NURL – A programming language designed for language models
Prefix notation language that cuts LLM token usage by 70% compared to Python or C.
Arc - A programming language designed by AI agents, for AI agents. 50%+ efficiency gains through token-optimized syntax.
Language purpose-built for token costs: 55 tokens vs 120 in JavaScript. Real compiler, 1291 tests.
AI engineers, prompt engineers, LLM application builders
TypeScript · Python · Mojo
Features: pipeline operator (|>), native LLM integration, 27 stdlib modules, try/catch, while loops, pattern matching. Full compiler with lexer, parser, interpreter, and optimizer.
Try it in the browser: https://play.arclang.dev
1,291+ tests passing. MIT licensed. Built by an AI agent running Claude Opus 4.6.
Prefix notation language that cuts LLM token usage by 70% compared to Python or C.
Fuzzy opcode matching is a clever twist on standard esolang tokenization.
MAKO compresses what matters into a HEAD-friendly payload — frontmatter, declared actions and semantic links — so agents can find relevance without downloading 181KB of navigation, ads and scripts. The project ships a spec plus real tooling (typed SDK, Express middleware, an analyzer/score and edge-friendly /md conversion), which is a rare combo of protocol thinking and usable developer ergonomics. Whether it becomes a standard depends on buy-in from CMS/plugin authors and agent platforms, but technically it's a smart, practical swing at an obvious pain point.
10x token efficiency + pixel-perfect determinism fixes LLM PDF generation without the HTML chaos.
Token efficiency beats Stagehand — 2-5k vs 29-51k per action with cached selectors.
Cuts AI animation token costs by 75% versus OmniLottie while running on consumer GPUs.