| Crates.io | azathoth |
| lib.rs | azathoth |
| version | 0.0.1 |
| created_at | 2025-10-18 16:09:08.086507+00 |
| updated_at | 2025-10-18 16:09:08.086507+00 |
| description | Some of the stuff I've created while learning the 'State of the Art' in AI. |
| homepage | |
| repository | |
| max_upload_size | |
| id | 1889346 |
| size | 4,312 |
My personal AI architect and development partner, designed to enforce high-level coding standards and automate complex workflows.
Azathoth is not just a tool; it's an opinionated AI agent framework. It serves as a collection of specialized MCP (Master Control Program) servers that encapsulate a specific, high-level development philosophy.
Note: Azathoth is the production-ready assistant, ensuring that every piece of code and every workflow adheres to predefined best practices and personal standards.
This project is a workspace containing multiple components.
For Python dependencies:
uv sync
For Rust dependencies:
cargo build --release
The Azathoth project provides a suite of tools and servers that can be integrated with any MCP-compatible AI agent or CLI:
azathoth: The main binary of the project.mcp_py: A Python implementation of an MCP client, with the following scripts:
scout: An intelligent agent that can explore a codebase and generate a comprehensive report.workflow: Automate common Git tasks with AI-powered context.mcp_rs: A Rust implementation of an MCP client, with examples like:
directives: Configure the core behavior of your AI assistant on the fly.To run the python scripts:
mcpy-py
scout
workflow
To run the rust examples from the mcp_rs package:
cargo run --package mcp-rs --example <example_name>
This project is licensed under the MIT License. See the LICENSE file for details.