[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-619":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":25,"hasPages":23,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":33,"readmeContent":34,"aiSummary":35,"trendingCount":16,"starSnapshotCount":16,"syncStatus":36,"lastSyncTime":37,"discoverSource":38},619,"fireworks-tech-graph","yizhiyanhua-ai\u002Ffireworks-tech-graph","yizhiyanhua-ai","Generate production-quality SVG+PNG technical diagrams from natural language. 7 styles, UML support, and AI\u002FAgent workflow patterns.","https:\u002F\u002Fbradzhang.dev\u002Fen\u002Fcase-studies\u002Ffireworks-tech-graph",null,"Python",7498,652,24,3,0,100,251,470,300,39.44,"MIT License",false,"main",true,[27,28,29,30,31,32],"agent-workflows","ai","claude-code","developer-tools","diagrams","svg","2026-06-12 02:00:16","[English](README.md) | [中文](README.zh.md)\n\n# fireworks-tech-graph\n\n> **Stop drawing diagrams by hand.** Describe your system in English or Chinese — get publication-ready SVG + PNG technical diagrams in seconds.\n\n[![License: MIT](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FLicense-MIT-yellow.svg)](LICENSE)\n[![Claude Code Skill](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FClaude%20Code-Skill-blue)](https:\u002F\u002Fclaude.ai\u002Fcode)\n[![7 Visual Styles](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FStyles-7-purple)]()\n[![14 Diagram Types](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiagram%20Types-14-green)]()\n[![UML Support](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FUML-Full%20Support-orange)]()\n\n---\n\n## Overview\n\n`fireworks-tech-graph` turns natural language descriptions into polished SVG diagrams, then exports them as high-resolution PNG via `rsvg-convert`. It ships with **7 visual styles** and deep knowledge of AI\u002FAgent domain patterns (RAG, Agentic Search, Mem0, Multi-Agent, Tool Call flows), plus full support for all 14 UML diagram types.\n\n```\nUser: \"Generate a Mem0 memory architecture diagram, dark style\"\n  → Skill classifies: Memory Architecture Diagram, Style 2\n  → Generates SVG with swim lanes, cylinders, semantic arrows\n  → Exports 1920px PNG\n  → Reports: mem0-architecture.svg \u002F mem0-architecture.png\n```\n\n---\n\n## Work With the Builder\n\nThis project is also a proof surface for a broader capability: turning vague AI\u002Fdevtool workflows into constrained, reusable systems with validation, documentation, export paths, and product-facing polish.\n\nIf you are building agent infrastructure, AI IDEs, internal copilots, developer tools, technical documentation systems, or applied AI workflow products, I am open to scoped paid sprints, design-partner work, and founding engineer conversations.\n\n- Founder-facing profile: https:\u002F\u002Fbradzhang.dev\u002Fen\n- Commercial case study: https:\u002F\u002Fbradzhang.dev\u002Fen\u002Fcase-studies\u002Ffireworks-tech-graph\n- Work with me: https:\u002F\u002Fbradzhang.dev\u002Fen\u002Fwork-with-me\n\n---\n\n## Showcase\n\n> All samples exported at 1920px width (2× retina) via `rsvg-convert`. PNG is lossless and the right choice for technical diagrams — sharp edges, no JPEG compression artifacts on text\u002Flines.\n\n### Style 1 — Flat Icon (default)\n*Mem0 Memory Architecture — white background, semantic arrows, layered memory system*\n![Style 1 — Flat Icon](assets\u002Fsamples\u002Fsample-style1-flat.png)\n\n### Style 2 — Dark Terminal\n*Tool Call Flow — dark background, neon accents, monospace font*\n![Style 2 — Dark Terminal](assets\u002Fsamples\u002Fsample-style2-dark.png)\n\n### Style 3 — Blueprint\n*Microservices Architecture — deep blue background, grid lines, cyan strokes*\n![Style 3 — Blueprint](assets\u002Fsamples\u002Fsample-style3-blueprint.png)\n\n### Style 4 — Notion Clean\n*Agent Memory Types — minimal white, single accent color*\n![Style 4 — Notion Clean](assets\u002Fsamples\u002Fsample-style4-notion.png)\n\n### Style 5 — Glassmorphism\n*Multi-Agent Collaboration — dark gradient background, frosted glass cards*\n![Style 5 — Glassmorphism](assets\u002Fsamples\u002Fsample-style5-glass.png)\n\n### Style 6 — Claude Official\n*System Architecture — warm cream background (#f8f6f3), Anthropic brand colors, clean professional aesthetic*\n![Style 6 — Claude Official](assets\u002Fsamples\u002Fsample-style6-claude.png)\n\n### Style 7 — OpenAI Official\n*API Integration Flow — pure white background, OpenAI brand palette, modern minimalist design*\n![Style 7 — OpenAI Official](assets\u002Fsamples\u002Fsample-style7-openai.png)\n\n---\n\n## Stable Prompt Recipes\n\nUse prompts like these when you want the model to stay close to the repo's strongest regression-tested outputs:\n\n### Style 1 — Flat Icon\n```text\nDraw a Mem0 memory architecture diagram in style 1 (Flat Icon).\nUse four horizontal sections: Input Layer, Memory Manager, Storage Layer, Output \u002F Retrieval.\nInclude User, AI App \u002F Agent, LLM, mem0 Client, Memory Manager, Vector Store, Graph DB, Key-Value Store, History Store, Context Builder, Ranked Results, Personalized Response.\nUse semantic arrows for read, write, control, and data flow. Keep the layout clean and product-doc friendly.\n```\n\n### Style 2 — Dark Terminal\n```text\nDraw a tool call flow diagram in style 2 (Dark Terminal).\nShow User query, Retrieve chunks, Generate answer, Knowledge base, Agent, Terminal, Source documents, and Grounded answer.\nUse terminal chrome, neon accents, monospace typography, and semantic arrows for retrieval, synthesis, and embedding update.\n```\n\n### Style 3 — Blueprint\n```text\nDraw a microservices architecture diagram in style 3 (Blueprint).\nCreate numbered engineering sections like 01 \u002F\u002F EDGE, 02 \u002F\u002F APPLICATION SERVICES, 03 \u002F\u002F DATA + EVENT INFRA, 04 \u002F\u002F OBSERVABILITY.\nInclude Client Apps, API Gateway, Auth \u002F Policy, three services, Event Router, Postgres, Redis Cache, Warehouse, and Metrics \u002F Traces.\nUse blueprint grid, cyan strokes, and a bottom-right title block.\n```\n\n### Style 4 — Notion Clean\n```text\nDraw an agent memory types diagram in style 4 (Notion Clean).\nCompare Sensory Memory, Working Memory, Episodic Memory, Semantic Memory, and Procedural Memory around a central Agent core.\nUse a minimal white layout, neutral borders, one accent color for arrows, and short storage tags for each memory type.\n```\n\n### Style 5 — Glassmorphism\n```text\nDraw a multi-agent collaboration diagram in style 5 (Glassmorphism).\nUse three sections: Mission Control, Specialist Agents, and Synthesis.\nInclude User brief, Coordinator Agent, Research Agent, Coding Agent, Review Agent, Shared Memory, Synthesis Engine, and Final response.\nUse frosted cards, soft glow, and semantic arrows for delegation, shared memory writes, and synthesis output.\n```\n\n### Style 6 — Claude Official\n```text\nDraw a system architecture diagram in style 6 (Claude Official).\nUse left-side layer labels: Interface Layer, Core Layer, Foundation Layer.\nInclude Client Surface, Gateway, Task Planner, Model Runtime, Policy Guardrails, Memory Store, Tool Runtime, Observability, and Registry.\nUse warm cream background, restrained brand-like palette, generous whitespace, and a bottom-right legend.\n```\n\n### Style 7 — OpenAI Official\n```text\nDraw an API integration flow diagram in style 7 (OpenAI Official).\nUse three sections: Entry, Model + Tools, and Delivery.\nInclude Application, OpenAI SDK Layer, Prompt Builder, Model Runtime, Tool Calls, Response Formatter, Observability, and Release Control.\nKeep the look minimal, white, precise, and modern with clean green-accented arrows.\n```\n\n---\n\n## Features\n\n- **7 visual styles** — from clean white docs to dark neon to frosted glass to official brand styles\n- **Executable style system** — style guides are encoded into the generator, not only documented in markdown\n- **14 diagram types** — Full UML support (Class, Component, Deployment, Package, Composite Structure, Object, Use Case, Activity, State Machine, Sequence, Communication, Timing, Interaction Overview, ER Diagram) plus AI\u002FAgent domain diagrams\n- **AI\u002FAgent domain patterns** — RAG, Agentic Search, Mem0, Multi-Agent, Tool Call, and more built-in\n- **Semantic shape vocabulary** — LLM = double-border rect, Agent = hexagon, Vector Store = ringed cylinder\n- **Semantic arrow system** — color + dash pattern encode meaning (write vs read vs async vs loop)\n- **Product icons** — 40+ products with brand colors: OpenAI, Anthropic, Pinecone, Weaviate, Kafka, PostgreSQL…\n- **Swim lane grouping** — automatic layer labeling for complex architectures\n- **SVG + PNG output** — SVG for editing, 1920px PNG for embedding\n- **rsvg-convert compatible** — no external font fetching, pure inline SVG\n\n---\n\n## Installation\n\n```bash\nnpx skills add yizhiyanhua-ai\u002Ffireworks-tech-graph\n```\n\nThis skill is installed from the GitHub repository. The npm package page is the public package\u002Fdistribution page:\n\n```text\nhttps:\u002F\u002Fwww.npmjs.com\u002Fpackage\u002F@yizhiyanhua-ai\u002Ffireworks-tech-graph\n```\n\nDo not use the npm package name with `skills add`, because the CLI resolves install sources as GitHub\u002Flocal paths.\n\n## Update\n\n```bash\nnpx skills add yizhiyanhua-ai\u002Ffireworks-tech-graph --force -g -y\n```\n\nRe-run `add --force` to pull the latest version of this skill.\n\nOr clone directly:\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fyizhiyanhua-ai\u002Ffireworks-tech-graph.git ~\u002F.claude\u002Fskills\u002Ffireworks-tech-graph\n```\n\n---\n\n## Requirements\n\n```bash\n# macOS\nbrew install librsvg\n\n# Ubuntu\u002FDebian\nsudo apt install librsvg2-bin\n\n# Verify\nrsvg-convert --version\n```\n\n---\n\n## Why Not Mermaid or draw.io?\n\n| | Mermaid | draw.io | **fireworks-tech-graph** |\n|--|---------|---------|--------------------------|\n| Natural language input | ✗ | ✗ | ✅ |\n| AI\u002FAgent domain patterns | ✗ | ✗ | ✅ |\n| Multiple visual styles | ✗ | manual | ✅ 5 built-in |\n| High-res PNG export | ✗ | manual | ✅ auto 1920px |\n| Semantic arrow colors | ✗ | manual | ✅ auto |\n| No online tool needed | ✅ | ✗ | ✅ |\n\nMermaid is great for quick inline diagrams in markdown. draw.io is great for manual polishing. `fireworks-tech-graph` is optimized for **describing a system and getting a polished diagram immediately**, without writing DSL syntax or clicking around a GUI.\n\n---\n\n## Usage\n\n### Trigger phrases\n\nThe skill auto-triggers on:\n\n```\ngenerate diagram \u002F draw diagram \u002F create chart \u002F visualize\narchitecture diagram \u002F flowchart \u002F sequence diagram \u002F data flow\n```\n\n### Basic usage\n\n```\nDraw a RAG pipeline flowchart\n```\n\n```\nGenerate an Agentic Search architecture diagram\n```\n\n### Specify style\n\n```\nDraw a microservices architecture diagram, style 2 (dark terminal)\n```\n\n```\nDraw a multi-agent collaboration diagram --style glassmorphism\n```\n\n### Specify output path\n\n```\nGenerate a Mem0 architecture diagram, output to ~\u002FDesktop\u002F\n```\n\n```\nCreate a tool call flow diagram --output \u002Ftmp\u002Fdiagrams\u002F\n```\n\n---\n\n## Example Prompts by Scenario\n\n### AI\u002FAgent Systems\n\n```\nCompare Agentic RAG vs standard RAG in a feature matrix, Notion clean style\n```\n→ Comparison matrix: RAG vs Agentic RAG, covering retrieval strategy, agent loop, tool use\n\n```\nGenerate a Mem0 memory architecture diagram with vector store, graph DB, KV store, and memory manager\n```\n→ Memory Architecture with swim lanes: Input → Memory Manager → Storage tiers → Retrieval\n\n```\nDraw a Multi-Agent diagram: Orchestrator dispatches 3 SubAgents (search \u002F compute \u002F code execution), results aggregated\n```\n→ Agent Architecture with hexagons, tool layers, and result aggregation\n\n```\nVisualize the Tool Call execution flow: LLM → Tool Selector → Execution → Parser → back to LLM\n```\n→ Flowchart with decision loop showing tool invocation cycle\n\n```\nDraw the 5 agent memory types: Sensory, Working, Episodic, Semantic, Procedural\n```\n→ Mind map or layered architecture showing memory tiers from sensory to procedural\n\n### Infrastructure & Cloud\n\n```\nDraw a microservices architecture: Client → API Gateway → [User Service \u002F Order Service \u002F Payment Service] → PostgreSQL + Redis\n```\n→ Architecture diagram with horizontal layers, swim lanes per service cluster\n\n```\nGenerate a data pipeline diagram: Kafka → Spark processing → write to S3 → Athena query\n```\n→ Data flow diagram with labeled arrows (stream \u002F batch \u002F query)\n\n```\nDraw a Kubernetes deployment: Ingress → Service → [Pod × 3] → ConfigMap + PersistentVolume\n```\n→ Architecture with dashed containers per namespace, solid arrows for traffic flow\n\n### API & Sequence Flows\n\n```\nDraw an OAuth2 authorization code flow sequence diagram: User → Client → Auth Server → Resource Server\n```\n→ Sequence diagram with vertical lifelines and activation boxes\n\n```\nDraw the ChatGPT Plugin call sequence diagram\n```\n→ Sequence: User → ChatGPT → Plugin Manifest → API → Response chain\n\n### Decision & Process Flows\n\n```\nDraw a pre-launch QA flowchart for an AI app: Code Review → Security Scan → Performance Test → Manual Approval → Deploy\n```\n→ Flowchart with diamond decision nodes and parallel branches\n\n```\nGenerate a feature comparison matrix: RAG vs Fine-tuning vs Prompt Engineering\n```\n→ Comparison matrix with checked\u002Funchecked cells across cost, latency, accuracy, flexibility\n\n### Concept Maps\n\n```\nVisualize the LLM application tech stack: from foundation model to SDK to app framework to deployment\n```\n→ Layered architecture or mind map from model layer to product layer\n\n```\nDraw an AI Agent capability map: Perception \u002F Memory \u002F Reasoning \u002F Action \u002F Learning\n```\n→ Mind map with central \"AI Agent\" node and 5 radial branches\n\n---\n\n## Styles\n\n| # | Name | Background | Font | Best For |\n|---|------|-----------|------|----------|\n| 1 | **Flat Icon** *(default)* | `#ffffff` | Helvetica | Blogs, slides, docs |\n| 2 | **Dark Terminal** | `#0f0f1a` | SF Mono \u002F Fira Code | GitHub README, dev articles |\n| 3 | **Blueprint** | `#0a1628` | Courier New | Architecture docs, engineering |\n| 4 | **Notion Clean** | `#ffffff` | system-ui | Notion, Confluence, wikis |\n| 5 | **Glassmorphism** | `#0d1117` gradient | Inter | Product sites, keynotes |\n| 6 | **Claude Official** | `#f8f6f3` | system-ui | Anthropic-style diagrams, warm aesthetic |\n| 7 | **OpenAI Official** | `#ffffff` | system-ui | OpenAI-style diagrams, clean modern look |\n\nEach style has a dedicated reference file in `references\u002F` with exact color tokens, SVG patterns, and templates.\nThe generator also consumes style-aware structure fields such as `containers`, semantic `nodes[].kind`, `arrows[].flow`, and explicit port anchors so sample-grade layouts can be reproduced more consistently.\n\nUseful high-leverage fields for style-specific polish:\n- `style_overrides` to nudge title alignment or palette tokens without forking a full style\n- `containers[].header_prefix` \u002F `containers[].header_text` for blueprint-style numbered section headers such as `01 \u002F\u002F EDGE`\n- `containers[].side_label` for Claude-style left layer labels\n- `window_controls`, `meta_left`, `meta_center`, `meta_right` for terminal \u002F document chrome\n- `blueprint_title_block` for engineering title boxes in style 3\n\n### Style Selection Guide\n\n**For UML Diagrams:**\n- **Class\u002FComponent\u002FPackage**: Style 1 (Flat Icon) or Style 4 (Notion Clean) — clear structure, easy to read\n- **Sequence\u002FTiming**: Style 2 (Dark Terminal) — monospace fonts help with alignment\n- **State Machine\u002FActivity**: Style 3 (Blueprint) — engineering aesthetic fits process flows\n- **Use Case\u002FInterview**: Style 1 (Flat Icon) — colorful, accessible\n\n**For AI\u002FAgent Diagrams:**\n- **RAG\u002FAgentic Search**: Style 2 (Dark Terminal) or Style 5 (Glassmorphism) — tech-forward aesthetic\n- **Memory Architecture**: Style 3 (Blueprint) — emphasizes layered storage tiers\n- **Multi-Agent**: Style 5 (Glassmorphism) — frosted cards distinguish agent boundaries\n\n**For Documentation:**\n- **Internal docs**: Style 4 (Notion Clean) — minimal, wiki-friendly\n- **Blog posts**: Style 1 (Flat Icon) — colorful, engaging\n- **GitHub README**: Style 2 (Dark Terminal) — matches dark theme\n- **Presentations**: Style 5 (Glassmorphism) or Style 6 (Claude Official) — polished\n\n**Brand-Specific:**\n- **Anthropic\u002FClaude projects**: Style 6 (Claude Official) — warm cream background, brand colors\n- **OpenAI projects**: Style 7 (OpenAI Official) — clean white, OpenAI palette\n\n---\n\n## Diagram Types\n\n| Type | Description | Key Layout Rule |\n|------|-------------|-----------------|\n| **Architecture** | Services, components, cloud infra | Horizontal layers top→bottom |\n| **Data Flow** | What data moves where | Label every arrow with data type |\n| **Flowchart** | Decisions, process steps | Diamond = decision, top→bottom |\n| **Agent Architecture** | LLM + tools + memory | 5-layer model: Input\u002FAgent\u002FMemory\u002FTool\u002FOutput |\n| **Memory Architecture** | Mem0, MemGPT-style | Separate read\u002Fwrite paths, memory tiers |\n| **Sequence** | API call chains, time-ordered | Vertical lifelines, horizontal messages |\n| **Comparison** | Feature matrix, side-by-side | Column = system, row = attribute |\n| **Mind Map** | Concept maps, radial | Central node, bezier branches |\n\n### UML Diagram Support (14 Types)\n\n| UML Type | Description | Best Style |\n|----------|-------------|------------|\n| **Class Diagram** | Classes, attributes, methods, relationships | Style 1, 4 |\n| **Component Diagram** | Software components and dependencies | Style 1, 3 |\n| **Deployment Diagram** | Hardware nodes and software deployment | Style 3 |\n| **Package Diagram** | Package organization and dependencies | Style 1, 4 |\n| **Composite Structure** | Internal structure of classes\u002Fcomponents | Style 1, 3 |\n| **Object Diagram** | Object instances and relationships | Style 1, 4 |\n| **Use Case Diagram** | Actors, use cases, system boundaries | Style 1 |\n| **Activity Diagram** | Workflows, parallel processes | Style 3 |\n| **State Machine** | State transitions and events | Style 2, 3 |\n| **Sequence Diagram** | Message exchanges over time | Style 2 |\n| **Communication Diagram** | Object interactions and messages | Style 1, 2 |\n| **Timing Diagram** | State changes over time | Style 2 |\n| **Interaction Overview** | High-level interaction flow | Style 1, 2 |\n| **ER Diagram** | Entity-relationship data models | Style 1, 3 |\n\n---\n\n## AI\u002FAgent Domain Patterns\n\nBuilt-in pattern knowledge:\n\n```\nRAG Pipeline         → Query → Embed → VectorSearch → Retrieve → LLM → Response\nAgentic RAG          → adds Agent loop + Tool use\nAgentic Search       → Query → Planner → [Search\u002FCalc\u002FCode] → Synthesizer\nMem0 Memory Layer    → Input → Memory Manager → [VectorDB + GraphDB] → Context\nAgent Memory Types   → Sensory → Working → Episodic → Semantic → Procedural\nMulti-Agent          → Orchestrator → [SubAgent×N] → Aggregator → Output\nTool Call Flow       → LLM → Tool Selector → Execution → Parser → LLM (loop)\n```\n\n---\n\n## Shape Vocabulary\n\nShapes encode semantic meaning consistently across all styles:\n\n| Concept | Shape |\n|---------|-------|\n| User \u002F Human | Circle + body |\n| LLM \u002F Model | Rounded rect, double border, ⚡ |\n| Agent \u002F Orchestrator | Hexagon |\n| Memory (short-term) | Dashed-border rounded rect |\n| Memory (long-term) | Solid cylinder |\n| Vector Store | Cylinder with inner rings |\n| Graph DB | 3-circle cluster |\n| Tool \u002F Function | Rect with ⚙ |\n| API \u002F Gateway | Hexagon (single border) |\n| Queue \u002F Stream | Horizontal pipe\u002Ftube |\n| Document \u002F File | Folded-corner rect |\n| Browser \u002F UI | Rect with 3-dot titlebar |\n| Decision | Diamond |\n| External Service | Dashed-border rect |\n\n---\n\n## Arrow Semantics\n\n| Flow Type | Stroke | Dash | Meaning |\n|-----------|--------|------|---------|\n| Primary data flow | 2px solid | — | Main request\u002Fresponse |\n| Control \u002F trigger | 1.5px solid | — | System A triggers B |\n| Memory read | 1.5px solid | — | Retrieve from store |\n| Memory write | 1.5px | `5,3` | Write\u002Fstore operation |\n| Async \u002F event | 1.5px | `4,2` | Non-blocking |\n| Feedback \u002F loop | 1.5px curved | — | Iterative reasoning |\n\n---\n\n## File Structure\n\n```\nfireworks-tech-graph\u002F\n├── SKILL.md                      # Main skill — diagram types, layout rules, shape vocab\n├── README.md                     # This file (English)\n├── README.zh.md                  # Chinese version\n├── references\u002F\n│   ├── style-1-flat-icon.md      # White background, colored accents\n│   ├── style-2-dark-terminal.md  # Dark bg, neon accents, monospace\n│   ├── style-3-blueprint.md      # Blueprint grid, cyan lines\n│   ├── style-4-notion-clean.md   # Minimal, white, single arrow color\n│   ├── style-5-glassmorphism.md  # Dark gradient, frosted glass cards\n│   ├── style-6-claude-official.md # Warm cream background, Anthropic brand\n│   ├── style-7-openai.md      # Clean white, OpenAI brand palette\n│   └── icons.md                  # 40+ product icons + semantic shapes\n├── agents\u002F\n│   └── openai.yaml              # Agent metadata for compatible runtimes\n├── fixtures\u002F\n│   ├── mem0-style1.json         # Style 1 regression fixture\n│   ├── tool-call-style2.json    # Style 2 regression fixture\n│   └── ...                      # Additional sample-grade fixtures per style\n├── scripts\u002F\n│   ├── generate-diagram.sh       # Validate SVG + export PNG\n│   ├── generate-from-template.py # Create starter SVGs from templates\n│   ├── validate-svg.sh           # Validate SVG syntax\n│   └── test-all-styles.sh        # Batch test all styles\n├── assets\u002F\n│   └── samples\u002F                  # Showcase diagram PNGs\n├── templates\u002F\n│   ├── architecture.svg         # Architecture starter template\n│   ├── data-flow.svg            # Data-flow starter template\n│   └── ...                      # Additional diagram templates\n└── agentloop-core.svg           # Included sample SVG\n```\n\n---\n\n## Product Icon Coverage\n\n**AI\u002FML:** OpenAI, Anthropic\u002FClaude, Google Gemini, Meta LLaMA, Mistral, Cohere, Groq, Hugging Face\n\n**AI Frameworks:** Mem0, LangChain, LlamaIndex, LangGraph, CrewAI, AutoGen, DSPy, Haystack\n\n**Vector DBs:** Pinecone, Weaviate, Qdrant, Chroma, Milvus, pgvector, Faiss\n\n**Databases:** PostgreSQL, MySQL, MongoDB, Redis, Elasticsearch, Neo4j, Cassandra\n\n**Messaging:** Kafka, RabbitMQ, NATS, Pulsar\n\n**Cloud:** AWS, GCP, Azure, Cloudflare, Vercel, Docker, Kubernetes\n\n**Observability:** Grafana, Prometheus, Datadog, LangSmith, Langfuse, Arize\n\n---\n\n## Troubleshooting\n\n| Symptom | Cause | Fix |\n|---------|-------|-----|\n| PNG is blank or all-black | `@import url()` in SVG — rsvg-convert can't fetch fonts | Remove `@import`, use system font stack |\n| PNG not generated | `rsvg-convert` not installed | `brew install librsvg` (macOS) or `apt install librsvg2-bin` |\n| Diagram cut off at bottom | ViewBox height too short | Increase `height` in `viewBox=\"0 0 960 \u003Cheight>\"` |\n| Text overflowing boxes | Labels too long | Add `text-anchor=\"middle\"` + `\u003CclipPath>` or shorten label |\n| Icons not rendering | External CDN URL in rsvg-convert context | Use inline SVG paths from `references\u002Ficons.md` |\n\n---\n\n## License\n\nMIT © 2025 fireworks-tech-graph contributors\n","`fireworks-tech-graph` 是一个能够将自然语言描述转换为高质量SVG和PNG技术图表的工具。它支持7种视觉风格、14种UML图类型，并且内置了AI\u002F代理工作流模式的知识，如RAG、Agentic Search等。项目使用Python编写，通过`rsvg-convert`导出高分辨率PNG图像，适用于需要快速生成专业级技术架构图的场景，比如软件开发文档编制、系统设计讨论以及AI\u002F开发者工具构建等领域。MIT许可证下开源，适合希望提升工作效率的技术团队和个人开发者使用。",2,"2026-06-11 02:38:08","CREATED_QUERY"]