Overview
BoxLang AI gives you chat, agents, tools, memory, RAG, MCP, and enterprise governance through one fluent API across the leading AI providers.
BoxLang is the software productivity platform for building, modernizing and running applications, with developers and AI agents working together. BoxLang AI is how you build AI into your applications: one fluent API for chat, agents, tools, memory, RAG, MCP, and the governance controls that enterprises need.
π€ Two Different Ideas
What
Using AI agents to write your BoxLang application
Building AI features inside your application
β¨ What You Can Build
Chat with streaming and typed, structured output
Agents with instructions, memory, tools, skills, and sub-agents
Tools that let models call your code
Memory and RAG with 20+ memory types and many vector store integrations
MCP clients and servers
Governance with guardrails, prompt-injection defense, human approval, and audit trails
Multimodal audio, image generation, and web search
Browser agents that visit pages, fill forms, and click through web applications with bx-playwright
β‘ Quick Start
Install the module:
With CommandBox:
Configure a provider in boxlang.json, keeping keys in environment variables:
Your first chat:
Prefer to run models locally with no API costs? Use the ollama provider. See Providers & Gateways.
πΊοΈ In This Section
Chat & Structured OutputAgentsTools & SkillsMemory & RAGMCPGovernance & SecurityMultimodalProviders & Gatewaysπ’ Enterprise Ready
AI in production needs more than a model call. BoxLang AI includes middleware for guardrails, retries and logging, human approval for sensitive actions, prompt-injection defense, multi-tenant memory isolation, and a flight recorder for audit trails. See Governance & Security.
π Full Documentation
Docs MCP server for your agent:
https://ai.ortusbooks.com/~gitbook/mcp
Last updated
Was this helpful?
