MOL
A programming language where pipelines trace themselves
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
Hi HN,I built MOL, a domain-specific language for AI pipelines. The main idea: the pipe operator |> automatically generates execution traces — showing timing, types, and data at each step. No logging, no print debugging.Example: let index be doc |> chunk(512) |> embed("model-v1") |> store("kb") This auto-prints a trace table with each step's execution time and output type. Elixir and F# have |> but neither auto-traces.Other features: - 12 built-in domain types (Document, Chunk, Embedding, VectorStore, Thought, Memory, Node) - Guard assertions: `guard answer.confidence > 0.5 : "Too low"` - 90+ stdlib functions - Transpiles to Python and JavaScript - LALR parser using LarkThe interpreter is written in Python (~3,500 lines). 68 tests passing. On PyPI: `pip install mol-lang`.Online playground (no install needed): http://135.235.138.217:8000We're building this as part of IntraMind, a cognitive computing platform at CruxLabx. """
HN · launched Feb 11, 2026 · 38 upvotes (top 22%) · 1 view
Niche: programming languages and interpreters · 161 launches, 2 in the last 7 days ▼ -75% · Explore this niche →
Category and tags
- Horizontal
- Dev tools
- Developer
- Not AI
- Hobby / open-source project
Visit website ↗ Source listing ↗
More like this: all 161 launches in programming languages and interpreters →
Could you build this?
Partial The syntax and basic interpreter wrapper can be vibe-coded, but designing a reliable DSL runtime with automatic runtime tracing, type checking, and AI pipeline introspection requires compiler and language design fundamentals.
What it would actually take: The system requires a lexer, parser, and AST interpreter/compiler (likely built in Rust or Go) supporting custom pipe operators and automated execution telemetry. It requires hooks for streaming LLM outputs, asynchronous IO for embeddings/vector DB operations, and OpenTelemetry-compatible tracing infrastructure without introducing runtime overhead. This demands solid programming language design (PL) and distributed tracing expertise.
Discussion
16 comments analyzed.
Competitors mentioned: Elixir (pipe operator), Haskell (MonadTrace), F# (pipe operator), Python (operator overloading), Rust (operator overloading)
Concerns raised: Not Pythonic to use operator overloading for pipes, Performance overhead compared to native Python, Dynamic pipelines and batching execution unclear, Orphan rule violation in Rust implementation, Auto-tracing not truly automatic, still requires explicit setup
Feature requests: Examples of complex workflows and open-ended loops/agents, Clarification on dynamic pipeline support, Separate pipeline definition from execution for throughput optimization, Documentation on durable pipeline execution
Competitors
Other products that read as similar to this one : 209 launches clear the similarity bar, closest 8 shown.
Attention rank: #67 of 210 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 103 days after the earliest competitor.
- SHDL · hn · 2026-01-28 · 48 upvotes · similarity 0.48
- The Mog Programming Language · hn · 2026-03-09 · 163 upvotes · similarity 0.46
- laborix · github · 2026-09-30 · 88 upvotes · similarity 0.44
- LLM agents that write Python to analyze execution traces at scale · hn · 2026-03-07 · 5 upvotes · similarity 0.42
- Pipevals · hn · 2026-03-20 · 6 upvotes · similarity 0.41
- Pipe IDE for Visual Programming · ph · 2026-10-20 · 2 upvotes · similarity 0.41
- rul · github · 2026-10-28 · 45 upvotes · similarity 0.40
- A small programming language where everything is pass-by-value · hn · 2026-01-25 · 91 upvotes · similarity 0.40
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.