Browse applications built on modern technologies. Explore PoC and MVP applications created by our community and discover innovative use cases for modern technologies.
BandOps is an enterprise-grade command center that replaces siloed human panic with an orchestrated swarm of adversarial AI agents. Powered by Band, it resolves multi-million dollar aviation crises in seconds with immutable human-in-the-loop oversight.
EscrowGuard is a multi-agent system for high-value escrows. It uses PydanticAI, CrewAI, and LangGraph to analyze risks (OFAC/PEP) and allows compliance officers to resolve false positives by collaborating with AI on Band Pro.
BlackBox Labs is an AI infrastructure control plane that orchestrates multi-agent workflows with model routing, fallback recovery, observability, analytics, and Band.ai integration.
Voyage AI is an AI-powered travel planning platform that generates personalized itineraries, destination insights, weather forecasts, budget estimates, and smart recommendations to help travelers plan seamless trips worldwide.
Bedrock is a claim-level fact checker for enterprise deployment of AI-generated text. Paste an AI-written memo, brief, or summary, and it verifies each atomic claim against live web evidence with verdicts and source receipts.
We do a benchmark on the real data of selling cs go cases, to show how good the models are doing the trades comparsion to how human would do.
A control tower to deploy, monitor and audit autonomous AI agents before they touch production workflows.
Agent Testnet is an open-source sandboxed parallel internet for AI agents: a self-contained world of fake services where agents can browse, interact, and break things - phishing, prompt injections, destructive tool calls - without touching the real web.
Guardian AI est un espace de travail intelligent de conformité et de gouvernance qui analyse les documents d’entreprise en temps réel grâce à Gemini, détecte les risques de sécurité et les données sensibles et bien d'autres
AxiomGuard is a zero-trust Neuro-Symbolic AI Governance Control Plane that secures enterprise workflows. By combining Veea Lobster Trap DPI with AxiomLNN policy verification, it prevents unsafe agent actions via cryptographic Decision Receipts.
"AgentGuard is an enterprise-grade AI agent security monitoring platform delivering real-time threat detection, policy enforcement, audit trails, and governance dashboards for safe, compliant agent workflows."
An AI-powered visual modernization platform that maps complex codebase architectures and instantly refactors legacy scripts into production-ready, modern code.
odebase Time Machine turns any Git repository into a queryable knowledge base. Ask why code exists, scrub through file history, auto-generate ADRs, and chat with AI-synthesized profiles of past contributors, all powered by IBM Bob.
LeviathanMatrix is an accountability and execution-control layer for AI agents, turning high-value agent actions into policy-bound, auditable, attributable, and arbitration-ready execution records.
Governance.AI is an AI governance and observability platform that helps developers monitor, trace, audit, and control autonomous AI agents using real-time governance workflows, policy enforcement, SDK integrations, and observability infrastructure.
An elite multi-agent AI platform that autonomously plans, reasons, collaborates, and executes real-world tasks using advanced orchestration, memory, and adaptive intelligence — designed to redefine how humans interact with AI agents.
AI-powered TODO/FIXME scanner built entirely on Android. IBM Bob analyzes code, generates reports, and exports session logs. Zero hardware cost.
Skill Gap Detector helps you understand how well your resume matches a job role. It highlights your strengths, shows what skills are missing, and gives simple suggestions to improve your chances.
XIO ProofOps Agent turns decks, contracts, policies, and voice transcripts into risk-ranked findings, verified citations, redlined safer language, hash-bound human approvals, and a downloadable DOCX proof pack. Compliance teams ship evidence, not chat.
Turn every IBM Bob session into replayable memory. CrumdBob captures Bob's repo analysis as a 9-file CRUMB pack with proof chain, SQLite-backed cross-session history, FastAPI dashboard, LLM-powered insights, and enterprise observability.
heyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyheyhey
ATLAS is an AI-powered autonomous travel intelligence platform that uses agentic workflows to generate personalized itineraries, smart recommendations, and real-time travel insights for seamless trip planning.
An AI scientist that autonomously makes any PyTorch model faster on AMD MI300X — achieved a measured 2.93× speedup on Qwen2.5-7B without human input.
AUDITIA is an AI agent detecting opacity in Colombian public contracts. Built natively on JAX, Flax, and ROCm for the AMD MI300X , it uses an unsupervised Autoencoder to flag financial and semantic anomalies.
Solo builder shipping AI agent governance on AMD ROCm. Vaara is an open-source Python runtime that intercepts AI agent tool calls, scores risk with split conformal prediction, and writes a W3C PROV-JSON audit trail for EU AI Act Article 14 compliance.
Project Hyperion is an offline-first, adversarial multi-agent AI system delivering radiologist-level diagnostic triage. Powered by AMD MI300X, it features a 3-node consensus engine ensuring 100% data privacy and verifiable clinical accuracy at the edge.
Insight is an AI co-pilot for the operating room. Insight continuously ingests live video and voice to auto-generate operative notes, flag technical errors in real time, and surface intra-op decision support.