sequence-flow-experiment-with-desktop-commander
Fully AI generated Flutter app in Claude Desktop with 3.7 Sonnet by MCP servers desktop-commander and sequential-thinking
stepanic
README
sequence-flow-experiment-with-desktop-commander
Fully AI generated Flutter app in Claude Desktop with 3.7 Sonnet by MCP servers desktop-commander and sequential-thinking
Sequence Flow - HTN Planning System
A Flutter application for visualizing and managing Hierarchical Task Networks (HTN).
Overview
Sequence Flow is an interactive HTN Planning System that enables users to model complex planning problems through a guided AI conversation. It provides a visual representation of planning tasks as a directed graph and supports hierarchical compression of subgraphs to manage complexity while preserving cross-boundary references.
Key Features
- Interactive Modeling: Guided AI conversation for complex planning problems
- Directed Graph Visualization: Planning tasks displayed as a directed graph with complex dependencies
- Hierarchical Compression: Compress subgraphs to manage complexity while preserving references
- Three-Column Interface: AI chat, interactive graph, and hierarchical task list
- Iterative Problem Solving: Dynamic question selection based on current planning state
- External Persistence: Prevents data loss from LLM context limitations
Project Structure
sequence_flow/
├── lib/
│ ├── behaviors/ # Implements HTN planning behaviors
│ ├── models/ # Data models for the application
│ │ └── entities/ # Core entity definitions
│ ├── screens/ # Application screens
│ ├── services/ # External service integrations
│ ├── utils/ # Utility functions and helpers
│ └── widgets/ # Reusable UI components
├── assets/ # Static assets (icons, images)
└── test/ # Unit and widget tests
Getting Started
Prerequisites
- Flutter (>= 3.6.1)
- Dart (>= 3.6.0)
- An IDE (VS Code, Android Studio, or IntelliJ)
Installation
-
Clone the repository:
git clone https://github.com/yourusername/sequence_flow.git cd sequence_flow -
Install dependencies:
flutter pub get -
Run the app:
flutter run
Core Components
Entities
- Task: The fundamental building block of HTN planning
- Method: Defines ways to decompose a compound task
- TaskDecomposition: Hierarchical relationship between tasks
- TaskDependency: Non-hierarchical dependencies between tasks
- CrossBoundaryReference: References that span compressed subgraph boundaries
- WorldState: Representation of world states during planning
- Plan: Solution to a planning problem
- Conversation: AI-guided planning conversation
Behaviors
- HierarchicalCompression: Manages compression/expansion of subgraphs
- AIGuidedPlanning: Controls the AI-driven planning conversation
- GraphStateManagement: Manages persistence and history of graph state
User Interface
- ThreeColumnLayout: Main application layout with three panels
- AIChat: Left column for conversation with AI
- DirectedGraph: Middle column for graph visualization
- TaskList: Right column for hierarchical task view
Development
Code Style
This project follows the official Dart style guide and uses the recommended Flutter lints.
Building
Build for web deployment:
flutter build web
Acknowledgments
- This project is based on HTN planning techniques for complex domain modeling
- The UI/UX design is inspired by modern graph visualization tools
Recommended Servers
Sequential Thinking MCP Server
This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.
mixpanel
Connect to your Mixpanel data. Query events, retention, and funnel data from Mixpanel analytics.
MCP PubMed Search
Server to search PubMed (PubMed is a free, online database that allows users to search for biomedical and life sciences literature). I have created on a day MCP came out but was on vacation, I saw someone post similar server in your DB, but figured to post mine.
dbt Semantic Layer MCP Server
A server that enables querying the dbt Semantic Layer through natural language conversations with Claude Desktop and other AI assistants, allowing users to discover metrics, create queries, analyze data, and visualize results.
Crypto Price & Market Analysis MCP Server
A Model Context Protocol (MCP) server that provides comprehensive cryptocurrency analysis using the CoinCap API. This server offers real-time price data, market analysis, and historical trends through an easy-to-use interface.
Vectorize
Vectorize MCP server for advanced retrieval, Private Deep Research, Anything-to-Markdown file extraction and text chunking.
Nefino MCP Server
Provides large language models with access to news and information about renewable energy projects in Germany, allowing filtering by location, topic (solar, wind, hydrogen), and date range.
MATLAB MCP Server
Integrates MATLAB with AI to execute code, generate scripts from natural language, and access MATLAB documentation seamlessly.
Macrostrat MCP Server
Enables Claude to query comprehensive geologic data from the Macrostrat API, including geologic units, columns, minerals, and timescales through natural language.
MCP Word Counter
A Model Context Protocol server that provides tools for analyzing text documents, including counting words and characters. This server helps LLMs perform text analysis tasks by exposing simple document statistics functionality.