Blog

Ortus Solutions announces the release of BoxLang AI 3.7. Name a provider, model, params and API key once, then pick it by name for a call, an agent, or a single agent run. Embeddings get their own defaults, MCP servers you build get rate limiting and trusted proxies, and a handful of important fixes land along the way.

Ortus Solutions today announces the release of BoxLang 1.19.0, the software productivity platform for building, modernizing and running applications, with developers and AI agents working together. This release is about observability: built-in code coverage and execution profiling, the missing post-invocation events for BIFs, and new query and transaction events, and it pairs with the new BxLens beta, the debug bar and ops console that exposes hotspots and bytecode profilers. It also adds your own global settings in boxlang.json, static method interception, raw binary HTTP streaming and a lot of hardening across JDBC, Java interop and CFML compatibility.

Ortus Solutions today announces that bx-mcp, the Model Context Protocol (MCP) server for BoxLang, is now free for everyone. Install it, point any MCP capable client at it, and your AI coding assistant, IDE agent or automation pipeline can inspect and operate a live BoxLang runtime: JVM, caches, datasources, slow requests, schedulers, logs and more. No BoxLang+ subscription required.

Ortus Solutions today announces MatchBox 0.12.0, the Rust runtime for BoxLang, alongside the launch of matchbox.boxlang.io: a new website with a live in-browser playground, a ten-lesson course, and complete online docs. The release also brings a more capable JIT, prebuilt native modules, a richer web runtime, and a long list of BoxLang compatibility fixes.

Ortus Solutions today announces BoxLang AI 3.6, the release that connects the AI framework to the rest of the BoxLang productivity platform. Your agents can now drive a real browser via bx-playwright, speak and master audio via bx-audio, stream text-to-speech token by token, talk to any MCP server over stdio — and do all of it with the same fluent BoxLang syntax they always have.

Ortus Solutions today announces the official release of the BoxLang package for Sublime Text 4, the newest member of the BoxLang productivity tool suite.

Azure joins the serverless family. Scheduled tasks become cluster-safe. And the whole platform gets documentation and skills built for developers and AI agents working side by side.

If you run a technology organization, you are being asked to do three things at once: ship faster, keep the estate you already have running, and make AI part of how your teams work. Most stacks make you choose. BoxLang 1.18 is another step toward not having to.

Reasoning-capable models have been usable in BoxLang AI for a while. params passes straight through to the provider body, so params: { thinking: { type: "enabled", budget_tokens: 10000 } } for Claude, or params: { reasoning_effort: "high" } for OpenAI, already reached the API. What never worked was reading the reasoning back. It was parsed out on arrival and silently dropped. In 3.4.0, that's fixed, and it's fixed the same way for every provider.

You call writeDump() on an ORM entity or a very rich class graph . The browser locks up. Thirty seconds later you get a page with forty thousand rows on it, you scroll for a while, you give up, and you go edit your code to dump a sub-key instead. Or worse, you crash the server.

LLM applications face a class of attack traditional input validation was never built for: prompt injection. An attacker embeds instructions in user input, a retrieved document, a web page your tool fetched, or an MCP result, trying to override your system prompt, exfiltrate data, or hijack a tool call. BoxLang AI 3.4.0 ships four layered, configurable defenses against exactly this, plus one more that's on unconditionally.