LoadWarden is a server monitoring tool designed to prevent overload and server crashes. It constantly monitors server performance and sends alerts and warnings via webhook and email.
A focused async bulkhead for Java that limits in-flight work and makes overload visible.
Fail-fast admission control for LLM workloads, with concurrency limits, token budgeting, deduplication, streaming support, and overload protection.
Harmost - Rust reverse proxy that bounds SSR render concurrency for self-hosted Next.js. Request coalescing, safe microcaching, load shedding. Built on Pingora
A low-latency, adaptive load shedding library for backend services. Protects latency-sensitive services by rejecting or degrading low-priority traffic under overload, ensuring Service Level Objectives (SLOs) are maintained.
Express middleware for route-level bulkheads and fail-fast overload protection.
ARCORIS is an open source platform for building distributed schedulers with adaptive resource control, workload isolation, and feedback-driven overload protection across mixed workloads, queues, and execution backends.
Fail-fast admission control for async systems. Reject overload early instead of hiding it behind queues.
Protect expensive or fragile HTTP dependencies by limiting how many calls are allowed in flight at once.
To associate your repository with the overload-protection topic, visit your repo's landing page and select "manage topics."