AI Code Mentor

AI Code Mentor is a runtime environment designed for building applications with integrated autonomous AI agents. These applications are defined as workflows, written in Markdown files (.wf.md), which are interpreted and executed by the Code Mentor system.

GitHub Repo Link: https://github.com/BernLeWal/AICodeMentor

The AI agents (multiple instances are supported) generate and execute commands (e.g., Bash shell commands) directly, feeding the output back to the AI for analysis and iteration. This allows AI agents to self-improve their tasks when necessary. Currently, OpenAI's platform is integrated, with plans to add alternative AI models in the future.

Features & Benefits

Key Features

• Local Execution: Data remains local and is processed inside a Docker container, avoiding unnecessary cloud uploads.
• Autonomous Execution: AI-generated commands are executed automatically within the container, eliminating the need for manual copy-pasting.
• Multi-Agent Support: Multiple AI agents can operate simultaneously within the same workflow, distributing tasks efficiently.
• Structured Workflow Definition: Workflows define clear goals, paths, branches, and alternative solutions, providing better AI context compared to free-text prompting.
• Scalability & Automation: Execute workflows on multiple targets, e.g., grading 100+ source code submissions automatically.
• Traceability & Transparency: All AI-generated commands and their results are logged, providing visibility into the execution process.

Example Use Case: Automatic Grading of Software Development Assignments

AI Code Mentor enables autonomous evaluation of source code projects based on program requirements and specifications. The AI agents:

1. Analyze student submissions.
2. Provide feedback.
3. Assign grades automatically.
4. Iterate if necessary to refine evaluations.

This is particularly useful for software development educators, reducing manual grading effort while maintaining fairness and transparency.