Hugging Face Spaces

Top Builders

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

Hugging Face Spaces

Hugging Face Spaces is a hosting platform for interactive machine learning applications. Developers build demos and tools using Gradio or Streamlit, then deploy them on Hugging Face infrastructure and receive a public URL. Spaces are free to run on shared CPU instances and can be upgraded to GPU-backed hardware for workloads that need faster inference. They are widely used during hackathons and AI events to share working prototypes without managing any server infrastructure.

General
Author	Hugging Face
Type	AI Application Hosting Platform
Website	huggingface.co/spaces
Documentation	Spaces Documentation
Hardware Options	CPU (free), T4, A10G, A100, H100
Frameworks	Gradio, Streamlit, Docker

Start building with Hugging Face Spaces

Spaces is the quickest path from a working model to a shareable demo. Connect a model from the Hub, wrap it in a Gradio interface, and push to a Space — the application goes live with a public URL in minutes. GPU instances are available on an hourly basis for workloads that need real compute. During hackathons on lablab.ai, submitting a Hugging Face Space link is a standard way to present a working project. Spaces created under an event's Hugging Face organization are publicly discoverable, and community members can vote with likes. Explore examples at Hugging Face Use Cases and Applications.

Hugging Face Spaces Tutorials

Getting Started

Spaces Overview How to create, configure, and deploy a Space
Gradio Documentation Build interactive UIs for ML models with minimal code
Streamlit Documentation Alternative framework for building data and ML apps
Spaces GPU Instances Upgrade a Space to GPU-backed hardware for faster inference
Docker Spaces Deploy any containerized application as a Space

Key Features

Instant deployment Push a Gradio or Streamlit app to a Space repository and get a live URL without any server configuration or DevOps setup.

GPU hardware tiers Upgrade to T4, A10G, A100, or H100 instances for workloads that need GPU acceleration. Pricing is hourly with no long-term commitment.

Organization Spaces Create Spaces under a team or event organization so project submissions stay grouped and discoverable by judges and community members.

Persistent storage Attach a storage volume to a Space for stateful applications that need to read or write files between requests.

Community discovery Spaces are publicly indexed on Hugging Face and sortable by likes, making them a practical way to share and showcase AI projects.

Boilerplates

Gradio Chatbot Template Starter Space for building a conversational AI interface
Streamlit App Template Starter Space for data and model visualization apps

Edit on GitHub

huggingface HuggingFace Spaces AI technology Hackathon projects

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

AI Credit Committee

AI Credit Committee, a multi-agent AI system designed to simulate how corporate loan decisions are made inside banks. In traditional banking, approving a corporate loan requires multiple experts reviewing the application, discussing risks, and reaching a consensus. This process is often slow, manual, and difficult to scale. Our goal was to recreate this committee digitally using AI agents that can analyze, debate, and recommend credit decisions just like a real credit committee. Corporate credit decisions are usually broken into multiple independent processes. Financial analysis is done by one team, risk assessment by another, and compliance checks by yet another group. Because these activities happen separately, decision-making becomes slow and fragmented. As a result, organizations spend significant time collecting information and coordinating discussions instead of making decisions. We wanted to create a system that brings all these perspectives together into a single collaborative workflow

ClaimGuard: Multi-Agent Insurance Claims System

ClaimGuard is a multi-agent auto-insurance claims system that treats data governance as a first-class collaboration problem, not an afterthought. Four agents — Intake, Assessment, Payout, and a Compliance Firewall — communicate entirely through Band. Most multi-agent demos pass full records down a fixed pipeline, leaking sensitive data (SSNs, medical details, bank accounts) to agents that never needed it. ClaimGuard inverts this: the Compliance Firewall is a queryable Band participant, not a preprocessing step. Before Assessment or Payout act on any claim data, they actively request clearance over Band — "I am Assessment, clear me for my role" — and the Firewall responds with only the fields that agent is permitted to see, plus a logged justification for every decision. The firewall itself is a deterministic policy engine, not an LLM—compliance decisions must be auditable and immune to prompt injection, not probabilistic. Intake extracts structured claims from free text and validates policy status; Assessment runs a RAG-powered Four-Point Coverage Analysis against real policy documents to approve, deny, or escalate; Payout simulates disbursement. Every firewall decision is logged with a field-level reason, producing a complete data-minimization audit trail

HomzDoctor – AI Healthcare Copilot

HomzDoctor is an AI-powered healthcare platform built to assist both patients and healthcare providers throughout the healthcare journey. Our goal is not to replace doctors but to help them make faster and more informed decisions. Patients can upload medical reports, lab results, X-rays, MRI scans, CT scans, and other healthcare documents. The platform processes this information and generates structured insights that can help doctors review cases more efficiently. A key part of our solution is the doctor verification layer. Any AI-generated finding must be reviewed and approved by a licensed healthcare professional before it is presented as a diagnosis or treatment recommendation. This ensures patient safety and keeps doctors in control of medical decisions. After doctor approval, HomzDoctor continues to support patients through several healthcare services. Patients can ask questions about their reports using an AI assistant, receive medication reminders, track adherence to prescriptions, find nearby pharmacies, and schedule appointments with healthcare providers. The platform uses a multi-agent architecture where specialized AI agents handle different tasks such as medical imaging analysis, diagnostic support, medication information, pharmacy services, appointment scheduling, and patient assistance. This approach makes the system more scalable and efficient. We built HomzDoctor to address common healthcare challenges such as delayed access to information, missed medications, difficulty understanding medical reports, and finding healthcare services quickly. Our team consists of three members who worked on designing the healthcare workflow, building the AI agent system, developing the backend and frontend applications, and integrating healthcare-related services into a single platform.

NexusCore

NexusCore is the governance brain and emergency brake that sits above AI agent teams. Built for the Band of Agents Hackathon, it addresses a growing enterprise risk: AI agents are no longer only suggesting code. They can generate patches, call tools, modify databases, deploy services, and trigger live actions faster than humans can review them. NexusCore adds governance before execution. When an agent proposes or attempts an action, the system classifies it into LOW, MEDIUM, or CRITICAL risk. LOW actions are allowed and logged. MEDIUM actions are held for review. CRITICAL actions are stopped and require explicit human confirmation before they can proceed. The system uses nine specialized agents collaborating through Band: Engineer/Builder, Proposer, Risk, Compliance, Security, Test, Infrastructure, Rollback/Audit, and Master. The Proposer Agent turns risky work into a formal proposal. Reviewer agents assess blast radius, reversibility, security, policy, test readiness, infrastructure impact, rollback plans, backups, and audit evidence. The Master Agent reads all findings and issues the final ALLOW or BLOCK decision. Band is central to the workflow, not just a notification layer. It acts as the shared collaboration room where agents exchange context, post reviews, coordinate decisions, and create a visible reasoning trail. The NexusCore dashboard mirrors this process with live workflow status, agent architecture, runtime interception, pending approvals, and an audit ledger. NexusCore demonstrates a practical enterprise use case for collaborative agents: making autonomous AI workflows safer, traceable, and human-governed before they touch production systems.

FUSION — AI-Powered VC Investment Committee

Every year, investors lose billions backing the wrong startups. WeWork, Theranos, and FTX all passed human due diligence — and all failed. The root cause is not a lack of intelligence. It is a coordination failure. The lawyer does not know what the engineer found. The finance team does not know about the pending lawsuit. Everyone works in silos, and critical risks fall through the gaps. FUSION solves this with a five-agent AI investment committee powered by Band AI. Each agent is a specialist: the Financial Partner audits burn rate, revenue concentration, and unit economics. The Legal Partner flags litigation, IP disputes, and regulatory violations. The Technical Partner checks the codebase for EOL software, security vulnerabilities, and compliance gaps. The Market Partner validates TAM claims and competitive headwinds. The Managing Partner chairs the committee, coordinates findings, and delivers the final verdict. What makes FUSION genuinely multi-agent is Band AI. Each partner operates in its own isolated Band room. They @mention each other to share findings and raise cross-domain conflicts in real time. When agents disagree, the Managing Partner triggers a debate round over Band WebSocket before synthesizing the final decision. The verdict is mathematically grounded — a weighted risk score across all four domains (Financial 30%, Legal 25%, Technical 25%, Market 20%) — with full citations, evidence quality scores, and auto-generated diligence questions for human follow-up. FUSION also exposes a full MCP server, so any AI tool — Claude, Cursor, or others — can trigger the entire committee with a single API call. No installation required. Built with LangGraph, FastAPI, Band SDK (thenvoi), Next.js, and deployed on Hugging Face and Vercel.

AuraGrid — AI-Powered DePIN Migration Network

AuraGrid is a decentralized physical infrastructure network (DePIN) that uses AI agents to keep computing workloads alive during power outages. When a node loses power, AuraGrid automatically detects the crisis, selects the best available node using a LangGraph AI state machine, migrates the task with zero data loss, and narrates every decision through a Band AI agent powered by Phi3 running locally via Ollama. Built for regions with unstable power grids — starting with 13 nodes across 10 African countries — AuraGrid ensures that solar-powered edge nodes collaborate intelligently to maintain uptime. How it works: 1. Edge nodes stream live telemetry (battery, CPU, RAM, power source) to the coordinator 2. LangGraph brain (4 states: MONITORING → CRISIS_DETECTED → MIGRATING → RESTORED) decides where to move the workload 3. Migration engine selects the highest trust score node as target 4. Band AI Agent narrates the decision live using Phi3 AI 5. Dashboard updates in real time showing all nodes across Africa Tech Stack: Node.js, Express, Socket.IO, PostgreSQL, Prisma, LangGraph, Phi3, Ollama, Band AI SDK, Next.js, Vercel, Render