Filters

AI Models

Data

Redis Qdrant

Platforms

Streamlit Replit Vercel

Upcoming AI Hackathons
For Innovators & Creators

Meta LLaMA Applications

Browse applications built on Meta LLaMA technology. Explore PoC and MVP applications created by our community and discover innovative use cases for Meta LLaMA technology.

Bandwith

Bandwidth is an orchestration platform for AI coding agents. By treating specialized models like a synchronized band, it harmonizes code generation, testing, and deployment to instantly scale engineering capacity.

Lgtm Fire

Band Agentic MeshBand IntergrationsBERT+10

CONCIERTO

The Grand Band Hotel - staffed entirely by AI agents, coordinating over Band chatroom to fulfill customer requirements in real world hotel scenarios.

The Grand Band Hotel

AI/ML APIAuto-GPTGemini 3 Flash+5

FinOps Swarm

Six Band-coordinated AI agents that autonomously detect and reconcile financial discrepancies across legacy mainframe ERP, IBM TM1, and SQL systems, catching change order propagation failures the moment they happen, before Cognos ever runs a report.

Swarm Intelligence

Assistants APIBand Agentic MeshBand Intergrations+4

👤 Shadow-Orchestrator-Ransom-Worm-🪱

RANSOM.WORM 🪱 A swarm of Graveyard Agents that roam GitHub at night, reviving abandoned repositories. Every audit, repair, and pull request is sealed to an immutable WORM ledger. No deletes. No rewrites. Only provable resurrection.

Snapkitty collective

CodexClaude CodeLLaMA+3

Lumina — Embodied Spatial AI

A production-grade Multi-Agent System (MAS) that gives visually impaired users real-time spatial awareness, object memory, and voice-guided navigation — powered by computer vision, monocular depth estimation, and LLM-driven agent negotiation.

LUMINA

YOLOv8QdrantGroq+4

PostPilot: Multi-Agent Marketing Approval Workflow

PostPilot is a Band-native multi-agent workflow where 5 specialized AI agents — coordinator, compliance, analyst, strategist, and approver — collaborate inside a shared chat room to review, score, and approve marketing content before it ships.

loblobai

LangChainNVIDIALLaMA+2

AuraGrid — AI-Powered DePIN Migration Network

AuraGrid automatically migrates computing tasks between solar-powered nodes when power fails. Using LangGraph AI, a Band agent, and a 5-factor trust score, it keeps workloads alive across 20 nodes in 15 countries including Pakistan.

EANO World

Phi-3VercelLangChain+2

FinGuardAI fraud detection

FinGuardAI is an AI-powered financial security platform designed to detect fraud, monitor transactions, analyze spending patterns, and provide real-time insights, helping businesses and users manage finances securely, efficiently, and intelligently.

ctarius

ChatGPTDeepSeek V3LLaMA+1

Code Quorum: Agentic Pull Request Reviewers

Code Quorum deploys a specialized team of AI agents to automatically review your pull requests. From performance to security, our agents collaborate, debate, and deliver a single, unified verdict so you can merge with confidence and ship faster.

AI Solopreneur

AI/ML APIAntigravityDeepSeek V3+3

ClaimsChain

A collaborative AI system where specialized agents coordinate through Band to process insurance claims, detect fraud, verify policy coverage, calculate settlements, and maintain immutable blockchain audit trails.

DhinVortex

AI/ML APILangChainLlamaIndex+3

Autonomous Gemini 3.5 Market Research Agent

Autonomous market research agent utilizing Gemini 3.5 Flash and Streamlit. It executes a parallel ReAct loop using Bright Data's SERP & Web Unlocker APIs to search, scrape, and compile structured company dossiers from live web data.

Manifestation

AI StudioAI/ML APIBright Data Scraping Browser+17

AMS-Gemma4: Offline Antibiotic Stewardship AI

Offline antibiotic stewardship AI for Indian hospitals. Gemma 4 E2B with native function calling. Runs on 8GB laptop via Ollama. English and Tamil output. WHO AWaRe 2023 + ICMR India data integrated.

RxGuard

Gemini AIGemmaHuggingFace Spaces+1

Code Janitor

Code Janitor is an AI-powered code review and refactoring platform that detects bugs, suggests optimizations, visualizes codebases, and provides live previews, built with assistance from IBM BOB, IBM’s AI-powered development assistant.

Team Synergy

NVIDIACodexIBM+8

RepoGuardian AI

RepoGuardian AI is an AI-powered repository intelligence system that analyzes codebase changes, detects downstream impact, predicts risks, and generates self-healing fixes using graph-based dependency analysis and LLM-powered reasoning.

NovaHack

PineconeGemini 3 FlashGrok+6

BOB RaceData Engine: Complete F1 Data Engineering

This solution demonstrates how IBM Bob orchestrates complex data engineering workflows (5-stage medallion architecture with validation) while seamlessly integrating AI predictions via Watsonx.ai.

The Big Shorts

IBMIBM watsonx AssistantLLaMA

MeetIQ

MeetIQ is an AI-powered meeting intelligence platform that converts meeting audio into searchable transcripts, AI-generated summaries, action items, speaker recognition insights, and chatbot-assisted knowledge retrieval.

SemiColon

AgentOpsAI/ML APIChatGPT+14

Lobster Relay

Lobster Relay is an orchestration layer built on top of Lobster Trap that helps AI agents recover safely from policy violations. Safe requests pass through normally, while unsafe requests trigger explainable intervention.

Relay

Lobster TrapLLaMA

RosterAI: Workforce Optimization Engine

Finding the right talent for projects is slow and subjective. Roster AI uses IBM watsonx.ai and mathematical optimization to eliminate workforce bottlenecks, instantly matching employee skills to project needs across the entire organization.

Git Happens

LangChainLLaMArest api+5

Elith

Elith gives any AI model — Claude, Gemini, local LLMs — the same repo-aware intelligence that enterprise tools have natively, through a lightweight skill layer and smart context engine that loads only the files that matter.

Silo HQ

Mistral AIAnthropic ClaudeAntigravity+5

CODEORACLE

CodeOracle is an architectural decision support engine that helps engineers make confident decisions about unfamiliar codebases through multi-agent analysis.

codingersCar

IBM GraniteIBM watsonx AssistantIBM+3

EchoTwin – The Real-Time AI Communication Clone

EchoTwin is a real-time conversational AI agent that becomes your live communication twin. It doesn’t just transcribe or summarize—it actively listens, understands context, predicts intent, and speaks on your behalf in real time.

Leb-ai-dev

ChatGPTClaude CodeCodex+14

GHOST Chimera

local-first agent orchestration runtime. it acts as the user proxy, AI agent that is trained on the user's identity, local machine, emails and converts them into trainable datasets. a personal AI proxy (ghost)

INAN

AgentOpsAnthropic ClaudeChatGPT+11

ACMI: The Universal Memory Layer for AI Agents

Three keys per entity. One memory protocol. Every framework. Every model. One audit trail via Veea Lobster Trap. Production-proven across 9 agents over 30+ days.

madezmedia

Anthropic ClaudeAMD ROCmAntigravity+17

one-shot music video creator

Enter a topic, and a style, and then lyrics and a video is generated automatically

prompt-to-music-video

HuggingFace HubAMD ROCmAMD Developer Cloud+2

LUMEN - From topic to report

LUMEN is a multi-agent AI research assistant that takes any topic and autonomously plans, searches, extracts, analyzes, and writes a fully structured research report with citations — powered by CrewAI and AMD.

Latent Space Nomads

AMD Developer CloudQwen3LLaMA+3

Meridian: AI Engineering Platform for Teams

Meridian is an AI-first project management platform demo. It is powered by an AMD MI300X inference endpoint to provide a high-speed, context-aware AI assistant that acts as a PR Analyst, Sprint Coach, and an embedded autonomous coding agent.

Meridian Team

AMD Developer CloudLLaMAHuggingFace Spaces

Dissent: AI Red Team Workspace

Dissent turns authorized AI lab, CTF, or secure product context into evidence gaps, failure chains, adversarial agent debate, and writeup-ready next steps.

Anemos

AMD Developer CloudAMD ROCmQwen3+4

Forma — The Design Memory Layer for Vibe Coders

Forma is a Chrome extension that catches vague UI vocabulary in vibe coders' prompts on v0, Cursor, Lovable, and Bolt — rewriting them with canonical component terms. 7 agents on AMD MI300X: Llama 3.1 8B for real-time scoring, 70B AWQ for Memory Engine.

Forma

AMD ROCmAMD Developer CloudLLaMA+3

LIA — Autonomous AI with Evolving Identity

A modular autonomous AI agent inspired by the human brain. It features specialized LLMs for communication, coding, vision, and memory, with a Sims-inspired autonomy system of evolving traits, desires, dreams, and moods — running on AMD MI300X via ROCm.

LIA Project

AMD Developer CloudAMD ROCmQwen3+5

SOCrates

SOCrates is a multi-agent autonomous SOC analyst. Drop in a CVE — three AI agents fetch live threat intel, simulate the full attack path, and produce a MITRE ATT&CK–mapped IR report with a validated Sigma rule. Runs on AMD MI300X. Zero API fees.

git happens

CrewAILlama 3LLaMA+6

30apps loaded