Browse applications built on modern technologies. Explore PoC and MVP applications created by our community and discover innovative use cases for modern technologies.
ATLAS: An autonomous AI orchestrator for complex cloud infrastructures. It delegates tasks to AI agents via secure tools and projects real-time activity into a 3D digital twin, running on AMD GPUs.
IFI Gatehouse prices commercial fence bids. Open models on AMD read the documents, a deterministic engine calculates every dollar, and a named human authorizes each gate. When a document is silent, like a missing gate width, it asks instead of guessing.
HerFirst turns beginner software ideas into step-by-step project blueprints, coding prompts, testing and troubleshooting guidance, using AMD Token Factory AI when available with offline guidance as a fallback.
Automated RF test fault triage and measurement integrity assurance system powered by deterministic analytics, hybrid BM25 SOP retrieval, and AMD vLLM guardrails.
TrustForge is an autonomous software factory that builds, challenges, verifies, repairs and proves critical software behavior before it ships.
A 5-seat autonomous AI dark factory in Band Desktop that designed, coded, tested, and shipped all 4 stages of the Pocketful wallet service with zero human code commits. Achieved a perfect 193/193 test score with highest contiguous stage 4.
Transforms university lectures into 4-tier interactive concept mind maps, structured Markdown notes, and Socratic active-recall quizzes in real time using Assembly AI Universal-2 speech recognition.
A dashboard waits to be read. The First Officer reports to you: it speaks first, stops when you cut in, answers in under a second, carries out a spoken order and confirms it. Built on AssemblyAI Universal-3.6 Pro Realtime and the Voice Agent API.
An AI-assisted engineering governance layer built on IBM Bob 2.0 that analyzes change intent, repository architecture, contracts, and dependencies to validate software changes before coding agents write code.
AgentFlow is an AI Supervisor that verifies every AI-generated code change — running the real test suite, tracing failures, and fixing them — before a human ever has to trust a “done” claim.
RepoPilot is an agentic AI onboarding platform powered by IBM Bob 2.0. By simply pasting a GitHub URL, a new developer receives an autonomous architecture analysis, an interactive 8-step code tour with line-level citations, and a grounded Q&A interface.
AI-powered API migration guard and root-cause analysis agent built on IBM Bob 2.0 that eliminates cascading CI failure noise and verifies non-breaking migrations.
Flash Patch watches your Stripe integration for breaking API changes and ships the fix as a pull request before you ever see it break in production.
Git Lens mines your repository's history and uses AI to generate a narrated, significance-ranked onboarding tour, helping new developers understand the codebase quickly.
CodeGuard AI identifies code-risk hotspots, investigates bugs, independently verifies fixes with real tests, and builds reusable memory from only verified debugging incidents.
An autonomous 7-agent engine that decomposes monolithic codebases into cloud-native microservices with 100% verified behavioral parity, OpenAPI contracts, Docker/Helm scaffolding, and cryptographic migration passports. Modernize with proof, not faith.
ReleaseGuard AI is an AI-powered release safety platform that reviews code changes for security, infrastructure, database, cost, and testing risks. Its AI agents assess each release, flag issues, and recommend GO, CONDITIONAL, or NO-GO decisions.
A 3-Stage Remediation Pipeline, powered by IBM Bob, that checks and resolves software vulnerabilities given a code repository and a vulnerability report.
Rescue is an AI-native project recovery workflow that turns incomplete student codebases into prioritized, verified rescue plans to help ship projects before deadlines.
Meridian runs inside IBM Bob to reconstruct what is actually deployed, find version combinations nobody validated together, and prove the first integration failure in an isolated sandbox before production data is corrupted.
An AI-assisted incident-response prototype that turns a failing test and error log into explainable findings, a proposed-patch check in an isolated copy, and a postmortem draft—with human review and no auto-deployment.
SynQ connects scattered engineering knowledge—code, decisions, incidents, requirements, and people—into one intelligent platform, helping developers onboard faster, understand context, and make safer changes with grounded AI answers.
Scrum-Up is a centralized agile platform featuring AI-powered sprint planning, automated GitHub-driven skill profiling, real-time Kanban tracking, and smart retrospectives to streamline team collaboration.
Every new developer loses day one to a README that doesn't work. HUMBLE follows it on a clean machine, fixes what breaks, proves every fix from zero, then guides your team through setup, safely. Onboarding that just works, powered by IBM Bob.
Our project is a Repo Health & Onboarding Reporter , a developer tool designed to help teams understand and evaluate software repositories quickly.
PromptGold × IBM Bob: prompt QA that runs itself. Bob reads your prompt and its policy, writes the tests, attacks the prompt with parallel subagents, patches the leaks, and opens the PR — while a hook keeps the final "bless" in human hands.
RegTrace brings company policies into AI-assisted coding. It reviews Claude’s plan before implementation, checks the actual code afterward, applies supported fixes, and performs a fresh review against the policies supplied by the user.
FrestoDoc is an AI document intelligence platform that analyzes documents for risks, missing information and contradictions, provides evidence-backed insights, answers questions, and transforms important findings into actionable tasks.
Should you ship this code update? Release Captain gives you a clear go/no-go verdict — fast, automatic, and backed by evidence a human reviewer might miss.
Rowgate reads the API contract your partner actually signed - a spreadsheet - cites the exact cell a release branch breaks, and writes the failing test that proves it. Built with IBM Bob. A human decides what ships.