Blog

Vendor lock-in is the silent killer of AI projects. You pick OpenAI, build everything against the OpenAI API, and then GPT-5 launches at three times the price. Or a competitor launches a model that's faster for your use case. Or you need to self-host for compliance. Or your client is on AWS and wants Bedrock.

Agents make live LLM calls. They invoke real tools. They have non-deterministic outputs. Standard unit testing approaches fall apart. You can't mock every provider. You can't replay a conversation from three weeks ago. You can't confidently tell stakeholders that the agent you deployed today behaves the same way it did when you signed off on it.

The problem with most multi-agent frameworks is that the orchestration layer is bolted on — you're managing agent references manually, passing outputs between them by hand, and hoping you haven't introduced a cycle. There's no concept of hierarchy. No cycle detection. No way to ask "who's in charge here?" or "how deep in the tree am I?"

Function calling is where most AI frameworks look deceptively simple on the surface and turn into a mess underneath. You define a tool, pass it to the LLM, and when the LLM calls it — who handles the lifecycle? Who fires observability events? Who serializes the result? Who resolves the tool by name when the only thing you have is a string?

Every AI framework eventually hits the same wall: your system prompts start drifting. Agent A has a slightly different version of the SQL rules than Agent B. The tone policy on your support bot is three weeks behind the tone policy on your documentation bot. Someone copy-pasted the wrong version. Nobody noticed.

It's been a while since we've shipped something this big. BoxLang AI 3.0 is a ground-up rethink of how AI agents, models, and tools work in the BoxLang ecosystem — and it lands with ten major features at once.

TestBox 7.x series continues our mission to be the best testing framework for BoxLang and CFML. This release is focused heavily on BoxLang CLI runner enhancements, real-time streaming test execution via SSE, a powerful dry run capability, the brand-new TestBox RUN web IDE, and significant quality-of-life improvements for developers working in both BoxLang and CFML environments.

If you've been watching the AI-assisted development wave from the sidelines, wondering when it would actually matter for your ColdBox HMVC stack — the wait is over. The latest ColdBox CLI release ships a brand-new ai namespace that transforms how you and your team interact with coding agents like Claude, GitHub Copilot, Cursor, Codex, OpenCode, Gemini and many more.

This isn't a chatbot integration or a prompt template sitting in a README. This is a full framework-aware AI system built directly into your development workflow.

We're proud to announce BoxLang 1.11.0, a highly focused performance and stability release that delivers measurable speed improvements across every BoxLang application, with zero code changes required. The team invested deeply in bytecode generation, class loading, lock management, and type casting to produce one of the most impactful runtime optimization releases to date. Alongside the performance wave, this release resolves critical concurrency bugs, hardens DateTime handling, and ships powerful new developer tooling.

We're excited to announce the official BoxLang Homebrew tap — the easiest way to get BoxLang up and running on macOS (and Linux with Homebrew). One command, and you're in business.