Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

BAML

BAML agent programming language, listed for a v1 nightly integration that maps typed function return values to Jev questions.

Projectbeta
View on GitHub ↗

Overview

BAML is a programming language for agents from Boundary. It looks like TypeScript, has a Rust-like type system with types that persist at runtime, typed and statically analyzed errors, green-thread concurrency, built-in tests and evals, and a standard library for agents. BAML functions can be called from TypeScript, Python, Go, C#, Java and more.

Per the list summary, a v1 nightly integration maps typed function return values to Jev questions, so a BAML function returning a boolean or enum could be answered by Jev. It is not yet part of the stable release line, and the README excerpt does not describe it.

What the decision model decides

TypeQuestionAnswers
ChoiceEnum-typed BAML function return mapped to a Jev Choice(inferred)—
Yes / noBoolean-typed return mapped to a Jev Noul(inferred)true · false

How it works

  1. Write a BAML function with a typed return
  2. Select the Jev integration (nightly)
  3. BAML maps the return type to a Jev question
  4. Call it from your host language

Strengths

  • Typed returns fit Jev's primitives naturally

Caveats

  • Nightly only, not in stable releases
  • Not documented in the README excerpt

Getting started

brew install baml && baml init

At a glance

Type
Project
Status
beta
Language
Rust
Runtime
language toolchain
Has code
yes
Has tests
yes

Use cases and integrations

How curated lists describe it

  • The v1 nightly integration maps typed function return values to Jev questions; it is not part of the stable release line yet.

    cobanov/awesome-jev

Frequently asked questions

Is Jev support stable?

No, it is in the v1 nightly line per the listing.

How does it map to Jev?

Typed function return values become Jev questions.

How do I install BAML?

brew install baml, then baml init.

Related projects

  • Ax

    Ax, a DSPy-style multi-language LLM framework, listed with a native TypeSafe provider for Boolean, Choice, Score and raw Jev questions.

    PluginproductionTypeScript
  • Effect

    Effect TypeScript library whose @effect/ai-typesafe package maps classify, probability and rating operations to Jev questions.

    ProjectproductionTypeScript
  • instructor-php

    PHP monorepo whose Polyglot module adds a TypeSafe driver for typed Noul, Choice and Score decisions alongside LLM inference.

    ProjectproductionPHP
  • req\_llm

    Elixir library for unified LLM calls across providers, with an evaluate interface that calls Jev via TypeSafe or OpenRouter.

    ProjectproductionElixir
  • synkora-ai

    Self-hosted multi-tenant AI agent platform listed as including optional TypeSafe client tools for classification, scoring and yes/no.

    LibraryproductionPython
  • TanStack AI

    Provider-agnostic TypeScript AI SDK; per list sources, an @tanstack/ai-typesafe adapter exposes Jev decisions through decide().

    ServiceproductionTypeScript