FloGuru

January 27, 2026 Β· View on GitHub

FloGuru is an open, AI-powered automation platform built around smart "Guru" agents. It enables flexible workflow automation that connects browser automation, chat integrations (Telegram, WhatsApp, Discord, etc.), and continual learning via self-improvement mechanisms. FloGuru provides modular backend, frontend, and Python packages for seamless LLM-based task execution, human-in-the-loop actions, and rapid extensibility.


✨ Features

  • AI Reasoning Gurus: Specialized agents that use advanced LLMs (e.g., DeepSeek, Gemini) to understand and automate complex tasks.
  • Browser Automation: Python-based headless control for end-to-end browser workflows.
  • Self-Improvement: HyperHealing technology learns from past successes for better future task execution.
  • Chat Integrations: Out-of-the-box gateways for Telegram, WhatsApp, Discord, and more.
  • Modular Architecture: Decoupled code for API/backend, frontend, chat gateway, shared logic, and automation, making extension easy.

πŸ—‚οΈ Project Structure

Directory Tree
guru/
β”œβ”€β”€ apps/
β”‚   β”œβ”€β”€ api/              # Backend API (Node.js + Express)
β”‚   β”‚   β”œβ”€β”€ src/
β”‚   β”‚   β”‚   β”œβ”€β”€ index.ts           # Main entry point
β”‚   β”‚   β”‚   β”œβ”€β”€ routes/            # API endpoints
β”‚   β”‚   β”‚   β”œβ”€β”€ services/          # Business logic
β”‚   β”‚   β”‚   β”‚   β”œβ”€β”€ aiService.ts   # AI/LLM integration
β”‚   β”‚   β”‚   β”‚   β”œβ”€β”€ guruService.ts # Guru management
β”‚   β”‚   β”‚   β”‚   └── guruExecutorService.ts # Task execution
β”‚   β”‚   β”‚   └── lib/               # Utilities
β”‚   β”‚   └── Dockerfile
β”‚   └── web/              # Frontend (Next.js)
β”‚       └── src/
β”œβ”€β”€ packages/
β”‚   β”œβ”€β”€ database/         # Database schema (Drizzle ORM)
β”‚   β”œβ”€β”€ guru-core/        # Core logic
β”‚   └── shared/           # Shared utilities
β”œβ”€β”€ guru-gateway/         # Chat integration gateway
β”‚   └── src/
β”‚       └── GuruGateway.ts
β”œβ”€β”€ browser-use/          # Python browser automation
β”‚   └── python_bridge/
└── .github/workflows/    # CI/CD (GitHub Actions)

πŸš€ Getting Started

1. Install Dependencies

# Root install
npm install

# If using workspaces, install individually too:
cd apps/api && npm install
cd apps/web && npm install
cd packages/database && npm install
cd packages/guru-core && npm install
cd packages/shared && npm install

2. Run the API Backend

cd apps/api
npm run dev
# or docker compose up

3. Run the Frontend

cd apps/web
npm run dev

4. Python Automation (Browser Use)

cd browser-use/python_bridge
# (Set up virtualenv)
pip install -r requirements.txt

πŸ§‘β€πŸ’» Contributing

  • Follow GitHub Flow for all code changesβ€”make a branch, open a PR, get CI passing.
  • Use clear, descriptive commit messages and PR titles.
  • Add/Update documentation for any new features in related module/package.
  • For any new background jobs, include tests and a default-off feature flag.
  • Do NOT commit secrets or real API credentialsβ€”use .env.example for placeholders only.

πŸ“„ License

This project is licensed under the MIT License.


FloGuru: Automate anything with AI. Join the communityβ€”collaborate, share agents, and push the boundaries of workflow automation!