Nikhilesh Singh@niksi

Built a production-grade FastAPI API gateway acting as a reverse proxy with JWT/API-key auth, token-bucket rate limiting (IP/Redis), structured logs, Prometheus metrics, circuit breaker for upstream failures, and consistent JSON error responses.

GitHub Actions CI/CD pipeline for automated security scanning and containerized deployments with real-time vulnerability reporting, integrating SAST, DAST, dependency, container, and secret scanning for end-to-end production-grade security.

AgentMesh AI is a production-oriented AI task execution platform focused on solving one of the biggest challenges in modern AI systems: reliability. Instead of functioning as just another chatbot, AgentMesh AI transforms natural language into structured, executable workflows capable of performing real-world actions like sending emails, coordinating async tasks, triggering automations, and streaming real-time execution updates. The platform is built using Next.js, TypeScript, MongoDB, Socket.IO, async workers, and modular provider abstraction layers. A major focus of the project was creating resilient infrastructure that continues working even when AI providers behave unpredictably. To achieve this, AgentMesh AI implements watchdog-based monitoring, timeout protection, idempotent execution, deterministic validation pipelines, structured logging, queue orchestration, and real-time task synchronization. The system also supports multi-provider orchestration through OpenAI-compatible APIs, Hugging Face inference endpoints, and AMD-powered infrastructure, allowing dynamic provider switching and improved fault tolerance. During the hackathon, we focused heavily on runtime stabilization, execution consistency, and scalable orchestration architecture. Rather than building another demo-focused conversational app, AgentMesh AI was designed as foundational infrastructure for dependable AI-powered automation and future autonomous workflow systems.

Build solutions that improve how software is built. Work with an AI that understands your codebase, helping you reduce repetitive work and build with real context. ⏳ Build your project in 48 hours. 🚀 Get hands-on with IBM Bob and explore how AI fits into real development workflows before it becomes standard. 💡 Build tools and workflows that developers would actually use. ⭐ Learn directly from experts throughout the event. 🤝 Join a team or build solo. 💰 Prize pool: $10,000 🧑🏻‍💻 Register before the Kick-Off Stream and start building with Bob.

Grab your ideas, spin up compute, and start building what’s next! Start with $100 in AMD Developer Cloud credits and begin building right away. Get access to hands-on tutorials, workshops, and curated learning resources to help you build faster and go further. To unlock credits and join the hackathon, sign up for the AMD AI Developer Program. 🤝 Go solo or team up — ship something real. 💰 $21,500+ total prize pool & 1 × AMD Radeon™ AI PRO R9700 GPU up for grabs. 📍 On-site Venue (May 9-10): MindsDB SF AI Collective 3154 17th St, San Francisco, California, USA 📍On-site participation is by invitation only. Travel and accommodation expenses will not be covered. 🧑‍💻 Developers, builders, and innovators - bring your boldest ideas and let’s turn them into real AI systems on AMD.