BoundaryML/baml

The programming language for agents

What it solves

BAML addresses the instability and unpredictability of LLM outputs. It provides a structured programming language specifically designed for AI agents to reduce mistakes, eliminate "garbage outputs," and ensure that types persist at runtime without dangerous casting.

How it works

BAML functions as a specialized language that combines a Rust-like type system with Go-like concurrency (green threads). It allows developers to define agent logic and types that are statically analyzed for errors. It can be used as a standalone language or integrated incrementally into existing projects via calls from languages like Python, TypeScript, Go, C#, and Java.

Who it’s for

Software engineers building AI agents who require strict type safety, high performance, and a dedicated environment for testing and evaluation.

Highlights

  • Strong, static type system that eliminates any types and dangerous casting.
  • Built-in testing and evaluation framework.
  • Built-in standard library specifically for agents.
  • High-performance compilation and colorless concurrency.
  • Multi-language interoperability with TS, Py, Go, C#, and Java.

Related

  • Project
    microsoft/agent-framework

    Microsoft Agent Framework is an open‑source SDK for building production‑grade AI agents and multi‑agent workflows in Python, .NET, and Go. It offers provider‑agnostic LLM access, graph‑based orchestration, middleware, OpenTelemetry observability, declarative YAML agents, skill integration, and easy hosting on Azure or Microsoft Foundry.

  • Project
    liquidos-ai/AutoAgents

    A high-performance, modular multi-agent framework written in Rust that supports structured tool calling, local and cloud LLM backends, and secure agent execution.

  • Project
    mgechev/skills-best-practices

    A comprehensive guide on best practices for creating structured agent skills to improve AI agent reliability, discoverability, and token efficiency.

  • Project
    MaestroError/LarAgent

    An AI agent development framework for Laravel that allows developers to create and maintain AI agents using an Eloquent-like API and Laravel-style tooling.

  • Project
    confident-ai/deepeval

    DeepEval is an open‑source Python framework that lets you write pytest‑style tests for any LLM‑based app—chatbots, agents, RAG pipelines, or multimodal generators. It ships with dozens of research‑backed metrics (e.g., G‑Eval, JevEval, task‑completion, hallucination, bias) that can run on any model locally, and you can add custom metrics. The library integrates with popular toolkits (LangChain, OpenAI, Anthropic, LlamaIndex, etc.) to automatically trace model calls, enabling both end‑to‑end and step‑level evaluation. Tests run from the CLI, fit into CI/CD, and can be linked to the commercial Confident AI platform for production‑time monitoring. Ideal for developers and teams who need quantitative quality gates for LLM applications.