Zero | An agent-first language experiment.
Pre-1 experiment<br>The programming language<br>for agents<br>Zero explores what a programming language can look like when agents are primary users from day one. The aim is a language that is easy to learn on the fly, deterministic to inspect and repair, standard-library first, and explicit enough that most tasks have one obvious path.<br>For humans<br>For agents
$ curl -fsSL https://zerolang.ai/install.sh | bash
The current toolchain is useful for exploration, but today's syntax and APIs are not a contract. Expect breaking changes while Zero searches for what works best for agents. Run it in a safe environment, not against production systems.
Learnableon demand<br>Small surface area<br>Zero is aiming for a language an agent can learn while working: regular syntax, few special cases, and compiler feedback that points toward the next edit.
Libraryfirst<br>Fewer dependency searches<br>The long-term goal is a standard library broad and consistent enough that most programs start with documented APIs, not package selection.
Inspectableby tools<br>Deterministic repair loops<br>The toolchain is intended to expose diagnostics, graphs, size reports, explanations, and repair plans as structured data agents can consume.
main.0<br>fun answer() -> i32 {<br>return 40 + 2
pub fun main(world: World) -> Void raises {<br>if answer() == 42 {<br>check world.out.write("math works\n")
zero check --json<br>$ zero check --json<br>"ok": false,<br>"diagnostics": [{<br>"code": "NAM003",<br>"message": "unknown identifier",<br>"line": 3,<br>"repair": { "id": "declare-missing-symbol" }<br>}]
The direction is a CLI that works at both levels: readable messages for humans, structured facts for agents, and deterministic repair plans where the compiler can propose the next edit.
Direction<br>Regularity over cleverness.<br>Zero favors explicit capabilities and standard-library APIs over syntax for every convenience. Some code may be more verbose for humans if that makes it easier for agents to generate, inspect, and repair.
Pre-1 by design<br>Today's syntax and APIs are not a contract. Breaking changes are expected while Zero searches for what works best for agents.
Safe environments only<br>Security vulnerabilities should be expected. Run and develop Zero in isolated environments, not production systems or sensitive infrastructure.
Exploration over mastery<br>Try the current shape, inspect the output, and send feedback. The details will move as the experiment learns.
One obvious path<br>The language should favor a small set of regular patterns over many interchangeable styles.
Standard library over sugar<br>New capability should usually live in documented APIs before it becomes new syntax.
Agent-readable tooling<br>Diagnostics, graph facts, size reports, and repair metadata should be available as structured output.
Explicit effects<br>Outside-world access, fallibility, and resource use should stay visible to both readers and tools.
No legacy promises<br>When a clearer agent-facing design wins, Zero can replace old behavior instead of carrying compatibility paths forward.
DX as a goal<br>Checking, inspecting, explaining, and repairing code should feel direct even when the language is intentionally explicit.
Explore with us.<br>Install the compiler, run an example, and inspect what the experiment can do today. The most useful feedback is what helps agents work with less guesswork.<br>Get started
Ask AI⌘I