Browse applications built on modern technologies. Explore PoC and MVP applications created by our community and discover innovative use cases for modern technologies.
ResearchOS is a multi-agent AI research laboratory that autonomously retrieves academic evidence, analyzes literature, identifies research gaps, and generates evidence-grounded research reports.
Verity turns any claim into a traceable verdict. Multi-model consensus checks headlines, stats, and posts against real sources in seconds running live on AMD GPU's via Fireworks AI ,Gemma and Huggingface's APIs, open and inspectable, not a black box.
It helps the people to submit their issue to government by capturing them.
Local-first Rust proxy that intercepts AI agent tool calls over MCP, blocking destructive commands and obfuscated attacks via static policy + semantic LLM evaluation on AMD ROCm, with SQLite audit logging. Zero data exfiltration. 34 tests, containerized.
A cost-aware AI agent that routes each question to the cheapest backend that can answer it correctly — a free local model for simple tasks, Fireworks only when accuracy demands it.
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.
RampUp help developers understand unfamiliar codebases faster through architecture insights, repository intelligence, and implementation roadmaps by analyzing GitHub repositories using static code analysis and AI to generate personalized onboarding guides
AI-powered Engineering Intelligence Platform — analyzes GitHub repos and generates an explainable Engineering Score
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.
An aesthetic cognitive captioning workspace and real-time audio telemetry platform powered by Fireworks AI and AMD Cloud computing. Featuring multi-style subtitle tuning, instant Firestore sync, and dynamic interactive Recharts sentiment tracking.
Zuko is a multi-agent prediction engine that combines real-world statistical data with five ancient metaphysical systems to generate football match predictions. It provides an analytical framework for research and educational purposes.
Jardo is a voice-first assistant that supervises your coding agents (Claude Code, Gemini CLI): it reads your terminal, approves safe work, steers them back on track to user's goals, and talks in your language. Runs on Gemma on AMD Instinct GPUs via ROCm.
A real-time AI voice translator for live calls, turning multilingual conversations into instant speech, captions, and meeting intelligence.
RE-EVOLVE ON HGI is an Intelligence Operating System that orchestrates multi-agent AI workflows through intent-driven planning, adaptive routing, persistent memory, governance, and specification-driven engineering for heterogeneous AI infrastructure.
An AI document-compliance agent that turns raw English drafts into fully formatted UN Secretariat reports enforcing real DGACM/UN Editorial Manual rules using MiniMax M3 on AMD Instinct (via Fireworks AI) for fixes that need editorial judgement compliance
GemmaGate is a validation-gated routing agent that solves tasks locally when it can verify the answer, then escalates to Fireworks models only when needed to minimize token usage.
ForgeMind AI is an AI-powered software architecture assistant that transforms project ideas into complete technical blueprints, including system architecture, security recommendations, development roadmaps, and implementation guidance and etc.
An intelligent, 5-layer multi-model task orchestrator that routes queries to the most cost-effective path, reducing Fireworks API token consumption to near-zero while guaranteeing 100% accuracy.
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.
A video captioning pipeline that extracts frames, transcribes audio, &generates captions in 4 distinct tones formal, sarcastic, humorous-tech, and humorous-non-tech using Minimax M3 via Fireworks AI, with a built-in LLM self-judge & Streamlit demo UI.
An anti phishing and scam detector with inbuilt functionality of analysing threats and inbuilt facial deepfake detection
Knowledge Detective turns your company's scattered GitHub, Gmail, and Calendar history into a single, always-current AI brain with verified, citation-backed answers.
QuackVision AI is a multimodal video understanding platform powered by Google's Gemma via Fireworks AI.it combines vision,OCR, speech recognition, and AI reasoning to generate intelligent captions,summaries, hashtags, SEO keywords, and exportable reports.
6 specialized AI agents that tune your AMD CPU and GPU through natural language. Say "gaming mode, stay under 85°C" and the system reads your hardware, consults Groq AI, and applies the optimal power settings automatically in real-time.
Íris is a persistent AI Brain — one per user, auto-provisioned — that lives across your devices. Desktop, phone and watch become interchangeable "bodies" it sees, speaks and acts through, powered end-to-end by AMD-hosted Gemma.
An autonomous multi-agent security platform built with FastAPI and PySide6 that automates pentesting loops using LLMs accelerated by AMD Instinct GPUs and ROCm via Fireworks AI
Galaxy AI is a desktop application that analyzes hardware, recommends the best AI models, and enables seamless local or AMD Developer Cloud deployment, making advanced AI accessible to developers regardless of their hardware capabilities.
ProofGate coordinates five Band agents through structured `proofgate.band.v1` handoffs to plan, resolve, isolate failures, retry once, and deliver one terminal result.