Coming Soon
Blog
Technical insights on API gateways, AI governance, agent infrastructure, and building self-hosted platforms.
Upcoming Articles
Why your AI gateway and API gateway should be the same thing
The case for unified L1+L2+L3 architecture. Why running separate tools for the edge, the LLM layer, and agents creates three points of failure, three auth systems, and three 2am incidents.
ArchitecturePer-tenant rate limiting: the feature every API gateway gets wrong
Why global rate limits don't work in multi-tenant platforms. How sliding windows, tenant-scoped buckets, and hierarchical overrides (global -> tenant -> route) solve the problem.
Multi-tenancyRust vs Python for AI gateways: our benchmarks
We rewrote our AI Gateway from Python (LiteLLM + FastAPI) to Rust (axum + tokio). The numbers: 599 req/s cache-hit, 18ms P50. Here's what changed and why.
PerformanceGet notified when we publish
No spam. Technical content only. Unsubscribe anytime.