#Python

Dao-AILab

flash-attention

★ 24,920

Fast and memory-efficient exact attention. FlashAttention This repository provides the official implementation of FlashAttention and FlashAttention-2 from the following papers.

titanwings

colleague-skill

★ 24,715

将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0.

pyg-team

pytorch_geometric

★ 24,082

Graph Neural Network Library for PyTorch. For this, we load the Cora dataset, and create a simple 2-layer GCN model using the pre-defined GCNConv: We can now optimize the model in a training loop, similar to the standard PyTorch training procedure .

anthropics

knowledge-work-plugins

★ 24,014

Open source repository of plugins primarily intended for knowledge workers to use in Claude Cowork.

PrefectHQ

prefect

★ 23,845

Prefect is a workflow orchestration framework for building resilient data pipelines in Python.

verl-project

verl

★ 23,438

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework.

Skyvern-AI

skyvern

★ 22,997

Automate browser based workflows with AI. Automate Browser-based workflows using LLMs and Computer Vision Skyvern automates browser-based workflows using LLMs and computer vision.

1Panel-dev

MaxKB

★ 22,798

MaxKB is an open-source platform for building enterprise-grade agents. .

marimo-team

marimo

★ 22,780

A reactive notebook for Python : run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.

jundot

omlx

★ 21,764

LLM inference server with continuous batching & SSD caching for Apple Silicon, managed from the macOS menu bar.

Zeyi-Lin

HivisionIDPhotos

★ 21,528

HivisionIDPhotos: a lightweight and efficient AI ID photos tools. AI .

onnx

onnx

★ 21,486

Open standard for machine learning interoperability

KKKKhazix

khazix-skills

★ 20,660

数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: neat-freak 洁癖 (docs/memory closeout), hv-analysis, khazix-writer & more, Claude Code, Codex & 40+ agents.

SWE-agent

SWE-agent

★ 20,326

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024].

google

skills

★ 19,968

Google Skills provides agent instructions for working with Google Cloud and other Google products through supported tools and APIs.

pydantic

pydantic-ai

★ 19,961

AI Agent Framework, the Pydantic way. Yet despite virtually every Python agent framework and LLM library using Pydantic Validation, when we began to use LLMs in Pydantic Logfire, we couldn't find anything that gave us the same feeling.

Avaiga

taipy

★ 19,436

Turns Data and AI algorithms into production-ready web applications in no time.

huggingface

trl

★ 19,315

Train transformer language models with reinforcement learning. Built on top of the Transformers ecosystem, TRL supports a variety of model architectures and modalities, and can be scaled-up across various hardware setups.

nesquena

hermes-webui

★ 18,366

Hermes WebUI: to use Hermes Agent from the web or from your phone!

camel-ai

camel

★ 17,721

CAMEL is a research framework for studying how groups of AI agents communicate, cooperate, and scale.