The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

Kedro is a toolbox for production-ready data science. It uses software engineering best practices to help you create data engineering and data science pipelines that are reproducible, maintainable,…

Claude Code skill implementing Manus-style persistent markdown planning — the workflow pattern behind the $2B acquisition.

MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.

💫 Toolkit to help you get started with Spec-Driven Development

FlashInfer: Kernel Library for LLM Serving

The absolute trainer to light up AI agents.

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

LLMs as Copilots for Theorem Proving in Lean

AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。

Get started with building Fullstack Agents using Gemini 2.5 and LangGraph

Tools for merging pretrained large language models.

🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

Seamless operability between C++11 and Python

vLLM’s reference system for K8S-native cluster-wide deployment with community-driven performance optimization

Tevatron - Unified Document Retrieval Toolkit across Scale, Language, and Modality. Demo in SIGIR 2023, SIGIR 2025.

🤗 smolagents: a barebones library for agents that think in code.

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

A PyTorch native platform for training generative AI models

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

A repository to host extended examples and tutorials

[WIP] Resources for AI engineers. Also contains supporting materials for the book AI Engineering (Chip Huyen, 2025)

SGLang is a high-performance serving framework for large language models and multimodal models.

A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation

MiniCPM4 & MiniCPM4.1: Ultra-Efficient LLMs on End Devices, achieving 3+ generation speedup on reasoning tasks

All-in-One: Text Embedding, Retrieval, Reranking and RAG in Transformers

Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

Fast and memory-efficient exact attention

Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.