Blog

BoxLang AI 3.2.0 is here, and it's a landmark release. We're shipping five major features — image generation, web search, a fluent audio builder API, a centralized agent registry, and deep MCP observability — along with a suite of analytics improvements and a critical bug fix. Let's dig in. 🎉

We listen. A lot. And one message has come through loud and clear from our community: teams want a way to get into the BoxLang ecosystem with commercial licensing, real tooling, and actual support — without jumping straight to a full BoxLang+ subscription.

BoxLang 1.13.0 is here, and it marks an important step forward for the platform. This release includes 48 tickets—every one of them completed—reflecting a focused effort on CFML compatibility, a more robust concurrency engine, a production-hardened miniserver, and meaningful tooling improvements.

BoxLang AI 3.1 is here, and it's a release that makes your agents smarter, faster, and more capable than ever. 🎉

We just shipped the BoxLang Google Cloud Functions Runtime — and it brings the same write-once-run-anywhere serverless experience you already know from our AWS Lambda runtime, now running natively on Google Cloud Functions Gen2.

We believe the best way to learn a programming language is by writing code — real code, with real feedback, and real tests. That's exactly why we built BoxLings.

BoxLang 1.12.0 marks a meaningful turning point. After establishing a rock-solid foundation across runtime, compiler, CFML compatibility, and the module ecosystem, BoxLang has entered its innovation cycle. The language is mature, battle-tested, and production-deployed across the industry.

AI agents are transforming how we build software. Unlike traditional chatbots that just answer questions, agents can reason about what tools they need, decide when to use them, chain multiple actions together, and remember what happened earlier in a conversation.

The AI ecosystem has a tool problem. Every framework has its own way of defining tools, every agent has its own way of calling them, and every integration requires custom code on both sides. An agent built in Python can't easily use tools built in Java. An MCP server written for Claude Desktop can't easily be consumed by a BoxLang agent without a custom adapter.

A chatbot with no memory isn't a conversation — it's a series of isolated queries. Every message starts from scratch. The user has to re-explain who they are, what they're working on, and what was just said. It's exhausting, and it signals that the AI isn't really listening.