Tpc Server

🚀 TPC Server

Track the thought process 🧠, plans 📝, and change logs ✅ of your AI agents (or projects)!

The TPC Server provides a backend service for recording, storing, and retrieving inference processes, intentional behaviors, and execution steps in AI agents or collaborative projects. This server is built using FastAPI, MCP-Server, and SQLAlchemy.

🚀 Quick Start

Installation

1. Clone the repository:

git clone [https://github.com/suttonwilliamd/tpc-server.git](https://github.com/suttonwilliamd/tpc-server.git)
cd tpc-server

2. Create and activate a virtual environment:

# Create the environment
python -m venv venv

# Activate (macOS/Linux)
source venv/bin/activate

# Activate (Windows - Git Bash/WSL)
source venv/Scripts/activate

# Activate (Windows - Command Prompt/PowerShell)
.\venv\Scripts\activate

3. Install dependencies:

pip install -r requirements.txt

4. Configure the environment: Create a .env file in the project root directory:

DATABASE_URL=sqlite:///tpc_server.db

5. Run the server:

python main.py

✨ Features

• 🧠 Track thoughts, 📝 make plans, and ✅ record changes: Provide dedicated models and storage for each concept.
• 🔗 Interconnected data: Associate thoughts with plans (many-to-many) and changes as steps executed for specific plans (many-to-one).
• 🌐 Web interface: A simple HTML view for browsing recent activities, thoughts, plans, and change logs.
• 🔌 JSON API: Provide endpoints for programmatic data retrieval (recent activities, all thoughts/plans/changes).
• 🤖 Agent tools (MCP): Provide functions through mcp-server to enable AI agents to interact with TPC storage (add_thought, create_plan, log_change, get_...).
• 💾 Database backend: Use SQLAlchemy, defaulting to SQLite, and can be easily configured to other databases via URL.
• ⚙️ Configurability: Set the DB URL, host, port, and agent communication transport (SSE/stdio) through the .env file.
• 🪄 Automatic table creation: Automatically create database tables on the first run if they do not exist.

🤔 What is TPC?

The core idea is to create a structured and interconnected log:

• Thoughts (🧠): Record insights, ideas, observations, considerations, or data points before actions.
• Plans (📝): Define the intended actions, strategies, goals, or methods, usually derived from the thought process.
• Changes (✅): Record the actual executed operations or modifications, usually associated with specific plans.

This server helps record these items and their relationships (Thoughts <-> Plans -> Changes).

📚 Documentation

Database

• By default, it uses an SQLite file (tpc_server.db) located in the project directory - simple and does not require a separate database server.
• You can easily switch to other databases such as PostgreSQL, MySQL by changing the DATABASE_URL in .env and installing the corresponding driver (e.g., pip install psycopg2-binary).
• Tables are automatically created by SQLAlchemy at startup if they do not exist.

🙌 Contribution

Contributions, issues, and feature requests are welcome! Please feel free to check the issues page or submit a pull request.