A scalable, agentic-first, and HuggingFace-native RL framework for research (9k lines).

Self-hosted game stream host for Moonlight.

Steering vectors for transformer language models in Pytorch / Huggingface

Code for Base Models Can Reason by Taking a Cue From Training Data

An open-source AI accelerator, developed by AI: RTL, ISA, simulator, compiler and profiler in one repo. Runs Qwen3, LFM2.5 and Qwen3.5 on a Kintex-7 PCIe card.

This repository contains the Hugging Face Agents Course.

Code and data for the paper "Simulated Students in Tutoring Dialogues: Substance or Illusion?" (ACL 2026)

📖 This is a repository for organizing papers, codes and other resources related to Visual Reinforcement Learning.

Video-R1: Reinforcing Video Reasoning in MLLMs [🔥the first paper to explore R1 for video]

Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities. ACM Computing Surveys, 2026.

A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning. TPAMI, 2024.

Reverse engineer anything with agents, from app behavior down to native binaries.

Modular open-source brain for legged robots. Web UI for teleops, autonomous navigation, mapping & monitoring. 3D-printable hardware that runs on ROS2.

A Survey on Video Understanding Agents

Tiny LLMs, Q4, in the browser. WebGPU lab inspired by yangqi0/petitgpt.

Millisecond decisions, any domain: a 0.8B open "System 1" model that picks between your options with calibrated probabilities. One base, swappable LoRA adapters, on your own hardware.

Harness engineering beginner tutorial, from 0 to 1

Node Version Manager - POSIX-compliant bash script to manage multiple active node.js versions.

An agentic skills framework & software development methodology that works.

Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 250,000+ scientists worldwide. 177 ready-to-use validated skills plus 100+ scientific databases covering bio…

AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,400+ agentic skills. Includes CLI, local MCP, cat…

Learn AI Engineering! Learn it. Build it. Ship it for others.

The knowledge compiler. Raw sources in, interlinked wiki out. Inspired by Karpathy's LLM Wiki pattern.

A framework for long-running, unattended AI-driven development.

Agora: Git as Shared Memory for Collective AutoResearch (arXiv:2609.18094)

A curated list of 120+ LLM libraries category wise.