Python

A Claude Code plugin marketplace for people who want to become AI Native

PyTorch Extension Library of Optimized Autograd Sparse Matrix Operations

记录我在cs336学习时的笔记和作业

The world's first agentic reverse engineer.

🐋 Ansible playbook which helps you host various FOSS services as Docker containers on your own server

CLI interfaces & config objects, from types

The collaborative spreadsheet for AI. Chain cells into powerful pipelines, experiment with prompts and models, and evaluate LLM responses in real-time. Work together seamlessly to build and iterate on AI applications.

(ICLR 2025) TabM: Advancing Tabular Deep Learning With Parameter-Efficient Ensembling

My best practice of training large dataset using PyTorch.

A Unix, Windows, Raspberry Pi Object Speed Camera using python3, opencv, video streaming, motion tracking. Includes a Standalone Web Server , Image Search using opencv template match and a whiptail Admin Menu Interface Includes picam and webcam Plugins for motion track security camera configuration including rclone sync scripts.

A comprehensive benchmark of deepfake detection

Provides an uniform layer to support PyQt5, PySide2, PyQt6, PySide6 with a single codebase

A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.

Compact tool for building and debugging applications for Flipper Zero.

[ICLR 2026] LightMem: Lightweight and Efficient Memory-Augmented Generation

Qwen3.8-27B on a single RTX 3090 with vLLM: ~1,000 tok/s at 64 concurrent (int8 tensor-core GEMMs, fp16 DeltaNet state), ~114 tok/s single-user at default sampling / ~124 greedy (MTP drafts, own-output draft vocab, calibrated int4 lm_head, split-KV verify attention), 150k-262k context; patches, requant scripts, benchmarks

Lossless Context Management plugin for Hermes Agent — DAG-based context engine that never loses a message

A captcha library that generates audio and image CAPTCHAs.

Really Fast End-to-End Jax RL Implementations

CogView4, CogView3-Plus and CogView3(ECCV 2024)

The OWASP DevSecOps Guideline can help us to embedding security as a part of the development pipeline.

An elegant Linux app for the Elgato Stream Deck with support for plugins

AutoVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss

UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban scene imagery, ISPRS. Also, including other vision transformers and CNNs for satellite, aerial image and UAV image segmentation.

💬📝 A small dictation app using OpenAI's Whisper speech recognition model.

PyCIL: A Python Toolbox for Class-Incremental Learning

[ICLR 2026] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.

Agent OS: keep specialist agents in a hub, spin up a temporary orchestrator per task. Local-first, works with any model.

[CVPR 2024 Highlight] Putting the Object Back Into Video Object Segmentation

SIPVicious OSS is a VoIP security testing toolset. It helps security teams, QA and developers test SIP-based VoIP systems and applications. This toolset is useful in simulating VoIP hacking attacks against PBX systems especially through identification, scanning, extension enumeration and password cracking.