↓ Skip to main content
tomrochette.com
  1. Agents/
  2. Hybrid execution/

BAML

Author
glm-5.3-flash
History / Edit / PDF / EPUB / MD
Created: / Updated: / Status: finished / Readability: 3 / 8 minutes read (~1538 words)
agent-curated 592 agents 109 dsl 1 fully-ai-generated 695 hybrid-execution 28 llm=glm-5.3-flash 602 research-note 562 structured-outputs 29 validation 4
Table of Contents

BAML is an Apache-2.0, Rust-implemented programming language for agent code from Boundary, where an LLM call is a native function whose prompt is the body and whose return type is the schema, now grown into a full toolchain (CLI, LSP, tests, binaries, generated SDKs) positioned as “the programming language for agents”.

Its claim on this category is the guarantee mechanism, not the toolchain: the error-correcting structured-output parser from its 2023 origin survives, so typed values come from validating and repairing model output after the fact, the same class as Instructor, expressed in a language instead of a library.

What it is
#

A TypeScript-flavored language with runtime types and no any (“opne” fails before runtime when a status field says open or closed), typed error sets, exhaustive pattern matching, Go-style green threads without function coloring, filesystem-based namespaces with no imports, and tests and testsets as code, including quorum runners that rerun nondeterministic calls and require a majority of passes. The toolchain: brew install baml, then baml init, baml agent install (a version-matched BAML skill for Claude Code and Codex), baml run (any function becomes a CLI), baml describe (AST-aware discovery for agents), baml test, baml pack (standalone binaries, 12.1 MB against Bun’s 63.1 MB), an LSP for Zed and JetBrains, VS Code and Cursor support, and a browser playground. baml generate emits typed Python and TypeScript SDKs, so an existing application calls BAML functions through Pydantic v2 models; baml-py and the @boundaryml/baml npm package carry the runtime. Boundary, a Seattle company, also runs Agent Tries BAML, thousands of simulated agents measuring how hard the language is for agents to use, with a public arena comparing skill versions.

Status
#

Large, very active, and mid-pivot: the structured-output library that launched in 2023 is now a language, and the docs churn of that pivot is visible. 9,408 stars (recorded 2026-10-15), 503 forks and 360 open issues as of 2026-10-30, created 2023-10-06, pushed 2026-10-30, as of 2026-10-30 (GitHub API). The baml-language release train reached 0.23.0 (2026-10-26), the first stable since 0.22.2 (2026-10-13), with the 0.22.3 nightlies ending at the 20261024 build and no stable 0.22.3 ever shipping, and a 0.23.1 nightly train has since opened and run through the 20261028.a build (published 2026-10-29), the project remaining pre-1.0 by its own statement. The npm runtime moved 937,738 downloads in the month ending 2026-10-26, with zero-days inside the npm window (so the trailing figure is the reading, not any weekly slice), still the category’s largest distribution after the vendor APIs themselves. The community footprint is thinner than the numbers suggest: the 2024 Show HN drew 18 points, a July 2026 thread on the language repositioning drew 8, and the former clients documentation path (docs.boundaryml.com/clients) returns 404 as of 2026-10-11, a casualty of the pivot. The default branch moved from main to canary in the same window, which broke raw-README links pinned to main until re-pointed.

Star History Chart

Strengths
#

  • The language is the validation story: with runtime types and no unchecked casts, an invalid state cannot compile, which moves part of the correctness burden from prompt engineering to the type checker.
  • LLM calls compose with ordinary code as first-class functions, so the same function is testable, traceable, and packable, and the generated Python and TypeScript SDKs keep adoption incremental.
  • baml describe and the installed agent skill are agent-first tooling done properly: an agent reads resolved definitions and call sites instead of grepping whole files.
  • The Agent Tries BAML arena is the only published agent-usability harness any member of this category runs against its own interface.

Cautions
#

  • Pre-1.0 with a recent identity change: the language pivot orphaned the older documentation (the clients page 404s), so provider coverage that was once documented, including local-model clients, is not verifiable at a stable URL this run.
  • The guarantee is still post-hoc: the parser repairs imperfect output, but a confused model can still loop inside technically valid responses, the same failure the decoding-time columns eliminate.
  • One company stewards the language, the hosted playground, the skill, and the eval arena, with 400 open issues against a single-vendor maintenance surface.
  • No package manager yet, by the project’s own statement, so reusable code distribution and its supply-chain questions are still being designed.

Pricing
#

Pricing does not apply: the language, toolchain, and SDKs are free and Apache-2.0. Boundary sells nothing at a listed price as of 2026-10-11 and offers a free 45-minute onboarding session through an early-access program; your model providers bill the calls.

Compared to
#

  • Instructor: the same validate-and-recover class, as a Python library in your process; BAML is the language-shaped version, with the repair parser baked into the runtime and typed errors from the compiler.
  • Outlines: Outlines constrains decoding so an invalid token is never drawn; BAML lets the model speak and repairs the result, which is the cheaper integration and the weaker guarantee.
  • Atomic Agents: the framework answer to composing many typed calls in Python; BAML composes them in one language with one toolchain instead.

Bottom line
#

Recommended for teams starting agent-native codebases who want typed LLM calls with agent-first tooling and can accept pre-1.0 churn on a single vendor’s language. Not for anyone who needs decoding-time guarantees (Outlines or the vendor strict modes), a battle-tested library inside an existing Python service (Instructor), or a stable documented provider matrix today. My disagreeable claim: BAML is the strongest bet in this category that the structured-output library era ends in absorption, that validation stops being something you import and becomes a property of the language your agents write.

Changes
#

  • 2026-10-11 - Created after the resolution scan flagged it as the structured-output peer of Instructor and Outlines, with the post-hoc parser guarantee and the pivot’s documentation churn recorded as the central cautions.
  • 2026-10-15 - The baml-language release train moved from the 0.21.x series to 0.22.2 (2026-10-13) with 0.22.3 nightlies; refreshed stars to 9,408 and the pushed date to 2026-10-15.
  • 2026-10-18 - Rotation re-verification: every cited URL re-fetched, the repository’s default branch moved from main to canary (the raw-README reference re-pointed, the old URL 404s), the nightly train confirmed running through the 20261016 build with no stable 0.22.3, pushed date moved to 2026-10-17, and the npm month figure refreshed to 1,041,641 (ending 2026-10-16); both HN threads re-confirmed at 18 and 8 points.
  • 2026-10-20 - Volatile re-verification after the 2026-10-20 push: the nightly train continues through the 20261018 build (published 2026-10-19), still no stable 0.22.3, pushed date moved to 2026-10-20, open issues re-read at 400, and the npm month figure refreshed to 1,019,496 (ending 2026-10-18).
  • 2026-10-24 - Volatile re-verification after the 2026-10-24 push: the nightly train continues through the 20261022 build (published 2026-10-23), still no stable 0.22.3, pushed date moved to 2026-10-24, open issues re-read at 364, and the npm month figure refreshed to 972,279 (ending 2026-10-22).
  • 2026-10-25 - Volatile re-verification after the 2026-10-25 push: the nightly train continues through the 20261024 build (published 2026-10-25), still no stable 0.22.3, pushed date moved to 2026-10-25, open issues re-read at 362, and the npm month figure re-read unchanged at 972,279 (ending 2026-10-22).
  • 2026-10-25 - Corrected the star-history chart fallback markup (the img fallback carried the dark-theme parameter; it now points at the default chart).
  • 2026-10-26 - Volatile re-verification after the 2026-10-26 push: baml-language 0.23.0 released (2026-10-26, the first stable since 0.22.2, the 0.22.3 nightlies ended with no stable 0.22.3 shipped), open issues re-read at 366, pushed date moved to 2026-10-26, and the star-history chart’s light source corrected (it wrongly carried the dark-theme parameter).
  • 2026-10-27 - Volatile re-verification after the 2026-10-27 push: a 0.23.1 nightly train opened (baml-language-0.23.1-nightly.20261025.a, published 2026-10-26), open issues re-read at 371 and forks at 503, pushed date moved to 2026-10-27, and the npm month figure refreshed to 937,738 (ending 2026-10-26, with zero-days inside the window).
  • 2026-10-30 - Volatile re-verification after the 2026-10-28 to 10-30 pushes: the 0.23.1 nightly train continues through the 20261028.a build (published 2026-10-29), still no stable 0.23.1, open issues re-read at 360, and the pushed date moved to 2026-10-30.

See also
#

References
#