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

A local AI assistant running on your device. It turns your files into actionable memory.

The first HEVC style Vision Transformer with advanced multimodal capabilities

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

Scaling Agentic Environments Automatically.

A Collection of Papers about Memory for Language Agents

Data Pipeline, Models, and Benchmark for Omni-Captioner.

NEO Series: Native Vision-Language Models from First Principles

ripgrep recursively searches directories for a regex pattern while respecting your gitignore

The complete stack for AI Engineers: framework, runtime and control plane.

Collection of extracted System Prompts from popular chatbots like ChatGPT, Claude & Gemini

Generate a timeline of your day, automatically

[ICCV 2025] OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning

[EMNLP 2024 Oral] Model Balancing Helps Low Data Training and Fine-tuning

Post-training with Tinker

MineContext is your proactive context-aware AI partner（Context-Engineering+ChatGPT Pulse）

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI…

Fully Open Framework for Democratized Multimodal Training

A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM

4DNeX: Feed-Forward 4D Generative Modeling Made Easy

Port of Facebook's LLaMA model in C/C++

Get up and running with OpenAI gpt-oss, DeepSeek-R1, Gemma 3 and other models.

🚀 Accelerate inference and training of 🤗 Transformers, Diffusers, TIMM and Sentence Transformers with easy to use hardware optimization tools

Fast and accurate automatic speech recognition (ASR) for edge devices

LLM inference in C/C++

🚀 Efficient implementations of state-of-the-art linear attention models