Skip to content

Repository files navigation

Hexagonal Agents

A web-based tool that processes markdown notes using sequential LLM-powered agent pipelines to enforce formatting, grammar, tagging, and content enhancement guidelines.

📋 Project Documentation

Core Project Documents

Backend Documentation

Sample Data

🚀 Quick Start

  1. Clone and Setup

    cd src/backend
    python -m pip install -r requirements.txt
  2. Configure Environment

    cp .env.example .env
    # Edit .env with your LLM provider settings
  3. Run CLI Example

    python src.backend.app.adapters.cli.agent_cli execute grammar --text "Your markdown text here"

🏗️ Architecture

This project implements a hexagonal architecture with:

  • Domain Models: Agent, LLMProvider, AgentResult entities
  • Provider Factory: LLM provider abstraction (OpenAI, LM Studio)
  • Pipeline Engine: Sequential agent execution
  • CLI Adapter: Command-line interface for processing

📝 Available Agents

  • Grammar: Corrects grammatical errors
  • Tag: Adds semantic tags to content
  • Link: Processes and validates links

🔧 Development

See the backend documentation for detailed development instructions, testing procedures, and usage examples.

📄 License

See LICENSE file for details.

About

Sequential LLM agent pipelines that lint, tag and enhance markdown notes — hexagonal architecture with a FastAPI backend and web UI

Topics

Resources

Stars

2 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages