Back to Devoured - May 18, 2026
DEVOURED
Zero (GitHub Repo)

Zero (GitHub Repo)

Tech Vercel Labs
Vercel Labs released Zero, an experimental systems programming language designed for AI agents as primary users rather than humans.
What: Vercel Labs released Zero, a pre-1.0 systems programming language where AI agents are the primary intended users. It features a minimal syntax for agent learnability, a comprehensive standard library to avoid dependency searches, and structured compiler output that exposes diagnostics and facts for agents to debug and repair code. The language is intentionally unstable and not production-ready.
Why it matters: This signals a shift in programming language design toward AI-native tooling, where languages optimize for machine learnability and structured output over human ergonomics, betting that future development will be increasingly agent-mediated.
Takeaway: Try Zero in an isolated environment at https://zerolang.ai with `curl -fsSL https://zerolang.ai/install.sh | bash`, but avoid production use due to security warnings.
Deep dive
  • Released by Vercel Labs as an experimental systems programming language (pre-1.0, intentionally unstable)
  • Designed with AI agents as primary users from day one, not an afterthought
  • Key features: small regular syntax agents can learn from examples, comprehensive standard library, structured compiler diagnostics
  • Compiler outputs structured facts (diagnostics, graph data, size reports, explanations, fix plans) for agents to inspect and act on
  • Philosophy: regularity over syntax sugar — one obvious way to express things, more explicit than human-optimized languages
  • Standard library aims to cover common capabilities to minimize dependency searches
  • Tooling emphasizes fast, deterministic, scriptable operations (check, run, format, inspect, repair)
  • Not production-ready: security vulnerabilities expected, should only be used in isolated disposable environments
  • Installation via curl script, examples available in GitHub repo
  • Core commands: zero check, zero run, zero build, zero graph, zero skills
  • Project will make breaking changes while exploring optimal patterns for agent-first development
Decoder
  • Agent-first programming language: A language designed primarily for AI agents to read, write, and debug, optimizing for machine learnability (simple syntax, structured output, comprehensive docs) over human convenience features like syntax sugar.
Original article

Zero

Zero is an experiment in building an agent-first programming language.

The project is exploring what changes when agents are primary users from day one: a language that can be learned on the fly, tooling that exposes structured facts for debugging and repair, and a standard library broad enough that most programs do not start with a dependency search.

Zero is pre-1 and intentionally unstable. The project will make breaking changes while it searches for the language, library, and tooling patterns that work best for agents. Treat today's syntax and APIs as something to explore, not something to memorize. If that sounds useful, try it with us: run examples, inspect the structured output, and send feedback about what helps agents work better.

Security vulnerabilities should be expected. Zero is not ready for production systems, sensitive data, or trusted infrastructure. If you plan to run or develop Zero, do so in an isolated, disposable environment.

What Zero Is Aiming For

  • Agent-first learnability: a small, regular language surface that agents can pick up quickly from examples, docs, and compiler feedback.
  • Standard-library depth: common capabilities should live in documented, coherent library APIs instead of scattered dependency stacks.
  • Deterministic tooling: diagnostics, graph facts, size reports, explanations, and fix plans should be structured enough for agents to inspect and act on.
  • Direct developer experience: checking, running, formatting, inspecting, and repairing code should be fast, copyable, and scriptable.
  • Regularity over syntax: prefer one obvious way to express most things, even when that makes code more explicit than a human might choose in another language.

Quick Start

Install the latest release:

curl -fsSL https://zerolang.ai/install.sh | bash
export PATH="$HOME/.zero/bin:$PATH"
zero --version

Check a program:

zero check examples/hello.0

Run a small executable:

zero run examples/add.0

Expected output:

math works

Common Commands

zero check examples/hello.0
zero run examples/add.0
zero build --emit exe --target linux-musl-x64 examples/add.0 --out .zero/out/add
zero graph --json examples/systems-package
zero size --json examples/point.0
zero skills get zero --full
zero doctor --json

Validation

pnpm run docs:test
pnpm run conformance
pnpm run native:test
pnpm run command-contracts

Benchmarks run locally by default:

pnpm run bench
Explore all 67 articles in today's digest

Fresh dev news, AI-digested daily. Never miss a trend at devoured.fyi