Stars
Universal LLM Deployment Engine with ML Compilation
ThetaEvolve: Test-time Learning on Open Problems, enabling RL training on AlphaEvolve/OpenEvolve and emphasizing scaling test-time compute
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Collection of extracted System Prompts from popular chatbots like ChatGPT, Claude & Gemini
Build memory-native AI agents with Memory OS — an open-source framework for long-term memory, retrieval, and adaptive learning in large language models. Agent Memory | Memory System | Memory Manage…
Production-ready platform for agentic workflow development.
Real-time webcam demo with SmolVLM and llama.cpp server
Lightweight coding agent that runs in your terminal
2-2000x faster ML algos, 50% less memory usage, works on all hardware - new and old.
No fortress, purely open ground. OpenManus is Coming.
This repository contains the Hugging Face Agents Course.
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek-R1, Qwen3, Gemma 3, TTS 2x faster with 70% less VRAM.
Synthetic data curation for post-training and structured data extraction
Conditional diffusion model to generate MNIST. Minimal script. Based on 'Classifier-Free Diffusion Guidance'.
HunyuanVideo: A Systematic Framework For Large Video Generation Model
Official implementation for "TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables" (NeurIPS 2024)
SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
The open source implementation of Gemini, the model that will "eclipse ChatGPT" by Google
🦜🔗 The platform for reliable agents.
chatGPT prompts and programs generated by chatGPT (OpenAI)