"rsync for cloud storage" - Google Drive, S3, Dropbox, Backblaze B2, One Drive, Swift, Hubic, Wasabi, Google Cloud Storage, Azure Blob, Azure Files, Yandex Files

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

Algebrica is free and open a mathematical knowledge base dedicated to clarity, structure, and conceptual coherence.

PaperBanana: Automating Academic Illustration For AI Scientists

A free, open source, and extensible speech-to-text application that works completely offline.

Flash Attention Triton kernel with support for second-order derivatives

文颜 MCP Server 可以让 AI 自动将 Markdown 文章排版后发布至微信公众号。

A modern, cross-platform, multi-threaded, and general purpose filesystem and disk-usage utility that is aware of .gitignore and hidden file rules.

CUDA Python: Performance meets Productivity

Generation of diagrams like flowcharts or sequence diagrams from text in a similar manner as markdown

Development repository for the Triton language and compiler

Ongoing research training transformer models at scale

Linux kernel source tree

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

The Enterprise-Grade Production-Ready Multi-Agent Orchestration Framework. Website: https://swarms.ai

Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

A feature-rich command-line audio/video downloader

AllenAI's post-training codebase

leaked prompts of GPTs

🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation

Imitation learning algorithms with Co-training for Mobile ALOHA: ACT, Diffusion Policy, VINN

Virtual whiteboard for sketching hand-drawn like diagrams

IoT DC3 is a fully open-source distributed Internet of Things (IoT) platform built on Spring Cloud. It accelerates IoT project development and simplifies IoT device management, providing comprehens…

Eclipse ThreadX is an advanced real-time operating system (RTOS) designed specifically for deeply embedded applications.

Crawl a site to generate knowledge files to create your own custom GPT from a URL

Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)

Run, manage, and scale AI workloads on any AI infrastructure. Use one system to access & manage all AI compute (Kubernetes, Slurm, 20+ clouds, on-prem).

🤖 Deploy a private ChatGPT alternative hosted within your VPC. 🔮 Connect it to your organization's knowledge base and use it as a corporate oracle. Supports open-source LLMs like Llama 2, Falcon, a…

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