May 4 · 2 min read · Microsoft Azure now offers a capability to link an Azure Foundry project to another via an AI Gateway.This provides a pattern with which AI models can be centralised and then shared with governance an
Join discussion
May 4 · 17 min read · Inside an AI Gateway: 7 Cross-Cutting Concerns That Don't Belong in Your App Code Pull up the source of any production AI feature shipped in 2026 and you'll find the same mess. An OpenAI client wrapped in a try/except. A hardcoded retry. An if model ...
Join discussion
Apr 21 · 12 min read · ## Why OpenClaw Has 250,000 GitHub Stars in Four Months In late January 2026, a project called OpenClaw crossed 100,000 GitHub stars in under two weeks. By March 3, 2026, it had surpassed React's decade-long record of 243,000 stars, claiming the tit...
Join discussion
Feb 4 · 5 min read · # Building an AI Inference Gateway, Part 2: Unifying Streaming and Non-Streaming Processing Recently, while developing [llm-converter](https://github.com/putao520/llm-converter)—a Rust library for LLM protocol conversion—I encountered a problem: **h...
Join discussionFeb 4 · 15 min read · # Building an AI Inference Gateway: Practice and Insights Recently, while building an AI inference gateway, I encountered quite a few challenges. AI gateways differ significantly from traditional API gateways: request bodies can be tens of KB, infer...
Join discussionJan 29 · 6 min read · The fast-evolving AI landscape requires organizations to adopt experimentation-driven approaches to stay competitive. As AI transforms industries, rapid innovation is key. Since AI services are largely accessed through APIs, a strong API management s...
Join discussion
Jan 18 · 11 min read · kong kong-3.13 mcp ai-agents ai-gateway security TL;DR MCP servers expose all tools by default. Two problems: Security: Agents get capabilities they shouldn't have Performance: Too many tools degrade LLM tool selection Solution: Put a gateway betwe...
Join discussion
Nov 20, 2025 · 10 min read · Introduction: The Turning Point from Dispersed Traffic to Intelligent Governance Since early 2025, within a leading global appliance giant, multiple business lines have introduced numerous large language models (LLMs). The R&D department needed codin...
Join discussion
