NURL
nurl-lang.orgA token-efficient programming language built for language models.
Dev Toolsprogramming-languagellmllvmcompilerwebassemblytoken-efficientmcp
About
NURL (Neural Unified Representation Language) is a small, LLVM-backed programming language with a regular, prefix-notation grammar optimized for code generated or consumed by large language models. It compiles to native binaries and WebAssembly via LLVM IR, and includes a self-hosting compiler that also exposes an MCP server so AI assistants can build and run NURL programs directly. The language prioritizes token efficiency, local semantics, and deterministic compilation over human-oriented syntax conveniences.
Problem
Existing programming languages are designed for human ergonomics, making them verbose and token-inefficient when used with large language models.
For
AI/LLM developers and agent builders who generate or consume code programmatically
How it works
NURL uses a minimal prefix-notation grammar that compiles to LLVM IR, producing native binaries or WebAssembly, with a self-hosting compiler also accessible as a hosted MCP server for AI assistants.
Business model
open-source
Status
launched