Stars
Code release for "Convolutional Two-Stream Network Fusion for Video Action Recognition", CVPR 2016.
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
The batteries-included agent harness.
Kubernetes shell: An integrated shell for working with the Kubernetes
TencentDB Agent Memory is a team-level memory hub for AI Agents — turning conversations, docs, and code into four reusable memory assets (Chat Memory, Skill, LLM-Wiki, Code-Graph) that are governed…
CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs
Cross-platform, customizable ML solutions for live and streaming media.
[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]
PTX ISA 9.1 documentation converted to searchable markdown. Includes Claude Code skill for CUDA development.
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation
Use Garry Tan's exact Claude Code setup: 23 opinionated tools that serve as CEO, Designer, Eng Manager, Release Manager, Doc Engineer, and QA
A powerful meta-prompting, context engineering and spec-driven development system that enables agents to work for long periods of time autonomously without losing track of the big picture
A framework for building realtime voice AI agents 🤖🎙️📹
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack, Discord, Gmail and other messaging apps,, has memory, scheduled jobs, and runs dir…
A lightweight triton-based General Matrix Multiplication (GEMM) library.
Tile primitives for speedy kernels
AI agents running research on single-GPU nanochat training automatically
Scholar All-In-One: A research infrastructure for AI agents
A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.
CUDA-L2: Surpassing cuBLAS Performance for Matrix Multiplication through Reinforcement Learning
Firefly: 大模型训练工具，支持训练Qwen2.5、Qwen2、Yi1.5、Phi-3、Llama3、Gemma、MiniCPM、Yi、Deepseek、Orion、Xverse、Mixtral-8x7B、Zephyr、Mistral、Baichuan2、Llma2、Llama、Qwen、Baichuan、ChatGLM2、InternLM、Ziya2、Vicuna、Bloom等大模型
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!