[ICLR 2025] Automated Design of Agentic Systems

A topological machine learning framework based on PyTorch

Aurora — Open source AI-powered agentic incident management & root cause analysis for SREs. LangGraph agents investigate across AWS, Azure, GCP, Kubernetes. Integrates with PagerDuty, Datadog, Graf…

Deep learning made topological.

This is the repo for the living e-book SLOs can't catch a Black Swan

SRE Control Plane is an open-source Autonomous Reliability Engine that transforms telemetry into action. It ingests OpenTelemetry signals, performs LLM-driven root cause analysis, generates GitOps …

Scripts and data for finding company founders

Beautiful visualization of time-to-market data for flagship products at major tech companies

Predicting Chaotic Systems with Transformers