Hacker ApprovedDepartments

BAML

Hacker Approved

Shares rank 74 of 163 programming languages by recommenders

People recommend BAML for fast structured LLM outputs and quick prompt iteration. The main caveat is that its external DSL adds complexity some find unnecessary.

People recommend BAML for fast structured LLM outputs and quick prompt iteration. The main caveat is that its external DSL adds complexity some find unnecessary.

18 people gave an opinion

recommend it
16
criticize it
2
approval share
89%
Each figure is one person. RecommendsCriticizes

Recommended in 5 of 13 months

  1. November 2025: recommended
  2. December 2025: recommended
  3. January 2026: recommended
  4. February 2026: not recommended
  5. March 2026: recommended
  6. April 2026: not recommended
  7. May 2026: not recommended
  8. June 2026: not recommended
  9. July 2026: recommended
  10. August 2026: not recommended
  11. September 2026: not recommended
  12. October 2026: not recommended
  13. November 2026: not recommended (month in progress)

Why it carries the badge

  • 16 people recommend itNeeds 10 or more, met.
  • 8 recommenders for every criticNeeds 2 to 1 or better, met.
  • Recommended in 5 of 13 monthsNeeds 4 or more, met.

The same three rules apply to every product, and the badge can’t be bought. How the badge works

What people say about it

The reasons people give, with the number of comments that give each one. Open a reason to read what they said.

Why people recommend it

Each mark is one comment

  • Works well in practice

    “that workaround we've found works quite well”

    Comment from 21 Dec 2025 in “Structured outputs create false confidence”

    “that worked super well for me multiple times”

    Comment from 23 Mar 2026 in “If Dspy is so great, why isn't anyone using it?”

    “been using it in production”

    Comment from 23 Mar 2026 in “If Dspy is so great, why isn't anyone using it?”
  • Good fit for agents and SDKs

    “In most places a proper SDK like BAML will be better suited.”

    Comment from 29 Dec 2025 in “Koine”

    “Most agentic implementations should use something like BAML.”

    Comment from 29 Dec 2025 in “Koine”

    “BAML is likewise a good fit when you prefer generated SDKs”

    Comment from 1 Nov 2025 on Hacker News
  • Good for structured outputs

    “For structured outputs, JSON schema is slow and sluggish while BAML performs well.”

    Comment from 22 Nov 2025 in “Agent design is still hard”

    “is really great for handling structured outputs”

    Comment from 17 Jan 2026 in “LLM Structured Outputs Handbook”
  • Readable for humans

    “I'd rather write something human readable and debuggable.”

    Comment from 15 Nov 2025 in “Structured outputs on the Claude Developer Platform”

    “This looks pretty nice for humans too actually.”

    Comment from 16 Jul 2026 in “Baml: The Programming Language for Agents”

What people warn about

Each mark is one comment

  • Adds unnecessary complexity

    “I personally have a distaste for external DSLs as I think it generally introduces complexity that I don't think is actually worthwhile”

    Comment from 23 Mar 2026 in “If Dspy is so great, why isn't anyone using it?”

    “This isn't needed at all.”

    Comment from 15 Jul 2026 in “Baml: The Programming Language for Agents”

Other programming languages people recommend

The four most recommended other programming languages, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.

BAML compared with 4 alternatives
ProductRecommendCriticizeApprovalMonthsOwnedBadge
Rust2,03997368%134 yrs118 ownersApproved
Go1,25465166%135.9 yrs63 owners—
Python1,06782157%1218 yrs64 owners—
Zig74344962%121 yr27 owners—
BAMLThis page16289%5—Approved
See all 163 programming languages, ranked

What people said

16 of the 19 comments that mention it, newest first. Each links to the original comment.

“This looks pretty nice for humans too actually.”

MixedComment from 16 Jul 2026 in “Baml: The Programming Language for Agents”

“This isn't needed at all.”

CriticizesComment from 15 Jul 2026 in “Baml: The Programming Language for Agents”

“that worked super well for me multiple times”

RecommendsComment from 23 Mar 2026 in “If Dspy is so great, why isn't anyone using it?”

“been using it in production”

RecommendsComment from 23 Mar 2026 in “If Dspy is so great, why isn't anyone using it?”

“I personally have a distaste for external DSLs as I think it generally introduces complexity that I don't think is actually worthwhile”

CriticizesComment from 23 Mar 2026 in “If Dspy is so great, why isn't anyone using it?”

“I've been reaching for BAML when I really need prompt iteration at speed.”

RecommendsComment from 23 Mar 2026 in “If Dspy is so great, why isn't anyone using it?”

“is really great for handling structured outputs”

RecommendsComment from 17 Jan 2026 in “LLM Structured Outputs Handbook”

“Most agentic implementations should use something like BAML.”

RecommendsComment from 29 Dec 2025 in “Koine”

“In most places a proper SDK like BAML will be better suited.”

RecommendsComment from 29 Dec 2025 in “Koine”

“that workaround we've found works quite well”

RecommendsComment from 21 Dec 2025 in “Structured outputs create false confidence”

“I really like BAML but this post seems a little too much like a BAML funnel.”

RecommendsComment from 21 Dec 2025 in “Structured outputs create false confidence”

“excels at representing nested data with fewer tokens than JSON”

RecommendsComment from 16 Dec 2025 in “Achieving 20%+ improvement in structured extraction using DSPy and GEPA”

“For structured outputs, JSON schema is slow and sluggish while BAML performs well.”

RecommendsComment from 22 Nov 2025 in “Agent design is still hard”

“I'd rather write something human readable and debuggable.”

RecommendsComment from 15 Nov 2025 in “Structured outputs on the Claude Developer Platform”

“This looks like a great project.”

RecommendsComment from 5 Nov 2025 in “Why BAML?”

“BAML is likewise a good fit when you prefer generated SDKs”

RecommendsComment from 1 Nov 2025 on Hacker News

Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.