Stars
SoFlow: Solution Flow Models for One-Step Generative Modeling
An extremely fast Python type checker and language server, written in Rust.
Accelerating MoE with IO and Tile-aware Optimizations
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
An agent framework for building and evaluating general digital agents.
A benchmark for evaluating LLMs on open-ended CS problems. Exploring the Next Frontier of Computer Science.
The user-friendly command line shell.
A powerful coding agent toolkit providing semantic retrieval and editing capabilities (MCP server & other integrations)
A beautiful, simple, clean, and responsive Jekyll theme for academics
A latex template for writing statement-of-purpose for many schools at the same time
Fast TUI to browse Codex logs and jump straight into any session.
Lightweight coding agent that runs in your terminal
a benchmark tool for cloud object storage service
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
WFGY 2.0. Semantic Reasoning Engine for LLMs (MIT). Fixes RAG/OCR drift, collapse & “ghost matches” via symbolic overlays + logic patches. Autoboot; OneLine & Flagship. ⭐ Star if you explore semant…
A self-hosted, secure code execution sandbox for LLM agents deployed on your cloud infrastructure using SkyPilot. Built on llm-sandbox for multi-language code execution.
A high-throughput and memory-efficient inference and serving engine for LLMs
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, and more!
Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond
Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100% private RAG application on your personal device.
SkyRL: A Modular Full-stack RL Library for LLMs
UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)
Open-source implementation of AlphaEvolve