Zerolang
Graph-first programming language where agents edit semantic structure
Visit zerolang.ai ↗What is Zerolang?
Zerolang is an experimental programming language designed for AI agents to work with program semantics directly rather than raw source text. Humans request outcomes, agents query and edit the program graph with compiler-checked patches, and results remain reviewable as text projections. The project describes itself as built by Vercel Labs and emphasizes a tighter agent loop where the compiler validates edits before they affect the program database.
The language provides agents with explicit handles like symbols, node IDs, graph hashes, types, and effects to target semantic structure instead of line ranges. Stale or invalid edits fail before storage. Readable `.0` file projections stay available for human review and occasional manual editing, while agents typically interact through graph queries and patches.
Momentum
Daily activity over the last 30 days: upvotes, unique visits, new GitHub stars and Hacker News points.
How do we know it's vibe coded?
vibetrend discovered Zerolang automatically. Evidence: GitHub vercel-labs/zerolang; repo has AGENTS.md. View source.
Similar vibe-coded apps

Turn your codebase into a queryable knowledge graph for AI coding assistants

Operating layer for AI coding agents with skills, memory, planning and security

Self-hosted AI agent with persistent memory and multi-platform messaging

Open-source AI platform for short-form video and animated series creation


Open-source canvas workbench for AI-powered image and video creation

Community marketplace for DeepSeek Harness Web themes, pets, plugins

Open-source, AI-native knowledge base with Evernote-style interface