Zero
AIAn experimental graph-first programming language where agents edit a compiler-checked program graph instead of raw source text.
Zero
An experimental graph-first programming language where agents edit a compiler-checked program graph instead of raw source text.
About Zero
Zero (zerolang) is an experimental systems programming language from Vercel Labs designed so AI agents are primary users alongside humans. Instead of treating source text as the source of truth, Zero makes a compiler-owned semantic graph the program: agents query symbols, calls, types, effects, node IDs and graph hashes, then submit patches that target specific nodes and fields. Every patch is guarded by an expected graph hash and expected field values, so stale or invalid edits fail before they touch the store — which puts the compiler inside the agent loop rather than after it, replacing the usual write-text-then-run-tools-to-find-out cycle. Humans stay in the loop through readable .0 projections of the graph, which remain available for review and the occasional manual edit. The language itself aims to stay small and regular, with explicit effects via a World capability, structured JSON compiler diagnostics, token efficiency, low memory, fast startup and builds, and zero dependencies. The project is explicitly experimental, expects breaking changes and warns against running it against production systems; source is Apache-2.0 on GitHub with a one-line installer at zerolang.ai.
Screenshots
Key Features
Use Cases
Frequently asked questions about Zero
What is Zero?
An experimental graph-first programming language where agents edit a compiler-checked program graph instead of raw source text.
How does Zero work?
Zero works by combining Graph as the Program: A compiler-owned semantic graph of symbols, calls, types, effects and node IDs is the source of truth, so agents reason over program structure rather than parsing and regenerating text., Hash-Guarded Patches: Every edit carries an expected graph hash and expected field values, so a stale or conflicting patch is rejected before it reaches the store instead of silently corrupting the program., Compiler in the Loop: Shape, type, stale-state and repository metadata checks run as part of applying a patch, collapsing the write-build-test-inspect cycle into a single checked operation., Readable Text Projections: The graph renders to reviewable .0 source projections so humans can read diffs, audit what an agent changed and make rare manual edits., Structured JSON Diagnostics: The compiler emits machine-readable diagnostics rather than prose error text, so agents can act on failures without parsing terminal output. to help users with Reliable Agent Code Edits: Let a coding agent make semantic changes that are rejected outright if its view of the program is stale, instead of producing plausible-looking but broken text diffs., Reducing Agent Token Spend: Query the specific symbols, types and nodes relevant to a task rather than feeding whole files into context on every turn., Outcome-Driven Development: Describe a desired result in conversation — add auth, fix a failing route, build a CRM API — and review the resulting projection rather than writing the code., Auditable AI-Written Code: Review what changed through readable .0 projections and graph hashes, keeping a human checkpoint over agent-authored programs., Language and Tooling Research: Explore what a compiler and program representation look like when machine editors, not human typists, are the primary writers..
What are the main features of Zero?
Key features include Graph as the Program: A compiler-owned semantic graph of symbols, calls, types, effects and node IDs is the source of truth, so agents reason over program structure rather than parsing and regenerating text., Hash-Guarded Patches: Every edit carries an expected graph hash and expected field values, so a stale or conflicting patch is rejected before it reaches the store instead of silently corrupting the program., Compiler in the Loop: Shape, type, stale-state and repository metadata checks run as part of applying a patch, collapsing the write-build-test-inspect cycle into a single checked operation., Readable Text Projections: The graph renders to reviewable .0 source projections so humans can read diffs, audit what an agent changed and make rare manual edits., Structured JSON Diagnostics: The compiler emits machine-readable diagnostics rather than prose error text, so agents can act on failures without parsing terminal output..
Who is Zero for?
Zero is useful for anyone interested in Reliable Agent Code Edits: Let a coding agent make semantic changes that are rejected outright if its view of the program is stale, instead of producing plausible-looking but broken text diffs., Reducing Agent Token Spend: Query the specific symbols, types and nodes relevant to a task rather than feeding whole files into context on every turn., Outcome-Driven Development: Describe a desired result in conversation — add auth, fix a failing route, build a CRM API — and review the resulting projection rather than writing the code., Auditable AI-Written Code: Review what changed through readable .0 projections and graph hashes, keeping a human checkpoint over agent-authored programs., Language and Tooling Research: Explore what a compiler and program representation look like when machine editors, not human typists, are the primary writers..
How much does Zero cost?
Zero is free to use.
How do I get started with Zero?
Visit https://zerolang.ai/ to sign up and explore Zero.
Explore more AI Ai Tools tools
Browse all Ai Tools tools →Browse by use case: Automation & Productivity
Compare Zero: vs Agents Never Sleep · vs Port Radar for macOS · vs SubtitleGenerator · vs oMLX