Top Builders

Explore the top contributors showcasing the highest number of app submissions within our community.

Hugging Face

Hugging Face, Inc. is an AI company founded in 2016 by Clément Delangue, Julien Chaumond, and Thomas Wolf in New York City. Originally launched as a chatbot application, it pivoted to become the central open-source platform for the machine learning community. The Hub now hosts over one million models, datasets, and interactive applications, and the Transformers library has become the de facto standard for working with modern neural networks.

General
CompanyHugging Face, Inc.
Founded2016 by Clément Delangue, Julien Chaumond, and Thomas Wolf
HeadquartersNew York, NY, USA
Websitehuggingface.co
Documentationhuggingface.co/docs
GitHubgithub.com/huggingface
TypeAI Platform / Open-source ML Community

Start building with Hugging Face products

Hugging Face provides the model hub, deployment infrastructure, and open-source libraries that make up the standard developer workflow for modern AI applications. Whether you are loading a pretrained model, publishing a demo, or managing training data, Hugging Face has a product for each stage of the process. Explore what the community has built at Hugging Face Use Cases and Applications.

Core Products

The Hub

The Hugging Face Hub is a collaborative repository for models, datasets, and applications. Developers can host, version, and share any model type, including LLMs, diffusion models, embeddings, and classifiers. The Hub supports private and public repos, fine-tuned model versions, and model cards that document intended use and limitations.

For API reference, SDK documentation, and getting started resources, see our Hugging Face Hub tech page.

Transformers

The Transformers library is the most widely used open-source library for working with pretrained neural network models. It provides a unified API for loading, running, and fine-tuning models across text, vision, audio, and multimodal tasks. Over one million model checkpoints are available on the Hub for use with Transformers.

Spaces

Spaces lets developers build and host interactive ML applications directly on Hugging Face infrastructure. Most Spaces are built with Gradio or Streamlit and connect to models from the Hub. Spaces can be deployed on free shared CPU instances or upgraded to GPU-backed hardware for faster inference.

For deployment guides, GPU tiers, and examples, see our Hugging Face Spaces tech page.

Inference API and Endpoints

The Inference API provides access to hosted models over HTTP. A free tier is available with rate limits (around 50 requests per hour on popular models). The paid Inference Endpoints service offers dedicated, fully managed deployments starting around $0.60 per hour, suitable for production workloads that need consistent latency and throughput.

Diffusers

Diffusers is the Hugging Face library for diffusion models, supporting image, video, and audio generation. It provides pipelines for Stable Diffusion, FLUX, and other generative models with a consistent API for sampling and fine-tuning.

Datasets

The Datasets library provides efficient access to thousands of curated datasets hosted on the Hub. It handles streaming, caching, and preprocessing for large-scale training data and integrates directly with Transformers training pipelines.

Developer Resources

Hugging Face maintains extensive documentation, open-source libraries, and a large community forum for developers building on its platform.

Key Features

Unified model hub One repository format covers every model type, framework, and modality. Models download directly into Transformers, Diffusers, or any framework that supports the safetensors format.

Spaces for rapid prototyping Spaces deploys a Gradio or Streamlit app in minutes with no infrastructure setup, making it a practical choice for building demos and prototypes during hackathons and sprints.

Free inference access The shared Inference API lets developers test any public model without spinning up dedicated infrastructure, lowering the barrier to experimenting with new models.

Broad framework support Transformers supports PyTorch, TensorFlow, JAX, and ONNX, and integrates with training frameworks including Accelerate, PEFT, and TRL for fine-tuning workflows.

Use Cases

Rapid prototyping with pretrained models Developers use the Hub and Transformers to load state-of-the-art models in a few lines of code, enabling fast iteration during AI hackathons and project sprints.

Fine-tuning for specific tasks Teams fine-tune open-weight base models on domain-specific data using PEFT and TRL, then host the resulting adapters privately on the Hub.

Building and sharing AI demos Spaces provides a public URL for any Gradio or Streamlit application, making it straightforward to share working prototypes with collaborators, judges, or users.

Dataset management for training The Datasets library handles large-scale data efficiently with streaming and arrow-based caching, supporting training pipelines that cannot fit full datasets in memory.

Edit on GitHub

huggingface AI Technologies Hackathon projects

Discover innovative solutions crafted with huggingface AI Technologies, developed by our community members during our engaging hackathons.

AuraOS

AuraOS

Aura is a sovereign, neuro-symbolic AI operating system designed to make advanced artificial intelligence more transparent, efficient, collaborative, and accountable. Instead of sending every instruction directly to a language model, Aura can locally interpret natural-language intent, organize it into structured semantic and routing representations, identify relevant code or knowledge, and prepare a bounded task before model use is required. Aura combines deterministic routing, a 4,096-primitive lexical system, polysynthetic six-slot intent structures, visual code topology, guarded human-agent workflows, and a Learning Arena where verified experiences can be tested before becoming reusable knowledge. Its Observatory allows users to see how Aura understood an instruction, while the Human Agent Arena supports node-specific dialogue, approval gates, verification, and preserved attempt artifacts—including failed work that may help future refactoring. Aura is built around human authority. Models can propose, explain, investigate, and assist, but they cannot silently expand scope, bypass evidence requirements, or merge changes without approval. The result is an AI architecture focused not only on capability, but on sovereignty, inspectability, learning, and responsible action.

SOAP Copilot: AI Clinical Scribe on AMD

SOAP Copilot: AI Clinical Scribe on AMD

Physicians spend roughly two hours a day on clinical documentation, time pulled directly away from patient care, and a well-documented driver of burnout that costs the US healthcare system an estimated $8.3B a year in lost productivity. SOAP Copilot is a multi-agent AI system that turns a raw doctor-patient conversation into complete, structured clinical documentation in under 30 seconds. Three specialized agents, all built on Llama 3.3 70B Instruct, handle the pipeline in sequence: a SOAP Generator produces a structured Subjective/Objective/Assessment/Plan note, an ICD Coder extracts diagnosis codes with confidence scores, and a Summary Writer rewrites the note as a plain-language patient summary. The entire stack runs on open-source models, so no PHI ever needs to leave the user's own infrastructure. The project was originally prototyped and LoRA fine-tuned on a single AMD MI300X (192GB HBM3) via AMD Developer Cloud, running vLLM on ROCm 7.2. That memory headroom is what makes serving a 70B-parameter model in BF16 precision practical on one chip, something no consumer GPU and few cloud GPUs can do. For this submission, production inference is served through Fireworks AI, which itself runs on AMD Instinct hardware, so the project demonstrates the AMD AI stack end to end: self-managed fine-tuning through to hosted inference. Roadmap items include a distilled specialist model for lower-cost deployment, retrieval-augmented generation over clinical guidelines using the Qdrant vector database already wired into the architecture, and an on-premise, HIPAA-compliant deployment path for health systems that cannot send patient data to any external API.

Thymus

Thymus

Thymus is a lightweight hybrid token-efficient router designed to maximize accuracy while minimizing token costs in multi‑task LLM pipelines. It dynamically routes user queries across local and remote models on LLM providers. The general architecture of the router is as follows. 1. Classify: a fast regex/keyword pass handles the obvious cases for free; anything ambiguous falls back to the local model for classification. 2. Infer locally: the local model (Qwen2.5-3B-Instruct, GGUF, CPU) answers the query and self-reports a routing preference and confidence. 3. Verify: a task-aware verifier sanity-checks the answer (JSON structure, code execution, entity coverage, self-consistency, depending on task type). 4. Decide: LOCAL (free, done), SHEPHERD (local answer used as context, one cheap cloud pass to double check), or RESET (send straight to Fireworks).

CrosslaneAI

CrosslaneAI

CrosslaneAI is an agentic migration platform that autonomously ports CUDA codebases to ROCm/HIP, so teams can run their GPU workloads on AMD hardware without rewriting a single kernel by hand. For over fifteen years, the entire GPU computing world has been written in CUDA. That accumulated codebase — not the silicon itself — is the real reason teams stay locked to a single vendor. AMD's MI300X is genuinely competitive today, offering 192GB of HBM3 and far better price-per-hour economics, yet most organizations can't make the switch. The migration is manual, slow, error-prone, and expensive enough that it's typically handed to specialist consultants charging weeks of engineering time. PortForge productizes that migration and collapses it from weeks into minutes.

Verity — Fact-Checking for the Rest of Us

Verity — Fact-Checking for the Rest of Us

Most people believe first and verify never , there simply isn't time to check every headline, post, or forwarded message before deciding whether to trust it. That gap is where misinformation lives and spreads. Verity closes it. You give Verity a claim — a headline, a statistic, a line from an article — and it separates what's actually checkable from what's just opinion, then searches for independent evidence across 40+ public authoritative sources. Instead of trusting a single model's best guess, Verity requires independent checks to agree before returning a verdict: true, false, or somewhere in between, with a source trail you can click through and verify yourself. Every verification runs live on AMD Instinct hardware via the Fireworks AI API, using Gemma and other open-source models routed through a 5-pass consensus architecture — nothing pre-computed, nothing faked. The models are swappable and inspectable by design, because a trust tool that asks you to trust it blindly defeats its own purpose. Verity is built for the moment right before someone shares something they haven't checked , turning fact-checking from a newsroom luxury into something anyone can do in seconds.

Contxt

Contxt

Every AI grew a memory in 2026 — ChatGPT, Claude, Gemini, Copilot, Grok — but they're five walled gardens that never talk to each other, so you re-introduce yourself every time you switch. And every memory product (Mem0, Supermemory, Letta) is cloud-first and built for developers, not for you. Contxt is the consumer piece nobody built: one portable, privacy-first context layer that works across every AI, where your most sensitive data never leaves your device. A browser extension connects your Gmail, Calendar and Notion, then classifies every item on-device through a Crown-Jewels Gateway — Gemma 3 270M running in WebGPU plus a deterministic-rules safety floor. PRIVATE "crown jewels" stay local and end-to-end encrypted (the cloud is a blind relay of ciphertext, with keys transferred device-to-device by QR). SHARED context is distilled into reusable cards that any AI can read over MCP, and injected live into the composer on Claude, ChatGPT and Gemini. A companion web dashboard mirrors the extension in real time. One context layer. Every AI. Your data stays yours.