next-ai-draw-io
SHA-256An AI-powered diagram creation tool that integrates with draw.io, allowing users to create, modify, and enhance diagrams through natural language commands.
Smart Download
Download Download Version
v0.4.16 · 336.3 MB
One-sentence AI-powered diagram tool: describe what you want, AI draws it with draw.io.
Core Features
- Generate diagrams from plain text descriptions using LLMs
- Upload images, PDFs, or text files to recreate/extract diagrams
- Real-time chat interface for iterative refinement
- Support for 15+ AI providers (OpenAI, Claude, DeepSeek, etc.)
- MCP server for integration with AI agents like Claude Desktop and Cursor
What It Can't Do
- •Complex diagrams may require strong LLMs (e.g., Claude 4.5, GPT-5.1); weaker models may produce malformed output
- •No direct SVG/PNG export yet (use draw.io interface for that)
- •Demo site has rate limits – bring your own API key or self-deploy for production use
- •MCP server requires Node.js; Windows users need npx installed
Use Cases
- Developers creating system architecture, flowcharts, or ER diagrams
- Product managers visualizing workflows or user journeys
- Researchers illustrating models or data pipelines in academic papers
Detailed Introduction
Next AI Draw.io is a Next.js web application that brings artificial intelligence into diagram creation. By leveraging large language models (LLMs), users can describe diagrams in plain English and have them automatically generated as draw.io diagrams. It supports image-based replication, PDF/text file uploads for content extraction, animated connectors, cloud architecture diagrams (AWS, GCP, Azure), and an interactive chat interface for real-time refinement. The project includes an MCP server for integration with AI agents like Claude Desktop and Cursor, and supports multiple AI providers (OpenAI, Anthropic, Google, DeepSeek, etc.). Compared to traditional diagram tools like Lucidchart or draw.io alone, this tool uniquely eliminates manual drawing by allowing natural language input and AI-assisted editing, drastically reducing the time from concept to visualization. It also offers a built-in version history and admin panel for server-side model management.
Tags
Getting Started
Download installer
Click the button above to download the installer for your system
Install the software
Install the appropriate package for your distro (dpkg / rpm / AppImage)
Try online: visit https://next-ai-drawio.jiang.jp/ (no installation needed)
Self-host: clone repo, run npm install && npm run dev, open http://localhost:6002
Configure AI models: set API keys in .env.local (e.g., OpenAI, Claude) or use multi-model config
- Try online: visit https://next-ai-drawio.jiang.jp/ (no installation needed)
- Self-host: clone repo, run npm install && npm run dev, open http://localhost:6002
- Configure AI models: set API keys in .env.local (e.g., OpenAI, Claude) or use multi-model config
SHA-256 checksum verified
Checksum extracted from GitHub official Release page
SHA256 Checksum
f12a048f8f77051a45a7ada25901cb9c4b369a9da53feb3e1e8efbce6d84a1dbThis checksum is extracted from the GitHub Release page. Verify file integrity after download.
All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.
Open Source Transparency
View GitHub SourceUninstall Info
If deployed via Docker: docker rm -f container-name; if via source: delete project directory; desktop app: uninstall via OS app manager.
No Extra Dependencies
Ready to use after download. No additional runtime required.
Similar Projects
ragflow
RAGFlow is a leading open-source RAG engine that fuses deep document understanding with agentic workflows, offering precise, citation-grounded answers. Unlike LangChain's DIY approach, RAGFlow provides a turnkey, enterprise-ready platform with a visual interface and template-based chunking, reducing hallucinations and setup complexity.
unsloth
Unsloth is the first desktop app to run and train AI models locally. It supports a wide range of models including Qwen3.8, Kimi K3, MiniMax-H3, Gemma 4, DeepSeek-V4, and FLUX. Unlike most local model tools that focus only on inference, Unsloth adds a full training stack: fine-tune LLMs, diffusion, TTS, and embedding models 2× faster with 70% less VRAM. It also supports LoRA, QLoRA, RL, GRPO, DPO, and FP8. The app includes built-in Agents & Tools integration (Claude Code, Codex, MCP), private search and RAG, image/video diffusion, and audio support. With hardware support for CPU, NVIDIA, AMD, Intel, macOS, and multi-GPU setups, plus remote access via Cloudflare, Unsloth is a comprehensive local AI studio. It can export to GGUF, NVFP4, FP8 and offers an OpenAI-compatible API for easy deployment.
AnythingLLM
Chat with your docs, use AI agents, multi-user support, runs locally with zero setup.