An autonomous SRE agent that monitors cloud logs across multiple platforms, leveraging AI models from various providers to detect anomalies, perform root cause analysis, and automate remediation by creating GitHub Pull Requests.

Production-grade multi-agent AI system for infrastructure reliability analysis and advisory intelligence, with governed execution available in Enterprise deployments.

Open source code for AIOpsServing

🚀 Enhance Google Cloud operations with the Gemini SRE Agent, automating log monitoring and incident response for smarter site reliability.

It is an AI-powered DevOps tool that analyzes Linux server logs to detect anomalies and predict failures. It integrates ML models, automated fixes via Ansible, containerization with Docker, and orchestration using Kubernetes—providing a full-stack solution for predictive maintenance.

ReliaKit TL-15 is an open-source, planet-grade resilience framework for distributed infrastructure. It integrates automated DDoS protection, geo-aware routing, chaos engineering, and symbolic AI hooks to achieve fault tolerance beyond traditional benchmarks.

An AI Agent IaC tool that aims to make developing and deploying AI Agents easier.

The collection of charms used to integrate Juju deployed Slurm clusters with Vantage.

🤖 Build and deploy scalable Multi-AI Agent systems with LangGraph and Groq LLMs to enhance intelligence across enterprise applications.

End-to-end healthcare intake pipeline: clean, validate, route, and AI-summarize intake notes using SQLite, Python, and local Llama 3 (Ollama).

Experimental Python tool for assessing raw data readiness for process mining and event-log generation

DevOps, SRE & AI portfolio: multi-cloud (AWS/Azure/GCP/OCI), MLOps & automation.

AI-Ops decision support tool that analyzes RDS failure scenarios and translates them into business impact (SLA, RTO, RPO).

ModelSpec is an open, declarative specification for describing how AI models especially LLMs are deployed, served, and operated in production. It captures execution, serving, and orchestration intent to enable validation, reasoning, and automation across modern AI infrastructure.

Open R&D notes demo site for lumencore: grid aware, resource efficient compute, and telecom practices aimed at reducing operational GHG intensity

End-to-end design and implementation of a multi-intent AI chatbot architecture. Includes intent detection, dynamic routing, document retrieval, SQL query generation, observability, guardrails, and CI/CD automation for enterprise-scale deployment.