Codebuddy

A lightweight Cognitive Scaffolding Platform that provides advanced task decomposition, metacognitive guidance, and intelligent memory for AI agents.

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "jacklatrobe-codebuddy-mcp": {
      "command": "python",
      "args": [
        "codebuddy.py",
        "--host",
        "0.0.0.0",
        "--port",
        "8000"
      ]
    }
  }
}

Codebuddy MCP Server is a lightweight Cognitive Scaffolding Platform that guides AI agents through smart task planning, metacognitive prompts, and persistent cognitive memory. It helps teams decompose complex problems, track progress, and learn from past projects to improve future outcomes.

How to use

You interact with Codebuddy MCP Server through a client that communicates with the server to create, update, and search for tasks. Use the core tools to plan new tasks, monitor progress, and analyze lessons learned from completed work. The server stores tasks in a persistent JSONL format and provides context-aware search to discover relevant patterns from prior projects.

How to install

Prerequisites: ensure you have Python installed on your system. You may also use Docker or Docker Compose for containerized deployment.

Local installation and run steps:

pip install -r requirements.txt
python codebuddy.py --host 0.0.0.0 --port 8000

Additional sections

Configuration and runtime details are provided below to help you run Codebuddy MCP Server in your environment. This server accepts command-line arguments to customize host, port, data storage, and logging levels. The persistent task store is a JSONL file with one JSON object per line, enabling append-only history with cognitive metadata.

Common runtime commands to start the server in local development or containerized environments are shown here. Use these exactly as written to ensure proper operation.

# Local development
python codebuddy.py --host 0.0.0.0 --port 8000

# Docker (build and run)
docker build -t codebuddy-mcp .
docker run -p 8000:8000 -v $(pwd)/data:/app/data codebuddy-mcp

# Docker Compose
docker-compose up -d

Available tools

plan_task

Create a new task with generated steps, enabling hierarchical planning for complex problems.

update_task

Update task progress with status and notes to capture learning and insights.

list_tasks

Retrieve recent tasks to monitor ongoing work and focus areas.

search_tasks

Find tasks by keyword to surface related projects and patterns.

summarize_lessons

Analyze successful patterns and blockers to extract actionable insights.