Semantic SVG is an open-source LLM skill and deterministic compiler that converts natural-language briefs and grounded data into SVGs with stable IDs, provenance, and machine-readable metadata.

Stars

10

7-day growth

No data

Forks

4

Open issues

0

License

MIT

Last updated

2026-07-27

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It cleanly separates LLM-driven visual storytelling from deterministic coordinate and XML generation, avoiding common SVG fragility, text collisions, and drifting coordinates while ensuring every element remains queryable and zoomable.

Who it is for

  • Developers building data visualization pipelines
  • LLM skill users and coding agents
  • Data journalists and researchers needing scalable, inspectable graphics
  • Teams requiring verifiable SVGs with embedded provenance

Use cases

  • Generating concise knowledge atlases for 8–30 high-salience concepts
  • Creating dense evidence walls with hundreds of non-overlapping detail rows
  • Integrating with CI/CD to produce validated SVGs from CSV, JSON, or GeoJSON data
  • Using as a Codex-compatible skill for natural-language SVG generation

Strengths

  • Zero runtime dependencies in the core compiler
  • Deterministic compilation with strict semantic QA and verification gates
  • Two distinct output modes (Luminous Atlas and Evidence Wall) optimized for different information densities
  • Every meaningful element gets stable IDs, source references, and embedded JSON metadata

Considerations

  • Requires Node.js 20+ and an LLM skill (code agent) for best results
  • Currently supports only two visual modes with limited customization
  • Large evidence walls rely on manual zoom inspection despite automated checks

README quick start

Quick Start

Description

Natural language and grounded data compiled into beautiful, machine-addressable SVGs.

Related repositories

Similar projects matched by category, topics, and programming language.

react
Featured
react GitHub avatar

react

React is a JavaScript library for building user interfaces with declarative, component-based, and cross-platform design.

Web DevelopmentFrontend Frameworks
246,741
tandpfun
Featured
tandpfun GitHub avatar

wardrobe

A GPT‑image powered app that extracts individual garment cutouts from photos, organizes them into a digital wardrobe, and generates modeled outfit previews.

JavaScript
1,570
mshumer
Featured
mshumer GitHub avatar

Claude-of-Duty

A browser-based first-person shooter built entirely with procedural generation and orchestrated AI agents, featuring 55k lines of Three.js/WebGL2 code and no art assets.

AI & Machine LearningAI Agents
1,234