Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

Jacquard, a programming language for AI-written, human-reviewed code

Details

External ID
48894630
Source
HN
Company
—
Product
Jacquard, a programming language for AI-written, human-reviewed code
Website domain
github.com
Launched
July 13, 2026
Cohort
—
Upvotes
102
Upvotes percentile
0.9181600955794504
Tags
—
Fetched at
Sept. 7, 2026, 9:26 p.m.
Updated at
Sept. 7, 2026, 9:26 p.m.

Description

I'm fascinated by the generative AI wave rolling over us, and wondered if AI could create a language that it might prefer using over the ones created by and for humans.To create the design, I had AI analyze the ASTs of several mainstream languages plus a few of the conceptually groundbreaking but esoteric ones (listed in the README) and then create a new structure and new syntax. It was named after the Jacquard machine (https://en.wikipedia.org/wiki/Jacquard_machine), a precursor to Babbage's Analytical Engine (and punch cards).The result reused a lot of existing ideas but combined them in what I found to be an interesting way. External/world effects are visible in function signatures, and the runtime requires explicit permission to touch the filesystem, network, etc. Effect interactions can be recorded and replayed to see what happens under different conditions or code. And since code is given a content-addressed semantic identity internally, renames and formatting changes don't require recompile or retesting.Another piece that fell out of this was a testing framework called Warp, which combines replay, results caching, handler substitution, and a few other tools that I frankly wish I had when writing Python. There are a few examples available in the demos directory.There's more to do, but it's installable and usable. I'm hoping people will have their agents digest the docs/SKILL.md file and maybe write a few programs or see where it might fit in their projects. It should be particularly useful in agent systems. If an agent says something is painful or you as a human find the code tough to understand, I'd like to hear about it so I can address it.More detail here:Repository: https://github.com/jbwinters/jacquard-langFurther intro/human-oriented write-up here: https://research.friendmachine.co/jacquard/

Enrichment

Theme
AI agent frameworks and developer tools
Vertical
Horizontal
Function
Dev tools
Audience
Developer
AI stance
AI-native
Project type
Commercial product
Normalized one-liner
programming language for ai-written human-reviewed code
Manually corrected
False

Could you build this?

No Designing and building a novel programming language with custom syntax, AST representation, semantics, and an efficient compiler/interpreter requires deep programming language theory.

What it would actually take: A real programming language requires a formal grammar specification (EBNF), lexer and parser generation (or recursive descent parser), AST construction, type checker, and code generator (targeting LLVM IR, bytecode, or transpiling). Ensuring robust error reporting, deterministic human-readable diffs, and tooling/LSP support demands specialized compiler engineering experience.

Discussion

20 comments analyzed.

Competitors mentioned: Flix programming language, Languages with algebraic effects, Python, Rust

Concerns raised: Crashing instead of raising exceptions or return codes is a bug, Poor documentation compared to unfiltered LLM output, Unclear if reviewing Jacquard is substantially easier than existing languages, LLMs struggle to write prompts and documentation for other LLMs, New languages may not compete with mainstream languages in LLM training data

Feature requests: Annotations for memory usage, PII processing, response time, and user permissions, Better documentation with big picture explanation and effect system in first paragraphs, Clear guidelines avoiding jargon like 'kernel' and 'carrier', Database-backed approach like Unison for multiple annotations

Competitors

Other products that read as similar to this one — 86 launches clear the similarity bar, closest 8 shown.

Attention rank: #12 of 87 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 254 days after the earliest competitor.

Other launches for this product

Same idea, different domain

Nobody's really built a dev tools tool for Sales yet.