Python

Training neural models with structured signals.

Hybrid ML + physics model of the Earth's atmosphere

Code for "OnePose: One-Shot Object Pose Estimation without CAD Models", CVPR 2022

Official code, datasets and checkpoints for "Timer: Generative Pre-trained Transformers Are Large Time Series Models" (ICML 2024) and subsequent works

:zap: TensorFlowASR: Almost State-of-the-art Automatic Speech Recognition in Tensorflow 2. Supported languages that can use characters or subwords

allRank is a framework for training learning-to-rank neural models based on PyTorch.

Based on Nano-vLLM, a simple replication of vLLM with self-contained paged attention and flash attention implementation

微信公众号文章抓取 & Markdown 转换工具

Powerful analytics and cohort library using Redis bitmaps.

专注于代码审计skill，最小化轻量化skill，只负责安全边界。

Python package for graph statistics

Open Source Business Intelligence Tool

A Python library to inspect and modify the internal structure of a PDF file

[ICLR2026] Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework

Joint Semantic Detection and Dissemination Control of Phishing Attacks on Social Media via LLama- Based Modeling

Selects tests affected by changed files. Executes the right tests first. Continuous test runner when used with pytest-watch.

Lightweight models for real-time semantic segmentationon PyTorch (include SQNet, LinkNet, SegNet, UNet, ENet, ERFNet, EDANet, ESPNet, ESPNetv2, LEDNet, ESNet, FSSNet, CGNet, DABNet, Fast-SCNN, ContextNet, FPENet, etc.)

Google play scraper for Python inspired by <facundoolano/google-play-scraper>

SPLADE: sparse neural search (SIGIR21, SIGIR22)

A learning rate range test implementation in PyTorch

Media sorting tool to organize photos and videos from your camera in folders by year, month and day.

A physics-based multi-material FDM color system. Converts images to full-color 3D prints via calibrated light-transmission mixing. Supports 2-8 color systems with slicer-ready 3MF export (BambuStudio/OrcaSlicer).

An editing tool that uses AI to transcribe, understand content and search for anything in your footage, integrated with ChatGPT and other AI models

Python A2A is a powerful, easy-to-use library for implementing Google's [Agent-to-Agent (A2A) protocol](https://google.github.io/A2A/). It enables seamless communication between AI agents, creating interoperable agent ecosystems that can collaborate to solve complex problems.

ControlNet scheduling and masking nodes with sliding context support

Set of widgets to build dashboards for Django projects

Enterprise-grade deep research skill for Claude Code with 8-phase pipeline, source credibility scoring, and automated validation. Outperforms OpenAI, Gemini, and Claude Desktop in quality and verification.

Server for the ListenBrainz project, including the front-end (javascript/react) code that it serves and all of the data processing components that LB uses.