $100 can buy.

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

Master programming by recreating your favorite technologies from scratch.

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Implementation of [CVPR 2025] "DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation"

可商业化的 AI Web 平台，提供一站式人工智能服务解决方案。支持私有化部署，内置多用户管理，适合企业、团队或个人快速构建 AI 服务。

A React Rich Text Editor that's block-based (Notion style) and extensible. Built on top of Prosemirror and Tiptap.

Animation engine for explanatory math videos

InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Comflowyspace is an intuitive, user-friendly, open-source AI tool for generating images and videos, democratizing access to AI technology.

[AAAI 2025] Official implementation of "OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on"

[SIGGRAPH Asia 2023] Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation

Outfit Anyone: Ultra-high quality virtual try-on for Any Clothing and Any Person

Open-source Windows and Office activator featuring HWID, Ohook, TSforge, and Online KMS activation methods, along with advanced troubleshooting.

This repository contains a PyTorch implementation of "AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis".

[SIGGRAPH Asia 2022] VToonify: Controllable High-Resolution Portrait Video Style Transfer

The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

[CVPR'24 Highlight] Official PyTorch implementation of CoDeF: Content Deformation Fields for Temporally Consistent Video Processing