
Federated Anchors: Simplifying Linkerd Multicluster Trust and Certificate Rotation
Rotating a shared trust anchor across Linkerd clusters is painful. Federated anchors add per-cluster anchors so you can rotate one cluster at a time.
From the creators of Linkerd
Run coding assistants, apps, and agents on open-weight models you control, with no per-token bills and full control of cost, routing, and data.
AI inference
Move agentic coding to open-weight models running on GPUs you control.
Learn moreCache-aware routing that predicts latency and holds every tenant’s SLOs.
Learn moreMore useful work from every GPU, even at peak utilization.
Learn moreWhen GPUs saturate, excess requests burst to the cloud.
Learn moreProduction-grade Enterprise Linkerd
A validated control plane and data plane, audit-ready in 90 days
Learn moreGolden metrics, automated cert rotation, and OpenTelemetry tracing
Learn moreBuoyant AI serves your coding agents from open-weight models on GPUs you control, so inference scales with productivity as cost per token falls.
I lead a platform team
I build on Kubernetes
Learn more about what is possible with Buoyant Enterprise for Linkerd
Feature comparison
Service mesh certification

Rotating a shared trust anchor across Linkerd clusters is painful. Federated anchors add per-cluster anchors so you can rotate one cluster at a time.

Learn about Kinference, the open source inference control plane for Kubernetes. Maximize GPU efficiency, enforce policies, and cut TTFT by up to 95%.

Learn how Kinference cuts TTFT by up to 95% and boosts Kubernetes inference capacity compared to plain vLLM deployments in our latest benchmark.

Red Hat security expert Kathleen Goeschel explores AI code vulnerabilities, static analysis, and why finding bugs is harder than writing them.

Dapr creator Mark Fussell explains durable execution for AI agents: process recovery, SPIFFE identity, and EU AI Act attestation for Kubernetes teams.