Sreenath M Menon Staff Software Engineer · Bengaluru

Sreenath M Menon

I'm a staff software engineer with 14+ years building enterprise software and open-source AI tools, lately safe and auditable autonomous systems. I created llmswap (41K+ downloads), placed Top 15 of 70,000+ at the Meta × Hugging Face × PyTorch hackathon, and build AI agents and developer tooling. I'm currently a staff engineer.

FocusApplied AI & Agents·Product Engineering·Cloud Infrastructure·MCP & RAG·Distributed Systems
Selected work

Open source & projects.

all projects →

Tools I've built and open-sourced. Most started as something I needed, then grew a community.

Mela

01

Play with friends and AI, and let the crowd change the game.

A browser gaming platform where a game isn't just you versus an opponent. You play solo, invite friends by QR code, drop in AI agents as players, or open it up to a crowd that can actively change the match as it happens. It runs entirely in the browser with no download and no signup, ships 18 games and three-game circuits, and keeps your scorecards and clips. Agents join through WebMCP and remote MCP, with a deterministic default bot so a game still works even when no model is available.

  • WebMCP
  • MCP
  • Browser
  • Real-time

Krelvan

02

The operating system for autonomous work.

I built Krelvan around a simple belief: AI agents should become reusable software that people can install, connect, extend and genuinely own, not temporary prompts trapped inside closed platforms. A user describes an outcome, and Krelvan turns it into a working multi-step agent system with the right capabilities, tools, memory, schedules and approval controls. Its open registry provides an expanding ecosystem of installable agents, capabilities and connectors, while support for multiple model providers lets every user choose how their intelligence runs. Behind the experience is a signed, replayable execution ledger that makes every decision and action inspectable. Krelvan is more than an agent builder. It is an open foundation for creating, distributing and operating trusted AI systems on infrastructure controlled by the people who depend on them.

  • TypeScript
  • Next.js
  • Event-sourced
  • MCP

llmswap

03

Provider-agnostic LLM SDK + CLI supporting 11 providers (OpenAI, Anthropic, Gemini, Groq, Watsonx, Ollama, xAI, Sarvam…) with zero vendor lock-in. Workspace memory, universal tool-calling, an MCP client, and cost visibility.

41K+ downloads · 5 contributors · Homebrew tap
  • Python
  • TypeScript
  • MCP

Asha Sahayak

04

An RL environment for AI-assisted clinical triage for India's 1.07M frontline ASHA health workers. Multi-agent, adaptive curriculum, GRPO-trained to 0.947 peak reward. Built for the Meta × Hugging Face × PyTorch hackathon: Top 15 of 70,000+.

  • Python
  • OpenEnv
  • GRPO · Qwen3
Experience

14+ years, from grep to agents.

2019 to PresentIBM
Staff Software EngineerStaff → Senior Staff → Advisory Software Engineer

Product engineering on enterprise software, working across large-scale platform features used by customers worldwide.

2018 to 2019UST Global
Systems Analyst

Built a customer-interaction platform integrating AWS Connect, Transcribe and Comprehend for real-time call processing and sentiment analysis.

2011 to 2018Poornam Info Vision
Senior Software Engineer (L2)

Led cloud-management product development and architected an OpenStack-based billing platform, cutting customer onboarding from 2 days to 2 hours and improving VM migration workflows by 30%.

Recognition

Where the work got noticed.

Top 15 / 70,000+
Meta × Hugging Face × PyTorch OpenEnv Hackathon, India's biggest AI hackathon. Solo, prize winner, work shortlisted by Meta's global AI team (Apr 2026).
96/100
OpenAI × OutSkill hackathon (Helix Factory). "Clear product direction, solid build quality, well-structured evaluation narrative."
90/100
Deriv AI hackathon (Aegis WAF). Averaged 4.5/5 across two judges.
Top 50 Finalist
Anthropic + Accel Hackathon. Invited to Anthropic India Dev Day (Oct 2025).
2× Show HN
Featured on Hacker News for open-source projects.
About

I build things people keep using.

I started with bash and grep in 2011, moved into cloud infrastructure when OpenStack was new, and now work at the seam between natural language and systems, building safe, auditable autonomous systems where every action is signed, every budget enforced, and every decision reversible. I care about reliable software, good developer experience, and tools that earn a place in someone's daily workflow. Based in Bengaluru.

AI / ML
LLMsRAGAI AgentsMCP ProtocolReinforcement LearningLangChainLangGraphCrewAIVector DBs
Languages & API
PythonTypeScriptGoReactGraphQLFastAPINode.js
Platform & Data
KubernetesDockerAWSAzureGCPOpenStackKafkaMongoDBPostgreSQL

Let's build something.

I'm always happy to talk infrastructure, applied AI, open source, or anything in between. Drop me a line.