divar-ir/ai-doc-gen

AI-powered multi-agent system that automatically analyzes codebases and generates comprehensive documentation. Features GitLab integration, concurrent processing, and multiple LLM support for better code understanding and developer onboarding.

What it solves

Maintaining accurate code documentation is a constant struggle as codebases evolve. This tool automates the creation and updating of comprehensive README files and AI assistant configuration files, ensuring that documentation stays current without manual effort.

How it works

The system uses a multi-agent architecture powered by pydantic-ai. It employs five specialized analysis agents that run concurrently to map the codebase's structure, dependencies, data flow, request flow, and APIs. These agents save their findings to .ai/docs/. Subsequently, generation agents use these analyses to produce a polished README.md and AI-specific configuration files like CLAUDE.md, AGENTS.md, and Cursor rules.

Who it’s for

Developers and engineering teams who want to automate their documentation workflow, particularly those using AI coding assistants (like Claude Code or Cursor) and those integrated with GitLab for automated, scheduled updates via cronjobs.

Highlights

  • Multi-Agent Analysis: Uses five specialized agents to perform deep codebase analysis across different dimensions.
  • AI Assistant Optimization: Generates specific rules and configuration files to improve the performance of AI coding assistants.
  • GitLab Integration: Includes a cronjob mode that automatically discovers active projects and opens merge requests with updated documentation.
  • Flexible LLM Support: Compatible with any OpenAI-compatible API, allowing the use of various models and providers.
  • Claude Code Plugin: Can be installed as a plugin to provide analyze-codebase, generate-readme, and generate-ai-rules skills directly within the Claude Code environment.

Related

  • Project
    claesbackman/AI-research-feedback

    A collection of Claude Code skills that automate academic peer review, grant proposal evaluation, and paper-code reproducibility checks for researchers.

  • Project
    Pluviobyte/rnskill

    A comprehensive library of 55 AI Agent skills for Codex and Claude Code that automates content creation, video production, and business diagnosis workflows.

  • Project
    pedrohcgs/claude-code-my-workflow

    A ready-to-fork foundation for AI-assisted academic work that uses specialized agents and quality gates to automate the creation and review of papers, slides, and data analysis.

  • Project
    eli64s/readme-ai

    An automated developer tool that generates professional, structured README files by analyzing a codebase using LLMs.

  • Project
    caliber-ai-org/ai-setup

    A tool that automatically generates and maintains AI agent context files to prevent hallucinations and keep AI coding assistants in sync with codebase changes.