OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Workflow Agents

AI Documentation Generator

AI Documentation Generator is a Python command-line tool and Claude Code plugin that uses coordinated AI agents to analyze code repositories and generate project documentation and coding-assistant configuration files. Its analysis covers structure, dependencies, data flow, request flow and APIs; a GitLab cronjob mode can process active projects and open merge requests with updated documentation.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

AI Documentation Generator — OpenViST project profile in Workflow Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a repository needs structured codebase analysis translated into a README or AI-assistant guidance, or when a GitLab team wants a scheduled review flow that proposes updated documentation through merge requests.

Who it is for

  • Development teams maintaining repository documentation and architecture notes.
  • Teams preparing repository-specific instructions for Claude Code, other AI coding assistants or Cursor.
  • GitLab teams seeking scheduled documentation refreshes delivered as merge requests.

Documented uses

  • Map code structure, dependencies, data flow, request flow and APIs into reusable analysis documents.
  • Generate a README with configurable sections.
  • Generate CLAUDE.md, AGENTS.md and Cursor rule files for coding-assistant context.
  • Schedule analysis of active GitLab projects and open merge requests containing refreshed documentation.
Before you choose

Requirements & limits

The repository is public and licensed under MIT. The CLI prerequisites include Python 3.13, Git and API access to an OpenAI-compatible LLM provider. The documented Claude Code plugin installation is stated to require neither Python setup nor API keys.

  • Choose the CLI route if you need repository analysis and configurable outputs; it requires Python, Git and LLM-provider API access.
  • The Claude Code plugin provides three skills for analysis, README generation and AI-rule generation, with different setup prerequisites from the CLI route.
  • GitLab scheduled processing is explicitly described as discovering active projects and creating merge requests; other workflow integrations are not specified.
  • The README describes support for OpenAI-compatible APIs, including hosted and local-model options, with per-agent model and endpoint settings.
  • A Dockerfile and Helm chart are included for containerized and scheduled Kubernetes deployment.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install the CLI and configure a repository

Set up the Python CLI environment and prepare its environment and project configuration files.

Before you start

  • Python 3.13
  • Git
  • API access to an OpenAI-compatible LLM provider
  • A shell and access to the repository

Steps

  1. Clone the repository and change into its directory.

  2. Install dependencies with uv using the command below, or install the project with the command below.

    Documented command
    uv sync
    Documented command
    pip install -e .

  3. Copy .env.sample to .env and configure the LLM environment values.

  4. Create .ai/config.yaml by copying config_example.yaml and edit the configuration.

Expected outcome

The local project environment and configuration files are prepared for the documented analysis and generation commands.

Guide limitations

  • This guide covers setup only; it does not claim that analysis or generation has been run.
  • LLM provider API access is required for the CLI workflow.
Documentation 1 ↗
Source-based practical guide

Analyze a repository and generate documentation files

Use the documented CLI commands to analyze a repository and request README and AI-assistant configuration generation.

Before you start

  • The CLI environment and configuration prepared for the target repository
  • API access to an OpenAI-compatible LLM provider

Steps

  1. Run the command below for the target repository.

    Documented command
    uv run src/main.py analyze --repo-path

  2. Run the command below to request README generation.

    Documented command
    uv run src/main.py generate readme --repo-path

  3. Run the command below to request assistant configuration generation.

    Documented command
    uv run src/main.py generate ai-rules --repo-path

Expected outcome

The documented output locations are `.ai/docs/` for analysis documents and the repository root for generated documentation and assistant configuration files.

Guide limitations

  • The commands and output locations are described in the project README; this recipe is not an execution test.
  • Generated assistant files include CLAUDE.md, AGENTS.md and Cursor rules.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Agent orchestration

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
AI Documentation GeneratorMap code structure, dependencies, data flow, request flow and APIs into reusable analysis documents.CLI, Server, Self-hostedThe repository is public and licensed under MIT. The CLI prerequisites include Python 3.13, Git and API access to an OpenAI-compatible LLM provider. The documented Claude Code plugin installation is stated to require neither Python setup nor API keys.
Agentic AI Helpdesk PlatformClassify tickets by issue domain and category, and estimate urgency and complexity.Cloud, Docker, Web
TgoConfigure multiple AI agents for different customer-service scenarios and connect supported LLM providers.Docker, Self-hosted, ServerThe repository describes Tgo as open source and provides self-hosting instructions. Its README lists minimum server requirements of four CPU cores and 8 GiB of RAM; local development setup lists macOS, Linux, and WSL2.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
7 November 2026
Original website title
divar-ir/ai-doc-gen · Official homepage title · retained in its source language
How we review sourcesSuggest a correction