Stars
An agentic skills framework & software development methodology that works.
RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
A construction kit for reinforcement learning environment management.
Fast inference engine for Transformer models
DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
Build resilient language agents as graphs.
A lightweight, powerful framework for multi-agent workflows
No fortress, purely open ground. OpenManus is Coming.
The official Java SDK for Model Context Protocol servers and clients. Maintained in collaboration with Spring AI
Specification and documentation for the Model Context Protocol
🔍 Search-o1: Agentic Search-Enhanced Large Reasoning Models [EMNLP 2025]
LlamaIndex is the leading framework for building LLM-powered agents over your data.
Langflow is a powerful tool for building and deploying AI-powered agents and workflows.
A Unified Toolkit for Deep Learning Based Document Image Analysis
The pytorch re-implement of the official efficientdet with SOTA performance in real time and pretrained weights.
A PyTorch impl of EfficientDet faithful to the original Google impl w/ ported weights
Heritrix is the Internet Archive's open-source, extensible, web-scale, archival-quality web crawler project.
Scrapy, a fast high-level web crawling & scraping framework for Python.
[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.
《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。
🦜🔗 The platform for reliable agents.
AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search