Stars
Quickly make and deploy full-stack apps with database, auth, styling, storage etc. figured out for you. Add all primitives you want.
Unleash your creativity with Pixelorama, a powerful and accessible open-source pixel art multitool. Whether you want to create sprites, tiles, animations, or just express yourself in the language o…
A course on aligning smol models.
The HTML5 Creation Engine: Create beautiful digital content with the fastest, most flexible 2D WebGL renderer.
Tiny fast HTML5 game engine with many features and no dependencies. 🚂 Choo-Choo!
Lightweight CodeAgent‑based research assistant for the Hugging Face Hub
Get started with building Fullstack Agents using Gemini 2.5 and LangGraph
Open source alternative to Gemini Deep Research. Generate reports with AI based on search results.
DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execution, while contributing back to the open-source community.
Build, enrich, and transform datasets using AI models with no code
An open source deep research clone. AI Agent that reasons large amounts of web data extracted with Firecrawl
DeepTeam is a framework to red team LLMs and LLM systems.
VideoLLM-online: Online Video Large Language Model for Streaming Video (CVPR 2024)
We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20 via OpenAI’s APIs.
Vibe Coding Full-stack App Starter Template
A free, open-source SaaS app starter for React & Node.js with superpowers. Full-featured. Community-driven.
Full-Stack SaaS Boilerplate and Starter Kit for your next SaaS Projects
Improve safety, security, and privacy of AI systems at build, deploy and run stages.
Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMs
A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
OWASP Top 10 for Large Language Model Apps (Part of the GenAI Security Project)
Robust recipes to align language models with human and AI preferences
Supercharge Your LLM Application Evaluations 🚀
The open source post-building layer for agents. Our environment data and evals power agent post-training (RL, SFT) and monitoring.
A lightweight express.js server implementing OpenAI’s Responses API, built on top of Chat Completions, powered by Hugging Face Inference Providers.
Rubiks Cube parametrization model in Python
Code Agent for automated vulnerability intelligence research, built on Hugging Face's Open Deep Research architecture.