Filters

AI Models

Data

Redis Qdrant

Platforms

Streamlit Replit Vercel

Upcoming AI Hackathons
For Innovators & Creators

OpenAI Assistants API Applications

Browse applications built on OpenAI Assistants API technology. Explore PoC and MVP applications created by our community and discover innovative use cases for OpenAI Assistants API technology.

Simple Request Router

Uses Gemma 4 to classify complex vs. simple requests, and routes them to a local LLM / cloud provider as needed.

lone wizard

AMD Developer CloudAMD ROCmGemma+2

KhetAI

KhetAI is an offline-first AI tool that diagnoses crop diseases from a photo and gives Indian farmers treatment advice in their own language - no internet connection required, running entirely on local hardware

Jeopardy_500

GemmaAssistants API

Clark

Clark is a general-purpose autonomous web agent. Give it a goal in plain language and it opens a real browser, reasons through the task step-by-step, and executes actions.

Clark

GemmaAMD Developer CloudAI/ML API+1

ChipPilot AI – AI Engineering Workspace

ChipPilot AI is an AI-powered engineering workspace that accelerates ASIC, FPGA, and Analog IC development by generating RTL, creating testbenches, reviewing designs, assisting verification and expert semiconductor guidance.

ASICVision

Assistants APIChatGPTLlama 3.1+1

Curio

"Curio is an AI-powered news engine that filters global noise to deliver a hyper-personalized, formatted daily brief tailored to each user’s specific interests."

Curio

Gemini AIAnthropic ClaudeAssistants API+6

Phi Router

We built a highly optimised local inference engine that hits good accuracy on constrained hardware by using Python validation loops to intercept and correct LLM hallucinations on the fly.

Sunlight404

Assistants APIAI/ML API

Contract Guardian

Contract Guardian verifies whether a website's real network traffic matches the promises in its privacy policy — extracting checkable claims, capturing traffic, and grounding each verdict in actual evidence.

Benora

Assistants API

Central Finite AI

An AI operating system for IT operations that investigates incidents, generates T24 core-banking OFS messages and routines from plain language, and routes every action through human approval before it runs.

Citadel Labs

AI StudioAssistants API

RouteZero — Autonomous Incident Routing

Four-agent AI system that classifies production incidents, routes them to the right team, writes role-appropriate Jira tickets, and detects architectural patterns — all with a human approval gate before anything is sent.

Winchester

AI/ML APIAnthropic ClaudeAssistants API

Adaptive General-Purpose AI Agent

A hybrid Track 1 AI agent that routes easy tasks to local deterministic solvers and escalates harder tasks to Fireworks models, reducing token usage while maintaining accurate batch task processing across 8 challenge categories.

Mr and Mrs Smith

AgentOpsAMD Developer CloudAssistants API+1

AITinerary

Turn any travel idea into a complete trip. AITinerary uses AI to convert your preferences and Instagram/YouTube inspiration into personalized itineraries, hidden gems, budget planning, recommendations, and an intelligent travel companion.

Ctrl-C*Ctrl-V

AI/ML APIOpenAIAssistants API+16

AMD Hybrid Token-Efficient AI Agent

A hybrid AI agent that intelligently routes tasks between deterministic local solvers and LLM inference, reducing token usage while maintaining fast, accurate, and scalable responses across diverse task types.

radSnap

OpenAIAssistants APIAutoGen+1

GemmaCaption

GemmaCaption captions each video in four styles — formal, sarcastic, tech-humor, and everyday-humor — using only Google Gemma. For the humor styles it drafts several candidates and picks the best using its own scene description as a fact-check.

Humongous_kitten

Assistants APIGemmaHuggingFace Hub

YOUSUN Axion

YOUSUN Axion turns messy AI workloads into AMD-ready deployments by scanning code, detecting CUDA/ROCm issues, suggesting fixes, benchmarking improvements, and creating a professional readiness report.

Yousun Apexia

AI/ML APIAMD Developer CloudAMD ROCm+4

RAYS Studio: Decentralized Federated OSINT Network

RAYS Studio is a decentralized OSINT AI agent network powered by FOGR and Spectrally Bounded Zero-Gated Adapters, enabling secure, privacy-preserving client-side fine-tuning and real-time orthogonal knowledge aggregation without server bottlenecks.

RAYS

AI StudioAgentOpsAI21 Labs+11

Jarvis Partner Assistant

JARVIS Voice AI is a real-time, voice-first AI assistant that enables natural human conversations while intelligently orchestrating MCP servers and external tools to perform real-world tasks—all without requiring a keyboard or graphical interface.

digital masters

AI/ML APIAssistants APIAuto-GPT+1

ARIA - Automated Research Intelligence Agent

ARIA is a multi-agent AI system that synthesizes biomedical literature from PubMed and audits it for citation fraud, methodology drift, overstated claims, cross-paper contradictions, and reproducibility gaps, built on Qwen2.5-72B via vLLM on AMD MI300X.

Glitch Squad

LangChainAnthropic ClaudeMistral AI+7

TokenRouter: Cost-Efficient Multi-Model AI Agent

A general-purpose AI agent spanning 8 task categories (factual, math, sentiment, summarisation, NER, code debugging, logic, code generation) that minimizes Fireworks API tokens.

Saving Money

AgentOpsAI/ML APIAssistants API

Hybrid Token Efficient Routing Agent

A Dockerized AI routing agent that solves simple tasks locally and routes harder prompts to the cheapest suitable Fireworks model, reducing token usage while preserving answer quality.

Dagger

AI/ML APIAssistants APIAMD Developer Cloud

Inbound Routing

The only router that catches a bad answer before it finishes being wrong — aborting failing generations mid-stream, racing local vs. remote in real time, and cutting token costs 69% without losing accuracy.

Inbound Crew

ChatGPTClaude CodeCursor+3

Memory Twin AI

Memory Twin AI runs entirely on AMD hardware to retrieve personal stories and generate warm, natural chat responses in under a second, perfectly synced to a responsive 8-bit companion.

Infinite Builders

Assistants APIDeepSeek R1Codex+1

penny-agent

Smart hybrid AI agent: a free local router sends easy tasks to a bundled on-device model (zero API tokens) and only hard ones to Fireworks—clearing the accuracy gate at minimum token cost.

Lyon

AMD Developer CloudAssistants API

Achyrix: AMD Gemma Restaurant Intelligence

Achyrix uses AMD-hosted Google Gemma to turn restaurant demand, inventory, supplier, and reservation signals into explainable, approval-gated recommendations that help teams reduce waste and prevent stockouts.

Achyrix

AMD Developer CloudClaude CodeCodex+5

LabPiolet AI

LabPilot AI is an AI-powered laboratory safety assistant that identifies chemical, biological, and physical hazards, provides safety recommendations, and generates risk assessment reports to improve lab safety.

Fusion Minds

AMD Developer CloudAssistants APIChatGPT+9

NovaAI : General Purpose AI Assistant

NovaAI is a modern AI assistant powered by Fireworks AI that solves diverse natural language tasks including reasoning, summarization, coding, mathematics through an intuitive interface.

Khdamin btkhbya

GemmaAI/ML APIAssistants API

SignalSniper Multi Agent Forex Market Intelligence

SignalSniper AI currently focuses on Forex Markets and is designed to scale seamlessly to Equities, ETFs, Cryptocurrencies, Commodities, and Indices. Its modular multi-agent architecture enables seamless expansion to additional Global Financial Markets

primehack

Qwen3GPT-4Assistants API+7

Agentic EWS Advisory system

the app will help Smallholder farmers in agricultural zonesget seasonal forecast and advisories to reduce planting-window errors, crop failure, and increase uptake of insurance cover owing to emergence of climatic regimes. advisory tools

GEOAI Kenya

AMD Developer CloudAgentOpsAMD ROCm+4

FairPrice: AI Agents for Africa's Informal Economy

An AI-powered escrow marketplace solving cash-on-delivery risk for Africa's informal sellers; autonomous agents (ZEMA 360) run fulfillment and pricing on Qwen 3.7 Plus, served on AMD Instinct GPUs via Fireworks AI, live in production today.

Zema AI Labs

AgentOpsAI/ML APIAI Studio+11

DeliveryBoy AI

DeliveryBoy AI is an intelligent assistant for motorcycle couriers that optimizes routes, predicts demand, improves productivity, and increases road safety using AMD AI technologies and edge computing.

DeliveryBoy

AMD ROCmAssistants APIAI/ML API+4

EMOS — Enterprise Memory Operating System

EMOS turns meeting transcripts into structured, trackable organizational memory. It uses AI to extract decisions, action items, and commitments — then automatically tracks owners, deadlines, and blocked tasks so nothing said in a meeting gets forgotten.

The Quantum Crew

AI/ML APIAMD Developer CloudAssistants API+2

30apps loaded