# yizhiyanhua-ai/fireworks-tech-graph

Generate production-quality SVG+PNG technical diagrams from natural language. 7 styles, UML support, and AI/Agent workflow patterns.

Repository: https://github.com/yizhiyanhua-ai/fireworks-tech-graph
Canonical: https://ross.abutalabs.com/products/fireworks-tech-graph
Homepage: https://yizhiyanhua-ai.github.io/fireworks-tech-graph/
Language: Python
License: MIT
License Family: permissive
Topics: agent-workflows, ai, claude-code, developer-tools, diagrams, svg
Last push: 2026-08-25T22:56:41+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 93, longevity 10
- inputs: {"age_days": 145, "days_push": 8, "days_rel": 47, "gap_med": 0, "n_releases_24m": 8}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 10914, forks 878 (observed 2026-08-28T04:10:44.671764+00:00)

## What it is
A Python-based Agent Skill for Codex and Claude Code that converts natural language descriptions (English or Chinese) into production-quality technical diagrams, including SVG, PNG, animated GIF, and interactive HTML output. It supports 12 visual styles, 14 UML diagram types, and built-in AI/Agent architecture patterns like RAG and multi-agent workflows.

## Use cases
- generate architecture diagrams from natural language
- create UML diagrams without drawing by hand
- produce SVG and PNG technical diagrams for documentation
- animate system diagrams as GIFs
- draw AI agent and RAG workflow diagrams
- generate diagrams inside Claude Code or Codex
- create cloud architecture diagrams for design reviews

## When to choose
- you want polished, geometry-safe diagrams from plain-language descriptions
- you work in Claude Code or Codex and want a diagram skill
- you need AI/agent architecture patterns with proper shape vocabulary
- Mermaid is too limited and draw.io is too manual for your needs

## When to avoid
- you need fully manual pixel-level control over diagram layout
- you need live diagram rendering in a web app at runtime
- you don't use an AI coding agent and prefer traditional diagramming tools

## Facets
- artifact type: library
- maturity: active
- function: data-visualization, developer-tools, llm-inference, agent-framework
- domain: developer-tools, data-visualization, artificial-intelligence, documentation
- platform: python, cli, cross-platform
- tags: diagram-generation, svg, png, gif-animation, uml, agent-skill, claude-code, codex, natural-language-to-diagram, architecture-diagrams

## Member repositories
- yizhiyanhua-ai/fireworks-tech-graph (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:44.671764+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:17:23.706731+00:00, confidence not recorded.
  - readme: https://github.com/yizhiyanhua-ai/fireworks-tech-graph (fetched 2026-08-28T04:10:44.671764+00:00, sha 909e8b82a70a)
  - homepage: https://yizhiyanhua-ai.github.io/fireworks-tech-graph/ (fetched 2026-08-29T08:16:11.680477+00:00, sha b492269c6cb4)
- Data as of 2026-08-30T08:39:29.467469+00:00.